From the uDemy course on LLM engineering.
https://www.udemy.com/course/llm-engineering-master-ai-and-large-language-models
1639 lines
90 KiB
1639 lines
90 KiB
{ |
|
"cells": [ |
|
{ |
|
"cell_type": "markdown", |
|
"id": "a98030af-fcd1-4d63-a36e-38ba053498fa", |
|
"metadata": {}, |
|
"source": [ |
|
"# A full business solution\n", |
|
"\n", |
|
"## Now we will take our project from Day 1 to the next level\n", |
|
"\n", |
|
"### BUSINESS CHALLENGE:\n", |
|
"\n", |
|
"Create a product that builds a Brochure for a company to be used for prospective clients, investors and potential recruits.\n", |
|
"\n", |
|
"We will be provided a company name and their primary website.\n", |
|
"\n", |
|
"See the end of this notebook for examples of real-world business applications.\n", |
|
"\n", |
|
"And remember: I'm always available if you have problems or ideas! Please do reach out." |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 1, |
|
"id": "d5b08506-dc8b-4443-9201-5f1848161363", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# imports\n", |
|
"# If these fail, please check you're running from an 'activated' environment with (llms) in the command prompt\n", |
|
"\n", |
|
"import os\n", |
|
"import requests\n", |
|
"import json\n", |
|
"from typing import List\n", |
|
"from dotenv import load_dotenv\n", |
|
"from bs4 import BeautifulSoup\n", |
|
"from IPython.display import Markdown, display, update_display\n", |
|
"from openai import OpenAI" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 2, |
|
"id": "fc5d8880-f2ee-4c06-af16-ecbc0262af61", |
|
"metadata": {}, |
|
"outputs": [ |
|
{ |
|
"name": "stdout", |
|
"output_type": "stream", |
|
"text": [ |
|
"API key looks good so far\n" |
|
] |
|
} |
|
], |
|
"source": [ |
|
"# Initialize and constants\n", |
|
"\n", |
|
"load_dotenv()\n", |
|
"api_key = os.getenv('OPENAI_API_KEY')\n", |
|
"\n", |
|
"if api_key and api_key.startswith('sk-proj-') and len(api_key)>10:\n", |
|
" print(\"API key looks good so far\")\n", |
|
"else:\n", |
|
" print(\"There might be a problem with your API key? Please visit the troubleshooting notebook!\")\n", |
|
" \n", |
|
"MODEL = 'gpt-4o-mini'\n", |
|
"openai = OpenAI()" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 3, |
|
"id": "106dd65e-90af-4ca8-86b6-23a41840645b", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# A class to represent a Webpage\n", |
|
"\n", |
|
"class Website:\n", |
|
" \"\"\"\n", |
|
" A utility class to represent a Website that we have scraped, now with links\n", |
|
" \"\"\"\n", |
|
"\n", |
|
" def __init__(self, url):\n", |
|
" self.url = url\n", |
|
" response = requests.get(url)\n", |
|
" self.body = response.content\n", |
|
" soup = BeautifulSoup(self.body, 'html.parser')\n", |
|
" self.title = soup.title.string if soup.title else \"No title found\"\n", |
|
" if soup.body:\n", |
|
" for irrelevant in soup.body([\"script\", \"style\", \"img\", \"input\"]):\n", |
|
" irrelevant.decompose()\n", |
|
" self.text = soup.body.get_text(separator=\"\\n\", strip=True)\n", |
|
" else:\n", |
|
" self.text = \"\"\n", |
|
" links = [link.get('href') for link in soup.find_all('a')]\n", |
|
" self.links = [link for link in links if link]\n", |
|
"\n", |
|
" def get_contents(self):\n", |
|
" return f\"Webpage Title:\\n{self.title}\\nWebpage Contents:\\n{self.text}\\n\\n\"" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 4, |
|
"id": "e30d8128-933b-44cc-81c8-ab4c9d86589a", |
|
"metadata": {}, |
|
"outputs": [ |
|
{ |
|
"data": { |
|
"text/plain": [ |
|
"['/cart',\n", |
|
" '#page',\n", |
|
" '/',\n", |
|
" '#services',\n", |
|
" '#about',\n", |
|
" '#contact',\n", |
|
" '/',\n", |
|
" '#services',\n", |
|
" '#about',\n", |
|
" '#contact',\n", |
|
" '#services',\n", |
|
" '#about',\n", |
|
" '#contact',\n", |
|
" '#services',\n", |
|
" 'http://squarespace.com']" |
|
] |
|
}, |
|
"execution_count": 4, |
|
"metadata": {}, |
|
"output_type": "execute_result" |
|
} |
|
], |
|
"source": [ |
|
"ed = Website(\"https://www.jaivikhimalay.com\")\n", |
|
"ed.links" |
|
] |
|
}, |
|
{ |
|
"cell_type": "markdown", |
|
"id": "1771af9c-717a-4fca-bbbe-8a95893312c3", |
|
"metadata": {}, |
|
"source": [ |
|
"## First step: Have GPT-4o-mini figure out which links are relevant\n", |
|
"\n", |
|
"### Use a call to gpt-4o-mini to read the links on a webpage, and respond in structured JSON. \n", |
|
"It should decide which links are relevant, and replace relative links such as \"/about\" with \"https://company.com/about\". \n", |
|
"We will use \"one shot prompting\" in which we provide an example of how it should respond in the prompt.\n", |
|
"\n", |
|
"This is an excellent use case for an LLM, because it requires nuanced understanding. Imagine trying to code this without LLMs by parsing and analyzing the webpage - it would be very hard!\n", |
|
"\n", |
|
"Sidenote: there is a more advanced technique called \"Structured Outputs\" in which we require the model to respond according to a spec. We cover this technique in Week 8 during our autonomous Agentic AI project." |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 5, |
|
"id": "6957b079-0d96-45f7-a26a-3487510e9b35", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"link_system_prompt = \"You are provided with a list of links found on a webpage. \\\n", |
|
"You are able to decide which of the links would be most relevant to include in a brochure about the company, \\\n", |
|
"such as links to an About page, or a Company page, or Careers/Jobs pages.\\n\"\n", |
|
"link_system_prompt += \"You should respond in JSON as in this example:\"\n", |
|
"link_system_prompt += \"\"\"\n", |
|
"{\n", |
|
" \"links\": [\n", |
|
" {\"type\": \"about page\", \"url\": \"https://full.url/goes/here/about\"},\n", |
|
" {\"type\": \"careers page\": \"url\": \"https://another.full.url/careers\"}\n", |
|
" ]\n", |
|
"}\n", |
|
"\"\"\"" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 6, |
|
"id": "b97e4068-97ed-4120-beae-c42105e4d59a", |
|
"metadata": {}, |
|
"outputs": [ |
|
{ |
|
"name": "stdout", |
|
"output_type": "stream", |
|
"text": [ |
|
"You are provided with a list of links found on a webpage. You are able to decide which of the links would be most relevant to include in a brochure about the company, such as links to an About page, or a Company page, or Careers/Jobs pages.\n", |
|
"You should respond in JSON as in this example:\n", |
|
"{\n", |
|
" \"links\": [\n", |
|
" {\"type\": \"about page\", \"url\": \"https://full.url/goes/here/about\"},\n", |
|
" {\"type\": \"careers page\": \"url\": \"https://another.full.url/careers\"}\n", |
|
" ]\n", |
|
"}\n", |
|
"\n" |
|
] |
|
} |
|
], |
|
"source": [ |
|
"print(link_system_prompt)" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 7, |
|
"id": "8e1f601b-2eaf-499d-b6b8-c99050c9d6b3", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"def get_links_user_prompt(website):\n", |
|
" user_prompt = f\"Here is the list of links on the website of {website.url} - \"\n", |
|
" user_prompt += \"please decide which of these are relevant web links for a brochure about the company, respond with the full https URL in JSON format. \\\n", |
|
"Do not include Terms of Service, Privacy, email links.\\n\"\n", |
|
" user_prompt += \"Links (some might be relative links):\\n\"\n", |
|
" user_prompt += \"\\n\".join(website.links)\n", |
|
" return user_prompt" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 8, |
|
"id": "6bcbfa78-6395-4685-b92c-22d592050fd7", |
|
"metadata": {}, |
|
"outputs": [ |
|
{ |
|
"name": "stdout", |
|
"output_type": "stream", |
|
"text": [ |
|
"Here is the list of links on the website of https://www.jaivikhimalay.com - please decide which of these are relevant web links for a brochure about the company, respond with the full https URL in JSON format. Do not include Terms of Service, Privacy, email links.\n", |
|
"Links (some might be relative links):\n", |
|
"/cart\n", |
|
"#page\n", |
|
"/\n", |
|
"#services\n", |
|
"#about\n", |
|
"#contact\n", |
|
"/\n", |
|
"#services\n", |
|
"#about\n", |
|
"#contact\n", |
|
"#services\n", |
|
"#about\n", |
|
"#contact\n", |
|
"#services\n", |
|
"http://squarespace.com\n" |
|
] |
|
} |
|
], |
|
"source": [ |
|
"print(get_links_user_prompt(ed))" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 9, |
|
"id": "a29aca19-ca13-471c-a4b4-5abbfa813f69", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"def get_links(url):\n", |
|
" website = Website(url)\n", |
|
" response = openai.chat.completions.create(\n", |
|
" model=MODEL,\n", |
|
" messages=[\n", |
|
" {\"role\": \"system\", \"content\": link_system_prompt},\n", |
|
" {\"role\": \"user\", \"content\": get_links_user_prompt(website)}\n", |
|
" ],\n", |
|
" response_format={\"type\": \"json_object\"}\n", |
|
" )\n", |
|
" result = response.choices[0].message.content\n", |
|
" return json.loads(result)" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 10, |
|
"id": "74a827a0-2782-4ae5-b210-4a242a8b4cc2", |
|
"metadata": {}, |
|
"outputs": [ |
|
{ |
|
"data": { |
|
"text/plain": [ |
|
"['/',\n", |
|
" '/claude',\n", |
|
" '/team',\n", |
|
" '/enterprise',\n", |
|
" '/api',\n", |
|
" '/pricing',\n", |
|
" '/research',\n", |
|
" '/company',\n", |
|
" '/careers',\n", |
|
" '/news',\n", |
|
" 'https://www.anthropic.com/research#entry:8@1:url',\n", |
|
" 'https://www.anthropic.com/claude',\n", |
|
" 'https://claude.ai/',\n", |
|
" '/api',\n", |
|
" '/news/3-5-models-and-computer-use',\n", |
|
" '/claude/sonnet',\n", |
|
" '/claude/haiku',\n", |
|
" '/news/claude-for-enterprise',\n", |
|
" '/research/constitutional-ai-harmlessness-from-ai-feedback',\n", |
|
" '/news/core-views-on-ai-safety',\n", |
|
" '/jobs',\n", |
|
" '/',\n", |
|
" '/claude',\n", |
|
" '/api',\n", |
|
" '/team',\n", |
|
" '/pricing',\n", |
|
" '/research',\n", |
|
" '/company',\n", |
|
" '/customers',\n", |
|
" '/news',\n", |
|
" '/careers',\n", |
|
" 'mailto:press@anthropic.com',\n", |
|
" 'https://support.anthropic.com/',\n", |
|
" 'https://status.anthropic.com/',\n", |
|
" '/supported-countries',\n", |
|
" 'https://twitter.com/AnthropicAI',\n", |
|
" 'https://www.linkedin.com/company/anthropicresearch',\n", |
|
" 'https://www.youtube.com/@anthropic-ai',\n", |
|
" '/legal/consumer-terms',\n", |
|
" '/legal/commercial-terms',\n", |
|
" '/legal/privacy',\n", |
|
" '/legal/aup',\n", |
|
" '/responsible-disclosure-policy',\n", |
|
" 'https://trust.anthropic.com/']" |
|
] |
|
}, |
|
"execution_count": 10, |
|
"metadata": {}, |
|
"output_type": "execute_result" |
|
} |
|
], |
|
"source": [ |
|
"anthropic = Website(\"https://anthropic.com\")\n", |
|
"anthropic.links" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 11, |
|
"id": "d3d583e2-dcc4-40cc-9b28-1e8dbf402924", |
|
"metadata": {}, |
|
"outputs": [ |
|
{ |
|
"data": { |
|
"text/plain": [ |
|
"{'links': [{'type': 'about page', 'url': 'https://anthropic.com/company'},\n", |
|
" {'type': 'careers page', 'url': 'https://anthropic.com/careers'},\n", |
|
" {'type': 'team page', 'url': 'https://anthropic.com/team'},\n", |
|
" {'type': 'research page', 'url': 'https://anthropic.com/research'},\n", |
|
" {'type': 'news page', 'url': 'https://anthropic.com/news'}]}" |
|
] |
|
}, |
|
"execution_count": 11, |
|
"metadata": {}, |
|
"output_type": "execute_result" |
|
} |
|
], |
|
"source": [ |
|
"get_links(\"https://anthropic.com\")" |
|
] |
|
}, |
|
{ |
|
"cell_type": "markdown", |
|
"id": "0d74128e-dfb6-47ec-9549-288b621c838c", |
|
"metadata": {}, |
|
"source": [ |
|
"## Second step: make the brochure!\n", |
|
"\n", |
|
"Assemble all the details into another prompt to GPT4-o" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 12, |
|
"id": "85a5b6e2-e7ef-44a9-bc7f-59ede71037b5", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"def get_all_details(url):\n", |
|
" result = \"Landing page:\\n\"\n", |
|
" result += Website(url).get_contents()\n", |
|
" links = get_links(url)\n", |
|
" print(\"Found links:\", links)\n", |
|
" for link in links[\"links\"]:\n", |
|
" result += f\"\\n\\n{link['type']}\\n\"\n", |
|
" result += Website(link[\"url\"]).get_contents()\n", |
|
" return result" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 13, |
|
"id": "5099bd14-076d-4745-baf3-dac08d8e5ab2", |
|
"metadata": {}, |
|
"outputs": [ |
|
{ |
|
"name": "stdout", |
|
"output_type": "stream", |
|
"text": [ |
|
"Found links: {'links': [{'type': 'about page', 'url': 'https://www.anthropic.com/company'}, {'type': 'careers page', 'url': 'https://www.anthropic.com/careers'}, {'type': 'team page', 'url': 'https://www.anthropic.com/team'}, {'type': 'research page', 'url': 'https://www.anthropic.com/research'}, {'type': 'news page', 'url': 'https://www.anthropic.com/news'}]}\n", |
|
"Landing page:\n", |
|
"Webpage Title:\n", |
|
"Home \\ Anthropic\n", |
|
"Webpage Contents:\n", |
|
"Claude\n", |
|
"Overview\n", |
|
"Team\n", |
|
"Enterprise\n", |
|
"API\n", |
|
"Pricing\n", |
|
"Research\n", |
|
"Company\n", |
|
"Careers\n", |
|
"News\n", |
|
"AI\n", |
|
"research\n", |
|
"and\n", |
|
"products\n", |
|
"that put safety at the frontier\n", |
|
"Claude.ai\n", |
|
"Meet Claude 3.5 Sonnet\n", |
|
"Claude 3.5 Sonnet, our most intelligent AI model, is now available.\n", |
|
"Talk to Claude\n", |
|
"API\n", |
|
"Build with Claude\n", |
|
"Start using Claude to drive efficiency and create new revenue streams.\n", |
|
"Learn more\n", |
|
"Announcements\n", |
|
"Introducing computer use, a new Claude 3.5 Sonnet, and Claude 3.5 Haiku\n", |
|
"Oct 22, 2024\n", |
|
"Model updates\n", |
|
"3.5 Sonnet\n", |
|
"3.5 Haiku\n", |
|
"Our Work\n", |
|
"Product\n", |
|
"Claude for Enterprise\n", |
|
"Sep 4, 2024\n", |
|
"Alignment\n", |
|
"·\n", |
|
"Research\n", |
|
"Constitutional AI: Harmlessness from AI Feedback\n", |
|
"Dec 15, 2022\n", |
|
"Announcements\n", |
|
"Core Views on AI Safety: When, Why, What, and How\n", |
|
"Mar 8, 2023\n", |
|
"Work with Anthropic\n", |
|
"Anthropic is an AI safety and research company based in San Francisco. Our interdisciplinary team has experience across ML, physics, policy, and product. Together, we generate research and create reliable, beneficial AI systems.\n", |
|
"See open roles\n", |
|
"Claude\n", |
|
"API\n", |
|
"Team\n", |
|
"Pricing\n", |
|
"Research\n", |
|
"Company\n", |
|
"Customers\n", |
|
"News\n", |
|
"Careers\n", |
|
"Press Inquiries\n", |
|
"Support\n", |
|
"Status\n", |
|
"Availability\n", |
|
"Twitter\n", |
|
"LinkedIn\n", |
|
"YouTube\n", |
|
"Terms of Service – Consumer\n", |
|
"Terms of Service – Commercial\n", |
|
"Privacy Policy\n", |
|
"Usage Policy\n", |
|
"Responsible Disclosure Policy\n", |
|
"Compliance\n", |
|
"Privacy Choices\n", |
|
"© 2024 Anthropic PBC\n", |
|
"\n", |
|
"\n", |
|
"\n", |
|
"about page\n", |
|
"Webpage Title:\n", |
|
"Company \\ Anthropic\n", |
|
"Webpage Contents:\n", |
|
"Claude\n", |
|
"Overview\n", |
|
"Team\n", |
|
"Enterprise\n", |
|
"API\n", |
|
"Pricing\n", |
|
"Research\n", |
|
"Company\n", |
|
"Careers\n", |
|
"News\n", |
|
"Making AI systems\n", |
|
"you can rely on\n", |
|
"Anthropic is an AI safety and research company. We build reliable, interpretable, and steerable AI systems.\n", |
|
"Join us\n", |
|
"Our Purpose\n", |
|
"We believe AI will have a vast impact on the world. Anthropic is dedicated to building systems that people can rely on and generating research about the opportunities and risks of AI.\n", |
|
"We Build Safer Systems\n", |
|
"We aim to build frontier AI systems that are reliable, interpretable, and steerable. We conduct frontier research, develop and apply a variety of safety techniques, and deploy the resulting systems via a set of partnerships and products.\n", |
|
"Safety Is a Science\n", |
|
"We treat AI safety as a systematic science, conducting research, applying it to our products, feeding those insights back into our research, and regularly sharing what we learn with the world along the way.\n", |
|
"Interdisciplinary\n", |
|
"Anthropic is a collaborative team of researchers, engineers, policy experts, business leaders and operators, who bring our experience from many different domains to our work.\n", |
|
"AI Companies are One Piece of a Big Puzzle\n", |
|
"AI has the potential to fundamentally change how the world works. We view ourselves as just one piece of this evolving puzzle. We collaborate with civil society, government, academia, nonprofits and industry to promote safety industry-wide.\n", |
|
"The Team\n", |
|
"We’re a team of researchers, engineers, policy experts and operational leaders, with experience spanning a variety of disciplines, all working together to build reliable and understandable AI systems.\n", |
|
"Research\n", |
|
"We conduct frontier AI research across a variety of modalities, and explore novel and emerging safety research areas from interpretability to RL from human feedback to policy and societal impacts analysis.\n", |
|
"Policy\n", |
|
"We think about the impacts of our work and strive to communicate what we’re seeing at the frontier to policymakers and civil society in the US and abroad to help promote safe and reliable AI.\n", |
|
"Product\n", |
|
"We translate our research into tangible, practical tools like Claude that benefit businesses, nonprofits and civil society groups and their clients and people around the globe.\n", |
|
"Operations\n", |
|
"Our people, finance, legal, and recruiting teams are the human engines that make Anthropic go. We’ve had previous careers at NASA, startups, and the armed forces and our diverse experiences help make Anthropic a great place to work (and we love plants!).\n", |
|
"Our Values\n", |
|
"01\n", |
|
"Here for the mission\n", |
|
"Anthropic exists for our mission: to ensure transformative AI helps people and society flourish. Progress this decade may be rapid, and we expect increasingly capable systems to pose novel challenges. We pursue our mission by building frontier systems, studying their behaviors, working to responsibly deploy them, and regularly sharing our safety insights. We collaborate with other projects and stakeholders seeking a similar outcome.\n", |
|
"02\n", |
|
"Unusually high trust\n", |
|
"Our company is an unusually high trust environment: we assume good faith, disagree kindly, and prioritize honesty. We expect emotional maturity and intellectual openness. At its best, our trust enables us to make better decisions as an organization than any one of us could as individuals.\n", |
|
"03\n", |
|
"One big team\n", |
|
"Collaboration is central to our work, culture, and value proposition. While we have many teams at Anthropic, we feel the broader sense in which we are all on the same team working together towards the mission. Leadership sets the strategy, with broad input from everyone, and trusts each piece of the organization to pursue these goals in their unique style. Individuals commonly contribute to work across many different areas.\n", |
|
"04\n", |
|
"Do the simple thing that works\n", |
|
"We celebrate trying the simple thing before the clever, novel thing. We embrace pragmatism - sensible, practical approaches that acknowledge tradeoffs. We love empiricism - finding out what actually works by trying it - and apply this to our research, our engineering and our collaboration. We aim to be open about what we understand and what we don’t.\n", |
|
"Governance\n", |
|
"Anthropic is a Public Benefit Corporation, whose purpose is the responsible development and maintenance of advanced AI for the long-term benefit of humanity. Our Board of Directors is elected by stockholders and our Long-Term Benefit Trust, as explained\n", |
|
"here.\n", |
|
"Current members of the Board and the Long-Term Benefit Trust (LTBT) are listed below.\n", |
|
"Anthropic Board of Directors\n", |
|
"Dario Amodei, Daniela Amodei, Yasmin Razavi, and Jay Kreps.\n", |
|
"LTBT Trustees\n", |
|
"Neil Buddy Shah, Kanika Bahl, and Zach Robinson.\n", |
|
"Company News\n", |
|
"See All\n", |
|
"Announcements\n", |
|
"Introducing the Model Context Protocol\n", |
|
"Nov 25, 2024\n", |
|
"Announcements\n", |
|
"Powering the next generation of AI development with AWS\n", |
|
"Nov 22, 2024\n", |
|
"Announcements\n", |
|
"Claude 3.5 Sonnet on GitHub Copilot\n", |
|
"Oct 29, 2024\n", |
|
"Want to help us build the future of safe AI?\n", |
|
"Join us\n", |
|
"Claude\n", |
|
"API\n", |
|
"Team\n", |
|
"Pricing\n", |
|
"Research\n", |
|
"Company\n", |
|
"Customers\n", |
|
"News\n", |
|
"Careers\n", |
|
"Press Inquiries\n", |
|
"Support\n", |
|
"Status\n", |
|
"Availability\n", |
|
"Twitter\n", |
|
"LinkedIn\n", |
|
"YouTube\n", |
|
"Terms of Service – Consumer\n", |
|
"Terms of Service – Commercial\n", |
|
"Privacy Policy\n", |
|
"Usage Policy\n", |
|
"Responsible Disclosure Policy\n", |
|
"Compliance\n", |
|
"Privacy Choices\n", |
|
"© 2024 Anthropic PBC\n", |
|
"\n", |
|
"\n", |
|
"\n", |
|
"careers page\n", |
|
"Webpage Title:\n", |
|
"Careers \\ Anthropic\n", |
|
"Webpage Contents:\n", |
|
"Claude\n", |
|
"Overview\n", |
|
"Team\n", |
|
"Enterprise\n", |
|
"API\n", |
|
"Pricing\n", |
|
"Research\n", |
|
"Company\n", |
|
"Careers\n", |
|
"News\n", |
|
"Join the team\n", |
|
"making AI safe\n", |
|
"We’re a public benefit corporation headquartered in San Francisco. Our team’s experience spans a variety of backgrounds and disciplines, from physics and machine learning to public policy and business. We work as a cohesive team that collectively forecasts the impact and tractability of research ideas in advancing our mission.\n", |
|
"See open roles\n", |
|
"What We Offer\n", |
|
"Health & Wellness\n", |
|
"At Anthropic, we believe that supporting our employees is crucial to our collective success and wellbeing. That's why we offer a range of benefits to best support you and your family, now and in the future.\n", |
|
"Comprehensive health, dental, and vision insurance for you and your dependents\n", |
|
"Inclusive fertility benefits via Carrot Fertility\n", |
|
"22 weeks of paid parental leave\n", |
|
"Flexible paid time off and absence policies\n", |
|
"Generous mental health support for you and your dependents\n", |
|
"Compensation & Support\n", |
|
"Our goal is to foster an environment where you can thrive professionally while feeling confident that you and your loved ones are taken care of.\n", |
|
"Competitive salary and equity packages\n", |
|
"Optional equity donation matching at a 1:1 ratio, up to 25% of your equity grant\n", |
|
"Robust retirement plans and salary sacrifice programs with market competitive matching\n", |
|
"Life and income protection plans\n", |
|
"Additional Benefits\n", |
|
"$500/month flexible wellness and time saver stipend\n", |
|
"Commuter benefits\n", |
|
"Annual education stipend\n", |
|
"Home office stipends\n", |
|
"Relocation support for those moving for Anthropic\n", |
|
"Daily meals and snacks in the office\n", |
|
"How We Hire\n", |
|
"The interview process at Anthropic varies based on role and candidate, but our standard process looks like this:\n", |
|
"Step 1\n", |
|
"Resume\n", |
|
"Submit your resume via our website.\n", |
|
"Step 2\n", |
|
"Exploratory chat\n", |
|
"You’ll have a chat with one of our staff to discuss your career interests and relevant experience, and learn more about Anthropic.\n", |
|
"Step 3\n", |
|
"Skills Assessment\n", |
|
"For technical roles, you’ll have a one-hour technical screening interview.\n", |
|
"For operations or policy roles, you’ll get a take-home assignment. These typically involve writing responses to several role-relevant questions; they may occasionally require some outside research. Assignments usually take between 2-5 hours, depending on the role.\n", |
|
"We include this to minimize bias and make well-informed hiring decisions. We think seeing a candidate’s work helps us assess how they might actually perform on the job; similarly, the assignment gives candidates a better idea of what their work at Anthropic might entail. If a candidate likes working through their take-home, that is one indicator that they would enjoy taking on the role, and vice versa.\n", |
|
"We recognize that completing work assignments requires time and effort, and that they are not perfectly reflective of the role’s work. Nonetheless, we think that work tests are a useful complement to interviews and reference checks.\n", |
|
"Step 4\n", |
|
"Team Screen\n", |
|
"You'll have a conversation with either the Hiring Manager or a member of your potential team.\n", |
|
"Step 5\n", |
|
"Interview Panel\n", |
|
"For technical roles, you’ll have 3-4 more one-hour technical interviews, plus a culture interview.\n", |
|
"For operations or policy roles, you’ll have 3-5 hours of interviews, including a culture interview.\n", |
|
"Step 6\n", |
|
"Final Checks\n", |
|
"We’ll ask for some references, and have you chat with our leadership.\n", |
|
"Step 7\n", |
|
"Offer\n", |
|
"We’ll make you an offer!\n", |
|
"Technical Interviews\n", |
|
"The novel challenges we think about at Anthropic demand diverse expertise and perspectives. Our interview process is designed to identify thoughtful candidates who bring unique strengths to our multidisciplinary team. If you think this may describe you, we’d love to hear from you regardless of your background or experience.\n", |
|
"One of the most common questions we get is about whether it is worth applying to work at Anthropic if you have not worked on modern machine learning systems in the past. Yes! For some roles, ML experience is expected, but many technical staff have arrived at Anthropic with no machine learning experience. If you aren’t sure about the ML experience needed for your role, ask your recruiter.\n", |
|
"We use shared environments like Colab and Replit for our programming-focused interviews. We’ll be very interested in how you think through each problem and analyze the tradeoffs between possible approaches, and we’ll also expect you to write, run, and debug your solutions. You’ll be allowed to look things up in documentation or on the web, just like you usually can (which is why we’ll ask you to share your screen throughout each interview); but it’s still important to be familiar with basic syntax, standard libraries, and common idioms in the language you’re interviewing in, so that looking things up doesn’t consume too much time. Your interview process will also include non-technical questions about your experience and what motivates you, and, of course, you’ll have time to ask us about Anthropic! We can’t wait to meet you.\n", |
|
"Other Things\n", |
|
"Engineers here do lots of research, and researchers do lots of engineering\n", |
|
"While there’s historically been a division between engineering and research in machine learning, we think that boundary has dissolved with the advent of large models. The distribution of candidates we interview is strongly bimodal in both engineering and research experience however, and we have necessarily tailored our interview structure to that.\n", |
|
"If you’ve an engineering background, please apply as an engineer. You’ll perform much better in the interviews, and if you join you’ll have as much input to Anthropic’s direction and interests as anyone else.\n", |
|
"As evidence towards this: all of our papers have engineers as authors, and often as first author. Research and engineering hires all share a single title - ‘Member of Technical Staff’.\n", |
|
"We value direct evidence of ability\n", |
|
"If you’ve done interesting independent research, written an insightful blog post, or made substantial contributions to open-source software, put that at the top of your resume!\n", |
|
"Feedback\n", |
|
"We do not provide feedback on resumes or interviews.\n", |
|
"Visas\n", |
|
"Anthropic sponsors visas! We aren't able to sponsor them for every role and every candidate; operations roles are especially difficult to support. But if we make you an offer, we will make every effort to get you into the United States, and we retain an immigration lawyer to help with this.\n", |
|
"Green cards\n", |
|
"Once you’re eligible, we’re also keen to sponsor green cards!\n", |
|
"We do not require PhDs, degrees, or previous ML experience\n", |
|
"About half of Anthropic technical staff have a PhD of some sort; about half had prior experience in ML. We have several brilliant colleagues who never went to college.\n", |
|
"Remote interviewing\n", |
|
"All our interviews are conducted over Google Meet. We prefer PST office hours, but we can be flexible if that’s difficult for you.\n", |
|
"Re-applying\n", |
|
"Similarly, if interviews don’t work out this time, you’re welcome to re-apply after 12 months, and earlier if something materially changes about your experience or skills.\n", |
|
"Remote work\n", |
|
"Anthropic staff all come to the office regularly. Most staff live in the Bay Area, though a few live further away and come in for one week a month. We also understand that moving can take time, so as a transitional phase some folks start while fully remote.\n", |
|
"Offer timing\n", |
|
"If we make an offer, we’re happy to give you time to think about it and finish up any other interview processes you’re going through.\n", |
|
"Internships\n", |
|
"We do not offer internships.\n", |
|
"Candidate Privacy Policy\n", |
|
"US Candidate Privacy Policy\n", |
|
"UK Employee and Candidate Privacy Policy\n", |
|
"Claude\n", |
|
"API\n", |
|
"Team\n", |
|
"Pricing\n", |
|
"Research\n", |
|
"Company\n", |
|
"Customers\n", |
|
"News\n", |
|
"Careers\n", |
|
"Press Inquiries\n", |
|
"Support\n", |
|
"Status\n", |
|
"Availability\n", |
|
"Twitter\n", |
|
"LinkedIn\n", |
|
"YouTube\n", |
|
"Terms of Service – Consumer\n", |
|
"Terms of Service – Commercial\n", |
|
"Privacy Policy\n", |
|
"Usage Policy\n", |
|
"Responsible Disclosure Policy\n", |
|
"Compliance\n", |
|
"Privacy Choices\n", |
|
"© 2024 Anthropic PBC\n", |
|
"\n", |
|
"\n", |
|
"\n", |
|
"team page\n", |
|
"Webpage Title:\n", |
|
"Team up with Claude \\ Anthropic\n", |
|
"Webpage Contents:\n", |
|
"Claude\n", |
|
"Overview\n", |
|
"Team\n", |
|
"Enterprise\n", |
|
"API\n", |
|
"Pricing\n", |
|
"Research\n", |
|
"Company\n", |
|
"Careers\n", |
|
"News\n", |
|
"Try Claude\n", |
|
"Team up with Claude\n", |
|
"Shorten the path from idea to impact with an AI assistant that taps into your team’s shared expertise.\n", |
|
"Get started\n", |
|
"Request demo\n", |
|
"Easy collaboration for better outcomes\n", |
|
"Claude doesn’t just speed up daily tasks like writing emails or docs. It’s a virtual teammate that moves work forward using your team’s knowledge.\n", |
|
"Create with Claude\n", |
|
"Claude can be a sounding board for your ideas, help you generate new ones, and pull insights from data in a snap.\n", |
|
"Prime the canvas\n", |
|
"Use Projects to ground Claude in specific knowledge that helps you produce higher-quality work with less effort.\n", |
|
"Spark inspiration\n", |
|
"Share your best chats with Claude across the team to spark creativity and improve your project deliverables.\n", |
|
"Transform how you work\n", |
|
"Claude makes work more productive—whether you need a partner for deep work, a creative collaborator, or an assistant for daily tasks.\n", |
|
"Create with Claude\n", |
|
"Draft and iterate on documents, code and websites, and images alongside your chat with Artifacts.\n", |
|
"Write and debug code\n", |
|
"Create marketing campaigns\n", |
|
"Draft job descriptions\n", |
|
"Build interactive visualizations\n", |
|
"Transform how your team works\n", |
|
"Claude can serve as your go-to expert, empowering each team member with shared knowledge from all across the organization.\n", |
|
"Prime the canvas\n", |
|
"Create Projects and add knowledge so each person on the team can deliver expert-level results.\n", |
|
"Find and summarize information faster\n", |
|
"Use Claude as your subject-matter expert\n", |
|
"Expand how each teammate can contribute\n", |
|
"Spark inspiration\n", |
|
"Share your best chats with everyone on the Project to spark better ideas, iterate on Artifacts, and move work forward.\n", |
|
"Brainstorm on new product ideas\n", |
|
"Discuss insights from user interviews\n", |
|
"Collaborate on hard research questions\n", |
|
"Every team can work with Claude\n", |
|
"Engineering\n", |
|
"Generate code snippets in seconds\n", |
|
"Create clear, comprehensive docs with no effort\n", |
|
"Get help debugging even the most complex issues\n", |
|
"Turn product feedback into roadmap items faster\n", |
|
"Support\n", |
|
"Resolve customer issues in record time\n", |
|
"Craft personalized responses effortlessly\n", |
|
"Build a dynamic, user-friendly knowledge base\n", |
|
"Generate insightful metrics reports instantly\n", |
|
"Marketing\n", |
|
"Create engaging content tailored to your audience\n", |
|
"Segment customers with pinpoint accuracy\n", |
|
"Analyze competitors with unparalleled depth\n", |
|
"Optimize campaigns for maximum ROI\n", |
|
"Sales\n", |
|
"Customize pitches for any customer segment\n", |
|
"Uncover hidden sales trends effortlessly\n", |
|
"Draft compelling follow-up emails in seconds\n", |
|
"Get comprehensive competitor insights on demand\n", |
|
"By leveraging content from our help center in Projects, we were able to generate comprehensive standard operating procedures for our core workflows in just a few hours—a task that previously took our team weeks to complete.\n", |
|
"Bradley Silicani\n", |
|
"COO, Anrok\n", |
|
"Claude Team is transforming our way of working at North Highland. Claude is a truly exceptional writer that has helped our team complete content creation and analysis tasks up to 5x faster than before—turning what was once two weeks of writing and research into minutes of work.\n", |
|
"Luka Anic\n", |
|
"Senior Director, Technical AI Program and Product Manager, North Highland\n", |
|
"Generating content, completing creative tasks, and creating summarized reports is much easier than before. There are many other areas of our business—like engineering, legal, risk and compliance—where we're excited to see what Claude can do.\n", |
|
"Olga Pirog\n", |
|
"Head of AI Transformation, IG Group\n", |
|
"Join the teams transforming with Claude\n", |
|
"See Pricing\n", |
|
"Claude\n", |
|
"API\n", |
|
"Team\n", |
|
"Pricing\n", |
|
"Research\n", |
|
"Company\n", |
|
"Customers\n", |
|
"News\n", |
|
"Careers\n", |
|
"Press Inquiries\n", |
|
"Support\n", |
|
"Status\n", |
|
"Availability\n", |
|
"Twitter\n", |
|
"LinkedIn\n", |
|
"YouTube\n", |
|
"Terms of Service – Consumer\n", |
|
"Terms of Service – Commercial\n", |
|
"Privacy Policy\n", |
|
"Usage Policy\n", |
|
"Responsible Disclosure Policy\n", |
|
"Compliance\n", |
|
"Privacy Choices\n", |
|
"© 2024 Anthropic PBC\n", |
|
"\n", |
|
"\n", |
|
"\n", |
|
"research page\n", |
|
"Webpage Title:\n", |
|
"Research \\ Anthropic\n", |
|
"Webpage Contents:\n", |
|
"Claude\n", |
|
"Overview\n", |
|
"Team\n", |
|
"Enterprise\n", |
|
"API\n", |
|
"Pricing\n", |
|
"Research\n", |
|
"Company\n", |
|
"Careers\n", |
|
"News\n", |
|
"Researching\n", |
|
"at the frontier\n", |
|
"At Anthropic, we develop large-scale AI systems, and our research teams help us to create safer, steerable, and more reliable models.\n", |
|
"See open roles\n", |
|
"Claude\n", |
|
"API\n", |
|
"Team\n", |
|
"Pricing\n", |
|
"Research\n", |
|
"Company\n", |
|
"Customers\n", |
|
"News\n", |
|
"Careers\n", |
|
"Press Inquiries\n", |
|
"Support\n", |
|
"Status\n", |
|
"Availability\n", |
|
"Twitter\n", |
|
"LinkedIn\n", |
|
"YouTube\n", |
|
"Terms of Service – Consumer\n", |
|
"Terms of Service – Commercial\n", |
|
"Privacy Policy\n", |
|
"Usage Policy\n", |
|
"Responsible Disclosure Policy\n", |
|
"Compliance\n", |
|
"Privacy Choices\n", |
|
"© 2024 Anthropic PBC\n", |
|
"\n", |
|
"\n", |
|
"\n", |
|
"news page\n", |
|
"Webpage Title:\n", |
|
"Newsroom \\ Anthropic\n", |
|
"Webpage Contents:\n", |
|
"Claude\n", |
|
"Overview\n", |
|
"Team\n", |
|
"Enterprise\n", |
|
"API\n", |
|
"Pricing\n", |
|
"Research\n", |
|
"Company\n", |
|
"Careers\n", |
|
"News\n", |
|
"Newsroom\n", |
|
"Featured\n", |
|
"Powering the next generation of AI development with AWS\n", |
|
"Press inquiries\n", |
|
"press@anthropic.com\n", |
|
"Non-media inquiries\n", |
|
"support.anthropic.com\n", |
|
"Media assets\n", |
|
"Download press kit\n", |
|
"Follow Anthropic\n", |
|
"Featured\n", |
|
"Announcing our updated Responsible Scaling Policy\n", |
|
"Featured\n", |
|
"Developing a computer use model\n", |
|
"News\n", |
|
"No results found.\n", |
|
"Product\n", |
|
"Tailor Claude’s responses to your personal style\n", |
|
"Nov 26, 2024\n", |
|
"Announcements\n", |
|
"Introducing the Model Context Protocol\n", |
|
"Nov 25, 2024\n", |
|
"Announcements\n", |
|
"Powering the next generation of AI development with AWS\n", |
|
"Nov 22, 2024\n", |
|
"Product\n", |
|
"Improve your prompts in the developer console\n", |
|
"Nov 14, 2024\n", |
|
"Policy\n", |
|
"The case for targeted regulation\n", |
|
"Oct 31, 2024\n", |
|
"Product\n", |
|
"Raising the bar on SWE-bench Verified with Claude 3.5 Sonnet\n", |
|
"Oct 30, 2024\n", |
|
"Announcements\n", |
|
"Claude 3.5 Sonnet on GitHub Copilot\n", |
|
"Oct 29, 2024\n", |
|
"Product\n", |
|
"Introducing the analysis tool in Claude.ai\n", |
|
"Oct 24, 2024\n", |
|
"Announcements\n", |
|
"·\n", |
|
"Product\n", |
|
"Developing a computer use model\n", |
|
"Oct 22, 2024\n", |
|
"Announcements\n", |
|
"Introducing computer use, a new Claude 3.5 Sonnet, and Claude 3.5 Haiku\n", |
|
"Oct 22, 2024\n", |
|
"Announcements\n", |
|
"Announcing our updated Responsible Scaling Policy\n", |
|
"Oct 15, 2024\n", |
|
"Societal Impacts\n", |
|
"U.S. Elections Readiness\n", |
|
"Oct 8, 2024\n", |
|
"Product\n", |
|
"Introducing the Message Batches API\n", |
|
"Oct 8, 2024\n", |
|
"Product\n", |
|
"·\n", |
|
"Announcements\n", |
|
"Introducing Contextual Retrieval\n", |
|
"Sep 19, 2024\n", |
|
"Product\n", |
|
"Workspaces in the Anthropic API Console\n", |
|
"Sep 10, 2024\n", |
|
"Product\n", |
|
"Claude for Enterprise\n", |
|
"Sep 4, 2024\n", |
|
"Announcements\n", |
|
"Salesforce teams up with Anthropic to enhance Einstein capabilities with Claude\n", |
|
"Sep 3, 2024\n", |
|
"Announcements\n", |
|
"Artifacts are now generally available\n", |
|
"Aug 27, 2024\n", |
|
"Product\n", |
|
"Prompt caching with Claude\n", |
|
"Aug 14, 2024\n", |
|
"Announcements\n", |
|
"Expanding our model safety bug bounty program\n", |
|
"Aug 8, 2024\n", |
|
"Announcements\n", |
|
"Claude is now available in Brazil\n", |
|
"Aug 1, 2024\n", |
|
"Announcements\n", |
|
"Anthropic partners with Menlo Ventures to launch Anthology Fund\n", |
|
"Jul 17, 2024\n", |
|
"Product\n", |
|
"Claude Android app\n", |
|
"Jul 16, 2024\n", |
|
"Product\n", |
|
"Fine-tune Claude 3 Haiku in Amazon Bedrock\n", |
|
"Jul 11, 2024\n", |
|
"Product\n", |
|
"Evaluate prompts in the developer console\n", |
|
"Jul 9, 2024\n", |
|
"Announcements\n", |
|
"A new initiative for developing third-party model evaluations\n", |
|
"Jul 1, 2024\n", |
|
"Announcements\n", |
|
"Expanding access to Claude for government\n", |
|
"Jun 26, 2024\n", |
|
"Product\n", |
|
"Collaborate with Claude on Projects\n", |
|
"Jun 25, 2024\n", |
|
"Announcements\n", |
|
"Claude 3.5 Sonnet\n", |
|
"Jun 21, 2024\n", |
|
"Policy\n", |
|
"Challenges in red teaming AI systems\n", |
|
"Jun 12, 2024\n", |
|
"Policy\n", |
|
"·\n", |
|
"Societal Impacts\n", |
|
"Testing and mitigating elections-related risks\n", |
|
"Jun 6, 2024\n", |
|
"Announcements\n", |
|
"Introducing Claude to Canada\n", |
|
"Jun 5, 2024\n", |
|
"Product\n", |
|
"Claude can now use tools\n", |
|
"May 30, 2024\n", |
|
"Announcements\n", |
|
"Jay Kreps appointed to Anthropic's Board of Directors\n", |
|
"May 29, 2024\n", |
|
"Product\n", |
|
"Golden Gate Claude\n", |
|
"May 23, 2024\n", |
|
"Announcements\n", |
|
"Krishna Rao joins Anthropic as Chief Financial Officer\n", |
|
"May 21, 2024\n", |
|
"Interpretability\n", |
|
"Mapping the Mind of a Large Language Model\n", |
|
"May 21, 2024\n", |
|
"Product\n", |
|
"Generate better prompts in the developer console\n", |
|
"May 20, 2024\n", |
|
"Policy\n", |
|
"Reflections on our Responsible Scaling Policy\n", |
|
"May 20, 2024\n", |
|
"Announcements\n", |
|
"Mike Krieger joins Anthropic as Chief Product Officer\n", |
|
"May 15, 2024\n", |
|
"Announcements\n", |
|
"Claude is now available in Europe\n", |
|
"May 14, 2024\n", |
|
"Announcements\n", |
|
"Updating our Usage Policy\n", |
|
"May 10, 2024\n", |
|
"Product\n", |
|
"·\n", |
|
"Announcements\n", |
|
"Introducing the Claude Team plan and iOS app\n", |
|
"May 1, 2024\n", |
|
"Announcements\n", |
|
"Aligning on child safety principles\n", |
|
"Apr 23, 2024\n", |
|
"Alignment\n", |
|
"Many-shot jailbreaking\n", |
|
"Apr 2, 2024\n", |
|
"Policy\n", |
|
"Third-party testing as a key ingredient of AI policy\n", |
|
"Mar 25, 2024\n", |
|
"Announcements\n", |
|
"Anthropic, AWS, and Accenture team up to build trusted solutions for enterprises\n", |
|
"Mar 20, 2024\n", |
|
"Announcements\n", |
|
"Claude 3 models on Vertex AI\n", |
|
"Mar 19, 2024\n", |
|
"Announcements\n", |
|
"Claude 3 Haiku: our fastest model yet\n", |
|
"Mar 13, 2024\n", |
|
"Announcements\n", |
|
"Introducing the next generation of Claude\n", |
|
"Mar 4, 2024\n", |
|
"Product\n", |
|
"Prompt engineering for business performance\n", |
|
"Feb 29, 2024\n", |
|
"Policy\n", |
|
"Preparing for global elections in 2024\n", |
|
"Feb 16, 2024\n", |
|
"Announcements\n", |
|
"Expanded legal protections and improvements to our API\n", |
|
"Dec 19, 2023\n", |
|
"Product\n", |
|
"Long context prompting for Claude 2.1\n", |
|
"Dec 6, 2023\n", |
|
"Product\n", |
|
"Introducing Claude 2.1\n", |
|
"Nov 21, 2023\n", |
|
"Policy\n", |
|
"Thoughts on the US Executive Order, G7 Code of Conduct, and Bletchley Park Summit\n", |
|
"Nov 5, 2023\n", |
|
"Policy\n", |
|
"Dario Amodei’s prepared remarks from the AI Safety Summit on Anthropic’s Responsible Scaling Policy\n", |
|
"Nov 1, 2023\n", |
|
"Announcements\n", |
|
"Claude on Amazon Bedrock now available to every AWS customer\n", |
|
"Sep 28, 2023\n", |
|
"Announcements\n", |
|
"Expanding access to safer AI with Amazon\n", |
|
"Sep 25, 2023\n", |
|
"Product\n", |
|
"Prompt engineering for Claude's long context window\n", |
|
"Sep 23, 2023\n", |
|
"Announcements\n", |
|
"Anthropic's Responsible Scaling Policy\n", |
|
"Sep 19, 2023\n", |
|
"Announcements\n", |
|
"The Long-Term Benefit Trust\n", |
|
"Sep 19, 2023\n", |
|
"Announcements\n", |
|
"Anthropic partners with BCG\n", |
|
"Sep 14, 2023\n", |
|
"Announcements\n", |
|
"Introducing Claude Pro\n", |
|
"Sep 7, 2023\n", |
|
"Product\n", |
|
"Claude 2 on Amazon Bedrock\n", |
|
"Aug 23, 2023\n", |
|
"Announcements\n", |
|
"SKT Partnership Announcement\n", |
|
"Aug 15, 2023\n", |
|
"Announcements\n", |
|
"Releasing Claude Instant 1.2\n", |
|
"Aug 9, 2023\n", |
|
"Announcements\n", |
|
"Frontier Threats Red Teaming for AI Safety\n", |
|
"Jul 26, 2023\n", |
|
"Announcements\n", |
|
"Frontier Model Security\n", |
|
"Jul 25, 2023\n", |
|
"Announcements\n", |
|
"Claude 2\n", |
|
"Jul 11, 2023\n", |
|
"Announcements\n", |
|
"Charting a Path to AI Accountability\n", |
|
"Jun 13, 2023\n", |
|
"Announcements\n", |
|
"Anthropic Raises $450 Million in Series C Funding to Scale Reliable AI Products\n", |
|
"May 23, 2023\n", |
|
"Announcements\n", |
|
"Zoom Partnership and Investment in Anthropic\n", |
|
"May 16, 2023\n", |
|
"Announcements\n", |
|
"Introducing 100K Context Windows\n", |
|
"May 11, 2023\n", |
|
"Announcements\n", |
|
"Claude’s Constitution\n", |
|
"May 9, 2023\n", |
|
"Announcements\n", |
|
"Partnering with Scale to Bring Generative AI to Enterprises\n", |
|
"Apr 26, 2023\n", |
|
"Announcements\n", |
|
"An AI Policy Tool for Today: Ambitiously Invest in NIST\n", |
|
"Apr 20, 2023\n", |
|
"Announcements\n", |
|
"Claude, now in Slack\n", |
|
"Mar 30, 2023\n", |
|
"Announcements\n", |
|
"Introducing Claude\n", |
|
"Mar 14, 2023\n", |
|
"Announcements\n", |
|
"Core Views on AI Safety: When, Why, What, and How\n", |
|
"Mar 8, 2023\n", |
|
"Announcements\n", |
|
"Anthropic Partners with Google Cloud\n", |
|
"Feb 3, 2023\n", |
|
"Announcements\n", |
|
"Anthropic Raises Series B to Build Steerable, Interpretable, Robust AI Systems\n", |
|
"Apr 29, 2022\n", |
|
"Announcements\n", |
|
"Anthropic raises $124 million to build more reliable, general AI systems\n", |
|
"May 28, 2021\n", |
|
"Claude\n", |
|
"API\n", |
|
"Team\n", |
|
"Pricing\n", |
|
"Research\n", |
|
"Company\n", |
|
"Customers\n", |
|
"News\n", |
|
"Careers\n", |
|
"Press Inquiries\n", |
|
"Support\n", |
|
"Status\n", |
|
"Availability\n", |
|
"Twitter\n", |
|
"LinkedIn\n", |
|
"YouTube\n", |
|
"Terms of Service – Consumer\n", |
|
"Terms of Service – Commercial\n", |
|
"Privacy Policy\n", |
|
"Usage Policy\n", |
|
"Responsible Disclosure Policy\n", |
|
"Compliance\n", |
|
"Privacy Choices\n", |
|
"© 2024 Anthropic PBC\n", |
|
"\n", |
|
"\n" |
|
] |
|
} |
|
], |
|
"source": [ |
|
"print(get_all_details(\"https://anthropic.com\"))" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 16, |
|
"id": "9b863a55-f86c-4e3f-8a79-94e24c1a8cf2", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"system_prompt = \"You are an assistant that analyzes the contents of several relevant pages from a company website \\\n", |
|
"and creates a short brochure about the company for prospective customers, investors and recruits. Respond in markdown.\\\n", |
|
"Include details of company culture, customers and careers/jobs if you have the information.\"\n", |
|
"\n", |
|
"# Or uncomment the lines below for a more humorous brochure - this demonstrates how easy it is to incorporate 'tone':\n", |
|
"\n", |
|
"# system_prompt = \"You are an assistant that analyzes the contents of several relevant pages from a company website \\\n", |
|
"# and creates a short humorous, entertaining, jokey brochure about the company for prospective customers, investors and recruits. Respond in markdown.\\\n", |
|
"# Include details of company culture, customers and careers/jobs if you have the information.\"\n" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 17, |
|
"id": "6ab83d92-d36b-4ce0-8bcc-5bb4c2f8ff23", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"def get_brochure_user_prompt(company_name, url):\n", |
|
" user_prompt = f\"You are looking at a company called: {company_name}\\n\"\n", |
|
" user_prompt += f\"Here are the contents of its landing page and other relevant pages; use this information to build a short brochure of the company in markdown.\\n\"\n", |
|
" user_prompt += get_all_details(url)\n", |
|
" user_prompt = user_prompt[:20_000] # Truncate if more than 20,000 characters\n", |
|
" return user_prompt" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 18, |
|
"id": "cd909e0b-1312-4ce2-a553-821e795d7572", |
|
"metadata": { |
|
"scrolled": true |
|
}, |
|
"outputs": [ |
|
{ |
|
"name": "stdout", |
|
"output_type": "stream", |
|
"text": [ |
|
"Found links: {'links': [{'type': 'about page', 'url': 'https://www.anthropic.com/company'}, {'type': 'careers page', 'url': 'https://www.anthropic.com/careers'}, {'type': 'team page', 'url': 'https://www.anthropic.com/team'}, {'type': 'research page', 'url': 'https://www.anthropic.com/research'}, {'type': 'enterprise page', 'url': 'https://www.anthropic.com/enterprise'}, {'type': 'api page', 'url': 'https://www.anthropic.com/api'}, {'type': 'pricing page', 'url': 'https://www.anthropic.com/pricing'}, {'type': 'news page', 'url': 'https://www.anthropic.com/news'}]}\n" |
|
] |
|
}, |
|
{ |
|
"data": { |
|
"text/plain": [ |
|
"\"You are looking at a company called: Anthropic\\nHere are the contents of its landing page and other relevant pages; use this information to build a short brochure of the company in markdown.\\nLanding page:\\nWebpage Title:\\nHome \\\\ Anthropic\\nWebpage Contents:\\nClaude\\nOverview\\nTeam\\nEnterprise\\nAPI\\nPricing\\nResearch\\nCompany\\nCareers\\nNews\\nAI\\nresearch\\nand\\nproducts\\nthat put safety at the frontier\\nClaude.ai\\nMeet Claude 3.5 Sonnet\\nClaude 3.5 Sonnet, our most intelligent AI model, is now available.\\nTalk to Claude\\nAPI\\nBuild with Claude\\nStart using Claude to drive efficiency and create new revenue streams.\\nLearn more\\nAnnouncements\\nIntroducing computer use, a new Claude 3.5 Sonnet, and Claude 3.5 Haiku\\nOct 22, 2024\\nModel updates\\n3.5 Sonnet\\n3.5 Haiku\\nOur Work\\nProduct\\nClaude for Enterprise\\nSep 4, 2024\\nAlignment\\n·\\nResearch\\nConstitutional AI: Harmlessness from AI Feedback\\nDec 15, 2022\\nAnnouncements\\nCore Views on AI Safety: When, Why, What, and How\\nMar 8, 2023\\nWork with Anthropic\\nAnthropic is an AI safety and research company based in San Francisco. Our interdisciplinary team has experience across ML, physics, policy, and product. Together, we generate research and create reliable, beneficial AI systems.\\nSee open roles\\nClaude\\nAPI\\nTeam\\nPricing\\nResearch\\nCompany\\nCustomers\\nNews\\nCareers\\nPress Inquiries\\nSupport\\nStatus\\nAvailability\\nTwitter\\nLinkedIn\\nYouTube\\nTerms of Service – Consumer\\nTerms of Service – Commercial\\nPrivacy Policy\\nUsage Policy\\nResponsible Disclosure Policy\\nCompliance\\nPrivacy Choices\\n© 2024 Anthropic PBC\\n\\n\\n\\nabout page\\nWebpage Title:\\nCompany \\\\ Anthropic\\nWebpage Contents:\\nClaude\\nOverview\\nTeam\\nEnterprise\\nAPI\\nPricing\\nResearch\\nCompany\\nCareers\\nNews\\nMaking AI systems\\nyou can rely on\\nAnthropic is an AI safety and research company. We build reliable, interpretable, and steerable AI systems.\\nJoin us\\nOur Purpose\\nWe believe AI will have a vast impact on the world. Anthropic is dedicated to building systems that people can rely on and generating research about the opportunities and risks of AI.\\nWe Build Safer Systems\\nWe aim to build frontier AI systems that are reliable, interpretable, and steerable. We conduct frontier research, develop and apply a variety of safety techniques, and deploy the resulting systems via a set of partnerships and products.\\nSafety Is a Science\\nWe treat AI safety as a systematic science, conducting research, applying it to our products, feeding those insights back into our research, and regularly sharing what we learn with the world along the way.\\nInterdisciplinary\\nAnthropic is a collaborative team of researchers, engineers, policy experts, business leaders and operators, who bring our experience from many different domains to our work.\\nAI Companies are One Piece of a Big Puzzle\\nAI has the potential to fundamentally change how the world works. We view ourselves as just one piece of this evolving puzzle. We collaborate with civil society, government, academia, nonprofits and industry to promote safety industry-wide.\\nThe Team\\nWe’re a team of researchers, engineers, policy experts and operational leaders, with experience spanning a variety of disciplines, all working together to build reliable and understandable AI systems.\\nResearch\\nWe conduct frontier AI research across a variety of modalities, and explore novel and emerging safety research areas from interpretability to RL from human feedback to policy and societal impacts analysis.\\nPolicy\\nWe think about the impacts of our work and strive to communicate what we’re seeing at the frontier to policymakers and civil society in the US and abroad to help promote safe and reliable AI.\\nProduct\\nWe translate our research into tangible, practical tools like Claude that benefit businesses, nonprofits and civil society groups and their clients and people around the globe.\\nOperations\\nOur people, finance, legal, and recruiting teams are the human engines that make Anthropic go. We’ve had previous careers at NASA, startups, and the armed forces and our diverse experiences help make Anthropic a great place to work (and we love plants!).\\nOur Values\\n01\\nHere for the mission\\nAnthropic exists for our mission: to ensure transformative AI helps people and society flourish. Progress this decade may be rapid, and we expect increasingly capable systems to pose novel challenges. We pursue our mission by building frontier systems, studying their behaviors, working to responsibly deploy them, and regularly sharing our safety insights. We collaborate with other projects and stakeholders seeking a similar outcome.\\n02\\nUnusually high trust\\nOur company is an unusually high trust environment: we assume good faith, disagree kindly, and prioritize honesty. We expect emotional maturity and intellectual openness. At its best, our trust enables us to make better decisions as an organization than any one of us could as individuals.\\n03\\nOne big team\\nCollaboration is central to our work, culture, and value proposition. While we have many teams at Anthropic, we feel the broader sense in which we are all on the same team working together towards the mission. Leadership sets the strategy, with broad input from everyone, and trusts each piece of the organization to pursue these goals in their unique style. Individuals commonly contribute to work across many different areas.\\n04\\nDo the simple thing that works\\nWe celebrate trying the simple thing before the clever, novel thing. We embrace pragmatism - sensible, practical approaches that acknowledge tradeoffs. We love empiricism - finding out what actually works by trying it - and apply this to our research, our engineering and our collaboration. We aim to be open about what we understand and what we don’t.\\nGovernance\\nAnthropic is a Public Benefit Corporation, whose purpose is the responsible development and maintenance of advanced AI for the long-term benefit of humanity. Our Board of Directors is elected by stockholders and our Long-Term Benefit Trust, as explained\\nhere.\\nCurrent members of the Board and the Long-Term Benefit Trust (LTBT) are listed below.\\nAnthropic Board of Directors\\nDario Amodei, Daniela Amodei, Yasmin Razavi, and Jay Kreps.\\nLTBT Trustees\\nNeil Buddy Shah, Kanika Bahl, and Zach Robinson.\\nCompany News\\nSee All\\nAnnouncements\\nIntroducing the Model Context Protocol\\nNov 25, 2024\\nAnnouncements\\nPowering the next generation of AI development with AWS\\nNov 22, 2024\\nAnnouncements\\nClaude 3.5 Sonnet on GitHub Copilot\\nOct 29, 2024\\nWant to help us build the future of safe AI?\\nJoin us\\nClaude\\nAPI\\nTeam\\nPricing\\nResearch\\nCompany\\nCustomers\\nNews\\nCareers\\nPress Inquiries\\nSupport\\nStatus\\nAvailability\\nTwitter\\nLinkedIn\\nYouTube\\nTerms of Service – Consumer\\nTerms of Service – Commercial\\nPrivacy Policy\\nUsage Policy\\nResponsible Disclosure Policy\\nCompliance\\nPrivacy Choices\\n© 2024 Anthropic PBC\\n\\n\\n\\ncareers page\\nWebpage Title:\\nCareers \\\\ Anthropic\\nWebpage Contents:\\nClaude\\nOverview\\nTeam\\nEnterprise\\nAPI\\nPricing\\nResearch\\nCompany\\nCareers\\nNews\\nJoin the team\\nmaking AI safe\\nWe’re a public benefit corporation headquartered in San Francisco. Our team’s experience spans a variety of backgrounds and disciplines, from physics and machine learning to public policy and business. We work as a cohesive team that collectively forecasts the impact and tractability of research ideas in advancing our mission.\\nSee open roles\\nWhat We Offer\\nHealth & Wellness\\nAt Anthropic, we believe that supporting our employees is crucial to our collective success and wellbeing. That's why we offer a range of benefits to best support you and your family, now and in the future.\\nComprehensive health, dental, and vision insurance for you and your dependents\\nInclusive fertility benefits via Carrot Fertility\\n22 weeks of paid parental leave\\nFlexible paid time off and absence policies\\nGenerous mental health support for you and your dependents\\nCompensation & Support\\nOur goal is to foster an environment where you can thrive professionally while feeling confident that you and your loved ones are taken care of.\\nCompetitive salary and equity packages\\nOptional equity donation matching at a 1:1 ratio, up to 25% of your equity grant\\nRobust retirement plans and salary sacrifice programs with market competitive matching\\nLife and income protection plans\\nAdditional Benefits\\n$500/month flexible wellness and time saver stipend\\nCommuter benefits\\nAnnual education stipend\\nHome office stipends\\nRelocation support for those moving for Anthropic\\nDaily meals and snacks in the office\\nHow We Hire\\nThe interview process at Anthropic varies based on role and candidate, but our standard process looks like this:\\nStep 1\\nResume\\nSubmit your resume via our website.\\nStep 2\\nExploratory chat\\nYou’ll have a chat with one of our staff to discuss your career interests and relevant experience, and learn more about Anthropic.\\nStep 3\\nSkills Assessment\\nFor technical roles, you’ll have a one-hour technical screening interview.\\nFor operations or policy roles, you’ll get a take-home assignment. These typically involve writing responses to several role-relevant questions; they may occasionally require some outside research. Assignments usually take between 2-5 hours, depending on the role.\\nWe include this to minimize bias and make well-informed hiring decisions. We think seeing a candidate’s work helps us assess how they might actually perform on the job; similarly, the assignment gives candidates a better idea of what their work at Anthropic might entail. If a candidate likes working through their take-home, that is one indicator that they would enjoy taking on the role, and vice versa.\\nWe recognize that completing work assignments requires time and effort, and that they are not perfectly reflective of the role’s work. Nonetheless, we think that work tests are a useful complement to interviews and reference checks.\\nStep 4\\nTeam Screen\\nYou'll have a conversation with either the Hiring Manager or a member of your potential team.\\nStep 5\\nInterview Panel\\nFor technical roles, you’ll have 3-4 more one-hour technical interviews, plus a culture interview.\\nFor operations or policy roles, you’ll have 3-5 hours of interviews, including a culture interview.\\nStep 6\\nFinal Checks\\nWe’ll ask for some references, and have you chat with our leadership.\\nStep 7\\nOffer\\nWe’ll make you an offer!\\nTechnical Interviews\\nThe novel challenges we think about at Anthropic demand diverse expertise and perspectives. Our interview process is designed to identify thoughtful candidates who bring unique strengths to our multidisciplinary team. If you think this may describe you, we’d love to hear from you regardless of your background or experience.\\nOne of the most common questions we get is about whether it is worth applying to work at Anthropic if you have not worked on modern machine learning systems in the past. Yes! For some roles, ML experience is expected, but many technical staff have arrived at Anthropic with no machine learning experience. If you aren’t sure about the ML experience needed for your role, ask your recruiter.\\nWe use shared environments like Colab and Replit for our programming-focused interviews. We’ll be very interested in how you think through each problem and analyze the tradeoffs between possible approaches, and we’ll also expect you to write, run, and debug your solutions. You’ll be allowed to look things up in documentation or on the web, just like you usually can (which is why we’ll ask you to share your screen throughout each interview); but it’s still important to be familiar with basic syntax, standard libraries, and common idioms in the language you’re interviewing in, so that looking things up doesn’t consume too much time. Your interview process will also include non-technical questions about your experience and what motivates you, and, of course, you’ll have time to ask us about Anthropic! We can’t wait to meet you.\\nOther Things\\nEngineers here do lots of research, and researchers do lots of engineering\\nWhile there’s historically been a division between engineering and research in machine learning, we think that boundary has dissolved with the advent of large models. The distribution of candidates we interview is strongly bimodal in both engineering and research experience however, and we have necessarily tailored our interview structure to that.\\nIf you’ve an engineering background, please apply as an engineer. You’ll perform much better in the interviews, and if you join you’ll have as much input to Anthropic’s direction and interests as anyone else.\\nAs evidence towards this: all of our papers have engineers as authors, and often as first author. Research and engineering hires all share a single title - ‘Member of Technical Staff’.\\nWe value direct evidence of ability\\nIf you’ve done interesting independent research, written an insightful blog post, or made substantial contributions to open-source software, put that at the top of your resume!\\nFeedback\\nWe do not provide feedback on resumes or interviews.\\nVisas\\nAnthropic sponsors visas! We aren't able to sponsor them for every role and every candidate; operations roles are especially difficult to support. But if we make you an offer, we will make every effort to get you into the United States, and we retain an immigration lawyer to help with this.\\nGreen cards\\nOnce you’re eligible, we’re also keen to sponsor green cards!\\nWe do not require PhDs, degrees, or previous ML experience\\nAbout half of Anthropic technical staff have a PhD of some sort; about half had prior experience in ML. We have several brilliant colleagues who never went to college.\\nRemote interviewing\\nAll our interviews are conducted over Google Meet. We prefer PST office hours, but we can be flexible if that’s difficult for you.\\nRe-applying\\nSimilarly, if interviews don’t work out this time, you’re welcome to re-apply after 12 months, and earlier if something materially changes about your experience or skills.\\nRemote work\\nAnthropic staff all come to the office regularly. Most staff live in the Bay Area, though a few live further away and come in for one week a month. We also understand that moving can take time, so as a transitional phase some folks start while fully remote.\\nOffer timing\\nIf we make an offer, we’re happy to give you time to think about it and finish up any other interview processes you’re going through.\\nInternships\\nWe do not offer internships.\\nCandidate Privacy Policy\\nUS Candidate Privacy Policy\\nUK Employee and Candidate Privacy Policy\\nClaude\\nAPI\\nTeam\\nPricing\\nResearch\\nCompany\\nCustomers\\nNews\\nCareers\\nPress Inquiries\\nSupport\\nStatus\\nAvailability\\nTwitter\\nLinkedIn\\nYouTube\\nTerms of Service – Consumer\\nTerms of Service – Commercial\\nPrivacy Policy\\nUsage Policy\\nResponsible Disclosure Policy\\nCompliance\\nPrivacy Choices\\n© 2024 Anthropic PBC\\n\\n\\n\\nteam page\\nWebpage Title:\\nTeam up with Claude \\\\ Anthropic\\nWebpage Contents:\\nClaude\\nOverview\\nTeam\\nEnterprise\\nAPI\\nPricing\\nResearch\\nCompany\\nCareers\\nNews\\nTry Claude\\nTeam up with Claude\\nShorten the path from idea to impact with an AI assistant that taps into your team’s shared expertise.\\nGet started\\nRequest demo\\nEasy collaboration for better outcomes\\nClaude doesn’t just speed up daily tasks like writing emails or docs. It’s a virtual teammate that moves work forward using your team’s knowledge.\\nCreate with Claude\\nClaude can be a sounding board for your ideas, help you generate new ones, and pull insights from data in a snap.\\nPrime the canvas\\nUse Projects to ground Claude in specific knowledge that helps you produce higher-quality work with less effort.\\nSpark inspiration\\nShare your best chats with Claude across the team to spark creativity and improve your project deliverables.\\nTransform how you work\\nClaude makes work more productive—whether you need a partner for deep work, a creative collaborator, or an assistant for daily tasks.\\nCreate with Claude\\nDraft and iterate on documents, code and websites, and images alongside your chat with Artifacts.\\nWrite and debug code\\nCreate marketing campaigns\\nDraft job descriptions\\nBuild interactive visualizations\\nTransform how your team works\\nClaude can serve as your go-to expert, empowering each team member with shared knowledge from all across the organization.\\nPrime the canvas\\nCreate Projects and add knowledge so each person on the team can deliver expert-level results.\\nFind and summarize information faster\\nUse Claude as your subject-matter expert\\nExpand how each teammate can contribute\\nSpark inspiration\\nShare your best chats with everyone on the Project to spark better ideas, iterate on Artifacts, and move work forward.\\nBrainstorm on new product ideas\\nDiscuss insights from user interviews\\nCollaborate on hard research questions\\nEvery team can work with Claude\\nEngineering\\nGenerate code snippets in seconds\\nCreate clear, comprehensive docs with no effort\\nGet help debugging even the most complex issues\\nTurn product feedback into roadmap items faster\\nSupport\\nResolve customer issues in record time\\nCraft personalized responses effortlessly\\nBuild a dynamic, user-friendly knowledge base\\nGenerate insightful metrics reports instantly\\nMarketing\\nCreate engaging content tailored to your audience\\nSegment customers with pinpoint accuracy\\nAnalyze competitors with unparalleled depth\\nOptimize campaigns for maximum ROI\\nSales\\nCustomize pitches for any customer segment\\nUncover hidden sales trends effortlessly\\nDraft compelling follow-up emails in seconds\\nGet comprehensive competitor insights on demand\\nBy leveraging content from our help center in Projects, we were able to generate comprehensive standard operating procedures for our core workflows in just a few hours—a task that previously took our team weeks to complete.\\nBradley Silicani\\nCOO, Anrok\\nClaude Team is transforming our way of working at North Highland. Claude is a truly exceptional writer that has helped our team complete content creation and analysis tasks up to 5x faster than before—turning what was once two weeks of writing and research into minutes of work.\\nLuka Anic\\nSenior Director, Technical AI Program and Product Manager, North Highland\\nGenerating content, completing creative tasks, and creating summarized reports is much easier than before. There are many other areas of our business—like engineering, legal, risk and compliance—where we're excited to see what Claude can do.\\nOlga Pirog\\nHead of AI Transformation, IG Group\\nJoin the teams transforming with Claude\\nSee Pricing\\nClaude\\nAPI\\nTeam\\nPricing\\nResearch\\nCompany\\nCustomers\\nNews\\nCareers\\nPress Inquiries\\nSupport\\nStatus\\nAvailability\\nTwitter\\nLinkedIn\\nYouTube\\nTerms of Service – Consumer\\nTerms of Service – Commercial\\nPrivacy Policy\\nUsage Policy\\nResponsible Disclosure Policy\\nCompliance\\nPrivacy Choices\\n© 2024 Anthropic PBC\\n\\n\\n\\nresearch page\\nWebpage Title:\\nResearch \\\\ Anthropic\\nWebpage Contents:\\nClaude\\nOverview\\nTeam\\nEnterprise\\nAPI\\nPricing\\nResearch\\nCompany\\nCareers\\nNews\\nResearching\\nat the frontier\\nAt Anthropic, we develop large-scale AI systems, and our research teams help us to create safer, steerable, and more reliable models.\\nSee open roles\\nClaude\\nAPI\\nTeam\\nPricing\\nResearch\\nCompany\\nCustomers\\nNews\\nCareers\\nPress Inquiries\\nSupport\\nStatus\\nAvailability\\nTwitter\\nLinkedIn\\nYouTube\\nTerms of Service – Consumer\\nTerms of Service – Commercial\\nPrivacy Policy\\nUsage Policy\\nResponsible Disclosure Policy\\nCompliance\\nPrivacy Choices\\n© 2024 Anthropic PBC\\n\\n\\n\\nenterprise page\\nWebpage Title:\\nEnterprise \\\\ Anthropic\\nWebpage Contents:\\nClaude\\nOverview\\nTeam\\nEnterprise\\nAPI\\nPricing\\nResearch\\nCompany\\nCareers\\nNews\\nClaude for\\n Enterprise\\nSecurely connect Claude to your company knowledge and empower every team with trusted AI.\\nContact sales\\nEmpower your entire organization with AI\\nEnable every team to spark new ideas, achieve more, and collaborate better.\\nUse company knowledge\\nScale internal expertise and knowledge across projects and teams.\\nCreate and share work\\nProduce high-impact output more efficiently with Claude.\\nSecure your data\\nProtect your sensitive data. Anthropic does not train our models on your Claude for Work data.\\nUse company knowledge\\nBring internal knowledge to scale institutional expertise, collaboration and decision-making across your enterpris\"" |
|
] |
|
}, |
|
"execution_count": 18, |
|
"metadata": {}, |
|
"output_type": "execute_result" |
|
} |
|
], |
|
"source": [ |
|
"get_brochure_user_prompt(\"Anthropic\", \"https://anthropic.com\")" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 19, |
|
"id": "e44de579-4a1a-4e6a-a510-20ea3e4b8d46", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"def create_brochure(company_name, url):\n", |
|
" response = openai.chat.completions.create(\n", |
|
" model=MODEL,\n", |
|
" messages=[\n", |
|
" {\"role\": \"system\", \"content\": system_prompt},\n", |
|
" {\"role\": \"user\", \"content\": get_brochure_user_prompt(company_name, url)}\n", |
|
" ],\n", |
|
" )\n", |
|
" result = response.choices[0].message.content\n", |
|
" display(Markdown(result))" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 20, |
|
"id": "e093444a-9407-42ae-924a-145730591a39", |
|
"metadata": {}, |
|
"outputs": [ |
|
{ |
|
"name": "stdout", |
|
"output_type": "stream", |
|
"text": [ |
|
"Found links: {'links': [{'type': 'about page', 'url': 'https://anthropic.com/company'}, {'type': 'careers page', 'url': 'https://anthropic.com/careers'}, {'type': 'team page', 'url': 'https://anthropic.com/team'}, {'type': 'research page', 'url': 'https://anthropic.com/research'}, {'type': 'pricing page', 'url': 'https://anthropic.com/pricing'}, {'type': 'enterprise page', 'url': 'https://anthropic.com/enterprise'}, {'type': 'api page', 'url': 'https://anthropic.com/api'}, {'type': 'news page', 'url': 'https://anthropic.com/news'}]}\n" |
|
] |
|
}, |
|
{ |
|
"data": { |
|
"text/markdown": [ |
|
"# Anthropic Company Brochure\n", |
|
"\n", |
|
"## Overview\n", |
|
"Anthropic is a pioneering AI safety and research organization based in San Francisco, committed to developing reliable, interpretable, and steerable AI systems. With a strong focus on safety as a scientific discipline, Anthropic aims to generate insights on the opportunities and risks associated with AI developments. The company promotes collaboration with civil society, government, academia, and industry to foster a safer AI ecosystem for the world.\n", |
|
"\n", |
|
"## Our Purpose\n", |
|
"At Anthropic, we believe that AI will have a significant impact on the world. Our mission is to ensure that transformative AI benefits society and individuals alike. Our interdisciplinary team of researchers, engineers, policy experts, and operational leaders works collaboratively to tackle the challenges posed by advanced AI technologies.\n", |
|
"\n", |
|
"## Products\n", |
|
"### Claude\n", |
|
"**Claude 3.5 Sonnet**: Our most advanced AI model designed to assist businesses in driving efficiency and creating new revenue streams. Claude serves as a virtual teammate, enhancing productivity through automation and intelligent collaboration.\n", |
|
"\n", |
|
"### Enterprise Solutions\n", |
|
"Anthropic provides enterprise-level solutions that seamlessly connect Claude to organizational knowledge, empowering teams to harness the full potential of AI in their workflows. Our offerings include tailored integrations that foster innovation and improve operational efficiencies across various functions like Engineering, Marketing, Sales, and Customer Support.\n", |
|
"\n", |
|
"## Customers\n", |
|
"Our diverse clientele consists of businesses, nonprofits, and civil society organizations that leverage Claude's capabilities to enhance their operations, creative processes, and overall productivity. Customers have reported significant improvements in efficiency, such as achieving project outcomes in markedly reduced timeframes.\n", |
|
"\n", |
|
"## Team and Culture\n", |
|
"At Anthropic, we uphold a culture of unusually high trust, emotional maturity, and intellectual openness. We operate as one cohesive team, valuing collaboration across disciplines to enrich our work. Our values reflect our commitment to our mission and our drive to ensure that our systems help society flourish.\n", |
|
"\n", |
|
"### Company Values\n", |
|
"1. **Here for the Mission**: We are dedicated to building AI systems that prioritize safety and human benefit.\n", |
|
"2. **Unusually High Trust**: Our work environment fosters honesty and constructive disagreement.\n", |
|
"3. **One Big Team**: Collaboration is central; input from all levels shapes our organizational goals.\n", |
|
"4. **Do the Simple Thing That Works**: We embrace pragmatic, evidence-based approaches in our processes.\n", |
|
"\n", |
|
"## Careers at Anthropic\n", |
|
"Join us in our mission to make AI safe for the future. At Anthropic, we pride ourselves on hiring individuals from diverse backgrounds, ensuring a rich variety of perspectives in our team.\n", |
|
"\n", |
|
"### What We Offer\n", |
|
"- **Health & Wellness**: Comprehensive health benefits, inclusive fertility support, flexible paid time off, and generous mental health resources.\n", |
|
"- **Compensation & Support**: Competitive salaries, equity packages, robust retirement plans, and additional perks like a wellness stipend and daily meals in our office.\n", |
|
"- **Career Growth**: Opportunities to work on cutting-edge research and contribute to impactful AI technology, alongside a supportive and collaborative work environment.\n", |
|
"\n", |
|
"### How to Apply\n", |
|
"Our interview process is designed to minimize bias and highlight each candidate's strengths. It includes:\n", |
|
"1. **Resume Submission**\n", |
|
"2. **Exploratory Chat**\n", |
|
"3. **Skills Assessment**\n", |
|
"4. **Team Screening**\n", |
|
"5. **Interview Panel**\n", |
|
"6. **Final Checks and Offer**\n", |
|
"\n", |
|
"We welcome talented individuals passionate about AI safety and innovation. Explore our open roles on our [Careers Page](https://www.anthropic.com/careers).\n", |
|
"\n", |
|
"## Join Us\n", |
|
"If you're eager to contribute to AI's future and want to explore innovative ways to ensure its safe development, we invite you to connect with us. Together, let's build AI that people can rely on.\n", |
|
"\n", |
|
"**Website**: [Anthropic](https://www.anthropic.com)\n", |
|
"\n", |
|
"**Social Media**: Follow us on [LinkedIn](https://www.linkedin.com/company/anthropic) and [Twitter](https://twitter.com/AnthropicAI) for the latest updates.\n", |
|
"\n", |
|
"--- \n", |
|
"\n", |
|
"This brochure encapsulates Anthropic's mission, culture, product offerings, and career opportunities. We look forward to welcoming you to our team and the future of AI!" |
|
], |
|
"text/plain": [ |
|
"<IPython.core.display.Markdown object>" |
|
] |
|
}, |
|
"metadata": {}, |
|
"output_type": "display_data" |
|
} |
|
], |
|
"source": [ |
|
"create_brochure(\"Anthropic\", \"https://anthropic.com\")" |
|
] |
|
}, |
|
{ |
|
"cell_type": "markdown", |
|
"id": "61eaaab7-0b47-4b29-82d4-75d474ad8d18", |
|
"metadata": {}, |
|
"source": [ |
|
"## Finally - a minor improvement\n", |
|
"\n", |
|
"With a small adjustment, we can change this so that the results stream back from OpenAI,\n", |
|
"with the familiar typewriter animation" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 21, |
|
"id": "51db0e49-f261-4137-aabe-92dd601f7725", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"def stream_brochure(company_name, url):\n", |
|
" stream = openai.chat.completions.create(\n", |
|
" model=MODEL,\n", |
|
" messages=[\n", |
|
" {\"role\": \"system\", \"content\": system_prompt},\n", |
|
" {\"role\": \"user\", \"content\": get_brochure_user_prompt(company_name, url)}\n", |
|
" ],\n", |
|
" stream=True\n", |
|
" )\n", |
|
" \n", |
|
" response = \"\"\n", |
|
" display_handle = display(Markdown(\"\"), display_id=True)\n", |
|
" for chunk in stream:\n", |
|
" response += chunk.choices[0].delta.content or ''\n", |
|
" response = response.replace(\"```\",\"\").replace(\"markdown\", \"\")\n", |
|
" update_display(Markdown(response), display_id=display_handle.display_id)" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 22, |
|
"id": "56bf0ae3-ee9d-4a72-9cd6-edcac67ceb6d", |
|
"metadata": {}, |
|
"outputs": [ |
|
{ |
|
"name": "stdout", |
|
"output_type": "stream", |
|
"text": [ |
|
"Found links: {'links': [{'type': 'about page', 'url': 'https://www.anthropic.com/company'}, {'type': 'careers page', 'url': 'https://www.anthropic.com/careers'}, {'type': 'team page', 'url': 'https://www.anthropic.com/team'}, {'type': 'research page', 'url': 'https://www.anthropic.com/research'}, {'type': 'news page', 'url': 'https://www.anthropic.com/news'}]}\n" |
|
] |
|
}, |
|
{ |
|
"data": { |
|
"text/markdown": [ |
|
"# Anthropic Brochure\n", |
|
"\n", |
|
"---\n", |
|
"\n", |
|
"## About Us\n", |
|
"\n", |
|
"**Anthropic** is an AI safety and research company headquartered in San Francisco, dedicated to developing reliable, interpretable, and steerable AI systems. With the belief that AI will have a vast impact on the world, we focus on building systems that people can trust while generating research about the opportunities and risks of AI. Our mission is to ensure that transformative AI helps people and society flourish.\n", |
|
"\n", |
|
"---\n", |
|
"\n", |
|
"## Our Products\n", |
|
"\n", |
|
"### Claude\n", |
|
"Claude is our flagship AI assistant, designed to empower teams by enhancing productivity and collaboration. Users can utilize Claude for tasks such as:\n", |
|
"\n", |
|
"- Drafting and iterating documents\n", |
|
"- Writing and debugging code\n", |
|
"- Creating marketing content\n", |
|
"- Generating insightful reports\n", |
|
"\n", |
|
"Claude is equipped to assist across various functions within organizations, ensuring that every team member has access to shared knowledge and expertise.\n", |
|
"\n", |
|
"### API\n", |
|
"Our API enables businesses to integrate Claude’s capabilities into their existing systems, driving efficiency and creating new revenue streams.\n", |
|
"\n", |
|
"---\n", |
|
"\n", |
|
"## Company Culture\n", |
|
"\n", |
|
"At Anthropic, we emphasize a culture of **collaboration**, **trust**, and **intellectual openness**. Our values include:\n", |
|
"\n", |
|
"1. **Here for the Mission**: Focused on ensuring that AI systems are safe and beneficial for society.\n", |
|
"2. **Unusually High Trust**: We prioritize honesty and the assumption of good faith in all interactions.\n", |
|
"3. **One Big Team**: Promoting collaboration across all teams, recognizing that every member contributes to the organization's shared goals.\n", |
|
"4. **Pragmatic Approach**: We celebrate simplistic solutions to problems and rely on empirical evidence to guide our practices.\n", |
|
"\n", |
|
"---\n", |
|
"\n", |
|
"## Our Team\n", |
|
"\n", |
|
"Anthropic's diverse team consists of researchers, engineers, policy experts, and operational leaders, all bringing different expertise to our mission. We foster an interdisciplinary approach, combining knowledge from various domains such as machine learning, physics, and public policy. Our leadership encourages input from all levels, ensuring that every voice contributes to the company’s strategic direction.\n", |
|
"\n", |
|
"---\n", |
|
"\n", |
|
"## Careers at Anthropic\n", |
|
"\n", |
|
"We are always on the lookout for talented individuals who are passionate about AI safety and innovation. Our hiring process is designed to identify thoughtful candidates from varied backgrounds, with a commitment to reduce biases. \n", |
|
"\n", |
|
"### What We Offer\n", |
|
"- **Health & Wellness**: Comprehensive healthcare, flexible paid time off, and generous mental health support.\n", |
|
"- **Competitive Compensation**: Attractive salary, equity packages, and additional benefits like stipends for wellness and education.\n", |
|
"- **Growth Opportunities**: As a public benefit corporation, we're invested in the long-term benefits of our employees and the communities we serve.\n", |
|
"\n", |
|
"### Join Us\n", |
|
"Check our [Careers page](https://anthropic.com/careers) for open roles and more information on how to apply.\n", |
|
"\n", |
|
"---\n", |
|
"\n", |
|
"## Customers\n", |
|
"\n", |
|
"Our products benefit businesses, nonprofits, and civil society organizations globally. Customer success stories highlight tangible improvements in productivity and efficiency, thanks to Claude’s capabilities. \n", |
|
"\n", |
|
"---\n", |
|
"\n", |
|
"## Follow Along\n", |
|
"\n", |
|
"Stay updated on our latest innovations and developments by following us on social media:\n", |
|
"\n", |
|
"- [Twitter](https://twitter.com/anthropic)\n", |
|
"- [LinkedIn](https://linkedin.com/company/anthropic)\n", |
|
"- [YouTube](https://youtube.com/@anthropic)\n", |
|
"\n", |
|
"---\n", |
|
"\n", |
|
"For more information, please visit our website at [Anthropic](https://anthropic.com) or reach out via our support channels.\n", |
|
"\n", |
|
"**Anthropic** – *Building reliable, interpretable, and safe AI systems for a better future.*" |
|
], |
|
"text/plain": [ |
|
"<IPython.core.display.Markdown object>" |
|
] |
|
}, |
|
"metadata": {}, |
|
"output_type": "display_data" |
|
} |
|
], |
|
"source": [ |
|
"stream_brochure(\"Anthropic\", \"https://anthropic.com\")" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 23, |
|
"id": "fdb3f8d8-a3eb-41c8-b1aa-9f60686a653b", |
|
"metadata": {}, |
|
"outputs": [ |
|
{ |
|
"name": "stdout", |
|
"output_type": "stream", |
|
"text": [ |
|
"Found links: {'links': [{'type': 'about page', 'url': 'https://huggingface.co'}, {'type': 'enterprise page', 'url': 'https://huggingface.co/enterprise'}, {'type': 'pricing page', 'url': 'https://huggingface.co/pricing'}, {'type': 'careers page', 'url': 'https://apply.workable.com/huggingface/'}, {'type': 'blog page', 'url': 'https://huggingface.co/blog'}, {'type': 'discussion forum', 'url': 'https://discuss.huggingface.co'}, {'type': 'GitHub page', 'url': 'https://github.com/huggingface'}, {'type': 'Twitter page', 'url': 'https://twitter.com/huggingface'}, {'type': 'LinkedIn page', 'url': 'https://www.linkedin.com/company/huggingface/'}]}\n" |
|
] |
|
}, |
|
{ |
|
"data": { |
|
"text/markdown": [ |
|
"# Hugging Face Brochure\n", |
|
"\n", |
|
"## About Us\n", |
|
"**Hugging Face** is an innovative AI community dedicated to building the future through collaborative machine learning. Our platform serves as the home for researchers, developers, and organizations to create, discover, and utilize state-of-the-art models and datasets. With over 400,000 models and 100,000 datasets available, we foster a collaborative environment that empowers all participants in the machine learning ecosystem.\n", |
|
"\n", |
|
"## Our Offerings\n", |
|
"- **Models**: Access to a vast library of machine learning models across various modalities, including text, images, videos, and more.\n", |
|
"- **Datasets**: Comprehensive datasets to facilitate training and evaluation across multiple domains.\n", |
|
"- **Spaces**: Host and share interactive machine learning applications easily.\n", |
|
"- **Enterprise Solutions**: Tailored offerings that focus on security, support, and features for large organizations.\n", |
|
"\n", |
|
"## Customers\n", |
|
"We proudly serve more than **50,000 organizations**, including prominent companies like:\n", |
|
"- Amazon Web Services\n", |
|
"- Google\n", |
|
"- Microsoft\n", |
|
"- Intel\n", |
|
"- Grammarly\n", |
|
"\n", |
|
"Our community continues to grow, making it a thriving hub for AI-driven companies.\n", |
|
"\n", |
|
"## Company Culture\n", |
|
"At Hugging Face, we prioritize community collaboration and open-source contributions. Our culture is built on the principles of transparency, inclusivity, and innovation, which are vital for advancing machine learning technology. We encourage our team members to engage in knowledge-sharing and continuous learning.\n", |
|
"\n", |
|
"## Careers\n", |
|
"We are constantly looking for talented individuals to join our team. Opportunities range from research and development roles to positions in sales, marketing, and operations. If you're interested in being part of a forward-thinking AI organization, explore our current openings on our [careers page](#).\n", |
|
"\n", |
|
"## Join Us\n", |
|
"Explore the exciting possibilities that Hugging Face has to offer! Whether you’re looking to collaborate on innovative machine learning models, deploy applications, or join our vibrant community, there's a place for you here.\n", |
|
"\n", |
|
"**Get Started Today!**\n", |
|
"- Visit us at [Hugging Face](https://huggingface.co/)\n", |
|
"- Connect with our community on [GitHub](https://github.com/huggingface), [Twitter](https://twitter.com/huggingface), [LinkedIn](https://www.linkedin.com/company/huggingface/)\n", |
|
"\n", |
|
"Together, let’s build the future of AI! 🌟" |
|
], |
|
"text/plain": [ |
|
"<IPython.core.display.Markdown object>" |
|
] |
|
}, |
|
"metadata": {}, |
|
"output_type": "display_data" |
|
} |
|
], |
|
"source": [ |
|
"# Try changing the system prompt to the humorous version when you make the Brochure for Hugging Face:\n", |
|
"\n", |
|
"stream_brochure(\"HuggingFace\", \"https://huggingface.co\")" |
|
] |
|
}, |
|
{ |
|
"cell_type": "markdown", |
|
"id": "a27bf9e0-665f-4645-b66b-9725e2a959b5", |
|
"metadata": {}, |
|
"source": [ |
|
"<table style=\"margin: 0; text-align: left;\">\n", |
|
" <tr>\n", |
|
" <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n", |
|
" <img src=\"../business.jpg\" width=\"150\" height=\"150\" style=\"display: block;\" />\n", |
|
" </td>\n", |
|
" <td>\n", |
|
" <h2 style=\"color:#181;\">Business applications</h2>\n", |
|
" <span style=\"color:#181;\">In this exercise we extended the Day 1 code to make multiple LLM calls, and generate a document.\n", |
|
"\n", |
|
"This is perhaps the first example of Agentic AI design patterns, as we combined multiple calls to LLMs. This will feature more in Week 2, and then we will return to Agentic AI in a big way in Week 8 when we build a fully autonomous Agent solution.\n", |
|
"\n", |
|
"Generating content in this way is one of the very most common Use Cases. As with summarization, this can be applied to any business vertical. Write marketing content, generate a product tutorial from a spec, create personalized email content, and so much more. Explore how you can apply content generation to your business, and try making yourself a proof-of-concept prototype.</span>\n", |
|
" </td>\n", |
|
" </tr>\n", |
|
"</table>" |
|
] |
|
}, |
|
{ |
|
"cell_type": "markdown", |
|
"id": "14b2454b-8ef8-4b5c-b928-053a15e0d553", |
|
"metadata": {}, |
|
"source": [ |
|
"<table style=\"margin: 0; text-align: left;\">\n", |
|
" <tr>\n", |
|
" <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n", |
|
" <img src=\"../important.jpg\" width=\"150\" height=\"150\" style=\"display: block;\" />\n", |
|
" </td>\n", |
|
" <td>\n", |
|
" <h2 style=\"color:#900;\">Before you move to Week 2 (which is tons of fun)</h2>\n", |
|
" <span style=\"color:#900;\">Please see the week1 EXERCISE notebook for your challenge for the end of week 1. This will give you some essential practice working with Frontier APIs, and prepare you well for Week 2.</span>\n", |
|
" </td>\n", |
|
" </tr>\n", |
|
"</table>" |
|
] |
|
}, |
|
{ |
|
"cell_type": "markdown", |
|
"id": "17b64f0f-7d33-4493-985a-033d06e8db08", |
|
"metadata": {}, |
|
"source": [ |
|
"<table style=\"margin: 0; text-align: left;\">\n", |
|
" <tr>\n", |
|
" <td style=\"width: 150px; height: 150px; vertical-align: middle;\">\n", |
|
" <img src=\"../resources.jpg\" width=\"150\" height=\"150\" style=\"display: block;\" />\n", |
|
" </td>\n", |
|
" <td>\n", |
|
" <h2 style=\"color:#f71;\">A reminder on 2 useful resources</h2>\n", |
|
" <span style=\"color:#f71;\">1. The resources for the course are available <a href=\"https://edwarddonner.com/2024/11/13/llm-engineering-resources/\">here.</a><br/>\n", |
|
" 2. I'm on LinkedIn <a href=\"https://www.linkedin.com/in/eddonner/\">here</a> and I love connecting with people taking the course!\n", |
|
" </span>\n", |
|
" </td>\n", |
|
" </tr>\n", |
|
"</table>" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "3de35771-455f-40b5-ba44-7c0a6b7c427a", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [] |
|
} |
|
], |
|
"metadata": { |
|
"kernelspec": { |
|
"display_name": "Python 3 (ipykernel)", |
|
"language": "python", |
|
"name": "python3" |
|
}, |
|
"language_info": { |
|
"codemirror_mode": { |
|
"name": "ipython", |
|
"version": 3 |
|
}, |
|
"file_extension": ".py", |
|
"mimetype": "text/x-python", |
|
"name": "python", |
|
"nbconvert_exporter": "python", |
|
"pygments_lexer": "ipython3", |
|
"version": "3.11.10" |
|
} |
|
}, |
|
"nbformat": 4, |
|
"nbformat_minor": 5 |
|
}
|
|
|