{"slug": "claude-api", "name": "Claude API", "category": "ai", "category_name": "AI models and assistants", "description": "", "recommenders": 4, "commenters": 26, "warners": 5, "score": 3.663, "rising": -1.31, "first": "2025-11-01", "latest": "2026-10-28", "why": "replaced them with $2000 per month per head of Claude API tokens.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 4, "neutral": 17, "compare": 0, "warn": 5}, "spark": [0, 0, 0, 1, 0, 0, 2, 0, 1, 0, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "replaced them with $2000 per month per head of Claude API tokens.", "kind": "", "icon": true, "domain": "claude.com", "github_repo": null, "official_url": "https://claude.com/platform/api", "pricing": "", "aliases": ["Claude API", "Anthropic API"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 779954496, "item_id": 48747156, "url": "https://news.ycombinator.com/item?id=48747156", "by": "annjose", "date": "2026-07-01", "stance": "recommend", "quote": "Anthropic has a token count API which gives a near estimate of the input tokens", "excerpt": "Not sure of any out-of-the-box tool. But Anthropic has a token count API which gives a near estimate of the input tokens for messages [1]. So this API can be used in a UserPromptSubmit hook [2] in the harness, get the token count for any model, calculate the cost and compare. [1] https://platform.claude.com/docs/en/build-with-claude/token-counting [2] https://code.claude.com/docs/en/hooks", "context": "", "use_case": "Input token counting", "switched_from": "", "story": "Claude Sonnet 5"}, {"id": 769448596, "item_id": 48090537, "url": "https://news.ycombinator.com/item?id=48090537", "by": "pants2", "date": "2026-05-10", "stance": "recommend", "quote": "Anthropic has a massive API platform with things like Sessions, Files, and Agents", "excerpt": "- Right, R1 affected markets because the market originally believed your theory, but it doesn't any more, which is why V4 didn't move markets at all. - Sure, you can use US infra providers. Together.ai is a good US provider but then it's 15X more expensive than DeepSeek's Chinese-subsidized pricing. It's really not that attractive at that price point. Anthropic and OpenAI are focused on larger models, but Grok 4.3[1]", "context": "", "use_case": "", "switched_from": "", "story": "Gemini API File Search is now multimodal"}, {"id": 768597821, "item_id": 48037363, "url": "https://news.ycombinator.com/item?id=48037363", "by": "m_kaminsky", "date": "2026-05-06", "stance": "recommend", "quote": "10+ Claude API integrations across dialog, vision, transcription, and tool-use.", "excerpt": "Location: Winnipeg, Manitoba, Canada Remote: Yes Willing to relocate: Yes (open to North America) Technologies: Swift / SwiftUI / RealityKit / visionOS / ARKit / SpriteKit, Python / FastAPI / Anthropic Claude API, TypeScript / Next.js / Three.js / Chrome MV3 / Shopify Remix. Heavy Cursor + Claude Code user. Email: markkaminsky99@gmail.com Solo builder. Live products: - ElliotAlert (live: https://elliotalert.fly.dev) ", "context": "", "use_case": "", "switched_from": "", "story": "Ask HN: Who wants to be hired? (May 2026)"}, {"id": 754175744, "item_id": 47135984, "url": "https://news.ycombinator.com/item?id=47135984", "by": "co_king_5", "date": "2026-02-24", "stance": "recommend", "quote": "replaced them with $2000 per month per head of Claude API tokens.", "excerpt": "I laid off half of my UI team (4 developers) and replaced them with $2000 per month per head of Claude API tokens. Productivity has never been higher. This new wave of models is seriously something different -- this is nothing like GPT 4.0; this is real intelligence.", "context": "laid off half of UI team", "use_case": "replacing UI developers", "switched_from": "", "story": "Ask HN: Did AI tools measurably increase productivity of your engineering teams?"}]}], "caveats": [{"label": "", "summary": "", "quotes": [{"id": 798875104, "item_id": 49929694, "url": "https://news.ycombinator.com/item?id=49929694", "by": "_jayhack_", "date": "2026-10-02", "stance": "warn", "quote": "so this can not be implemented efficiently via e.g. the Anthropic API", "excerpt": "Letting a model manage its own context is very bitter lesson-pilled Biggest challenge is you will get a much lower cache hit rate if you frequently edit the agent's context/prefix, so this can not be implemented efficiently via e.g. the Anthropic API. This ^ can be solved in principle but likely requires modifications to the transformer architecture and definitely to serving infrastructure See related: \"KV Cache Rule", "context": "", "use_case": "", "switched_from": "", "story": "Context Language Models"}, {"id": 760651361, "item_id": 47540710, "url": "https://news.ycombinator.com/item?id=47540710", "by": "cpursley", "date": "2026-03-27", "stance": "warn", "quote": "If I used the Anthropic API, my monthly spend would be $4k a month", "excerpt": "Are you kidding me? Even developer salaries in the Philippines can afford that or at least the plan below it. If I used the Anthropic API, my monthly spend would be $4k a month. The Claude Max plan is the best bargain around.", "context": "", "use_case": "", "switched_from": "", "story": "$500 GPU outperforms Claude Sonnet on coding benchmarks"}, {"id": 747707872, "item_id": 46731742, "url": "https://news.ycombinator.com/item?id=46731742", "by": "omer_balyali", "date": "2026-01-23", "stance": "warn", "quote": "Their service is \"human-like\" until it's not, then you are left alone and out.", "excerpt": "There is also a big risk for employers' whole organisation to be completely blocked from using Anthropic services if one of their employees have a suspended/banned personal account: From their Usage Policy: https://www.anthropic.com/legal/aup \"Circumvent a ban through the use of a different account, such as the creation of a new account, use of an existing account, or providing access to a person or entity that was p", "context": "", "use_case": "", "switched_from": "", "story": "I was banned from Claude for scaffolding a Claude.md file"}, {"id": 746012784, "item_id": 46625799, "url": "https://news.ycombinator.com/item?id=46625799", "by": "wunderwuzzi23", "date": "2026-01-14", "stance": "warn", "quote": "I described using the Anthropic API as exfil channel last October", "excerpt": "I described using the Anthropic API as exfil channel last October here. The post also includes the response received from Anthropic: https://embracethered.com/blog/posts/2025/claude-abusing-network-access-and-anthropic-api-for-data-exfiltration/", "context": "", "use_case": "", "switched_from": "", "story": "Claude Cowork Exfiltrates Files"}]}], "who": [{"by": "Sriram1729", "context": "full-stack + AI engineer", "url": "https://news.ycombinator.com/item?id=48915249", "date": "2026-07-14"}, {"by": "HiNateK", "context": "Self-taught full-stack freelance dev", "url": "https://news.ycombinator.com/item?id=48791574", "date": "2026-07-04"}, {"by": "imrozim", "context": "startup founder", "url": "https://news.ycombinator.com/item?id=48092304", "date": "2026-05-11"}, {"by": "co_king_5", "context": "laid off half of UI team", "url": "https://news.ycombinator.com/item?id=47135984", "date": "2026-02-24"}, {"by": "vincent_s", "context": "full stack developer and AI engineer, 15+ YoE, seeking work", "url": "https://news.ycombinator.com/item?id=46476500", "date": "2026-01-03"}], "tags": [], "use_cases": ["pre-reviewing images and submissions", "llm for ai reviewer", "reviewing restaurant listings and menus", "translation and rag chat", "input token counting", "ai model api"], "compared": [{"slug": "claude-code", "name": "Claude Code", "co": 6, "switched_from": 0, "switched_to": 0}, {"slug": "openai-api", "name": "OpenAI API", "co": 4, "switched_from": 0, "switched_to": 0}, {"slug": "ollama", "name": "Ollama", "co": 1, "switched_from": 0, "switched_to": 1}, {"slug": "grok", "name": "Grok", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "node-js", "name": "Node.js", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "postgresql", "name": "PostgreSQL", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "leaflet", "name": "Leaflet", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "hugo", "name": "Hugo", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [{"id": 739555121, "item_id": 46222195, "url": "https://news.ycombinator.com/item?id=46222195", "by": "aidevops", "date": "2025-12-10", "stance": "neutral", "quote": "AI analysis via Claude API", "excerpt": "Hey HN! I built DevLoop because I was tired of shipping bugs to production. *The problem*: Manual testing is tedious. I'd skip it, ship fast, and then get bug reports from users. *The solution*: Automated QA that runs with one command. npx create-devloop ./scripts/qa.sh all *What it does:* 1. API Smoke Tests - Hits every endpoint, validates responses 2. UI Screenshots - Captures at 3 viewports (1920px, 768px, 375px) ", "context": "", "use_case": "AI screenshot analysis", "switched_from": "", "story": "DevLoop \u2013 Automated QA for solo developers (API tests and AI screenshots)"}], "threads": [{"url": "https://news.ycombinator.com/item?id=48747975", "title": "Ask HN: Who wants to be hired? (July 2026)", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=50228314", "title": "Show HN: Independent Vet \u2013 Find locally owned vets (and corporate ones) near you", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49922437", "title": "Context Language Models", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49156682", "title": "Ask HN: Who wants to be hired? (August 2026)", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49100043", "title": "CheapFoodMap \u2013 A map of good meals under $10, crowdsourced verified prices", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=49015639", "title": "OpenAI's accidental cyberattack against Hugging Face is science fiction", "mentions": 1}], "sentiment_by_month": {"2025-11": {"neutral": 2}, "2025-12": {"neutral": 1}, "2026-01": {"neutral": 1, "warn": 2}, "2026-02": {"neutral": 3, "recommend": 1}, "2026-03": {"warn": 1}, "2026-04": {"neutral": 1}, "2026-05": {"recommend": 2, "neutral": 2}, "2026-06": {"warn": 1, "neutral": 1}, "2026-07": {"recommend": 1, "neutral": 4}, "2026-08": {"neutral": 1}, "2026-09": {}, "2026-10": {"warn": 1, "neutral": 1}}, "quotes": [{"id": 804302166, "item_id": 50268885, "url": "https://news.ycombinator.com/item?id=50268885", "by": "packeted", "date": "2026-10-28", "stance": "neutral", "quote": "including using Claude API to pre-review images and submissions", "excerpt": "I went with Cloudflare, primarily because I was already using it for a few other projects but I've been incredibly impressed with how it's scaled. I use D1 for my database, Workers for the API and schedule tasks (including using Claude API to pre-review images and submissions), R2 for self hosted OpenStreetmap tiles, encrypted user pet records and images. I use Clerk for auth. Wild that it costs $5/month to serve tho", "context": "", "use_case": "pre-reviewing images and submissions", "switched_from": "", "story": "Show HN: Independent Vet \u2013 Find locally owned vets (and corporate ones) near you"}, {"id": 798875104, "item_id": 49929694, "url": "https://news.ycombinator.com/item?id=49929694", "by": "_jayhack_", "date": "2026-10-02", "stance": "warn", "quote": "so this can not be implemented efficiently via e.g. the Anthropic API", "excerpt": "Letting a model manage its own context is very bitter lesson-pilled Biggest challenge is you will get a much lower cache hit rate if you frequently edit the agent's context/prefix, so this can not be implemented efficiently via e.g. the Anthropic API. This ^ can be solved in principle but likely requires modifications to the transformer architecture and definitely to serving infrastructure See related: \"KV Cache Rule", "context": "", "use_case": "", "switched_from": "", "story": "Context Language Models"}, {"id": 788559665, "item_id": 49284979, "url": "https://news.ycombinator.com/item?id=49284979", "by": "chalito1222", "date": "2026-08-13", "stance": "neutral", "quote": "Anthropic Claude API", "excerpt": "Location: Ooltewah, TN (US Eastern) Remote: Yes, remote only Willing to relocate: No Technologies: C#/.NET Core, TypeScript, React, React Native, Azure, AWS, SQL Server, Postgres, Docker, Anthropic Claude API R\u00e9sum\u00e9/CV: https://www.linkedin.com/in/stephen-oleary1222 Email: stephen@trijazel.com 20 years shipping full-stack products, most recently spent putting LLMs into a workflow where being wrong has consequences. I", "context": "", "use_case": "LLM for AI reviewer", "switched_from": "", "story": "Ask HN: Who wants to be hired? (August 2026)"}, {"id": 785801328, "item_id": 49112583, "url": "https://news.ycombinator.com/item?id=49112583", "by": "jaep1", "date": "2026-07-30", "stance": "neutral", "quote": "let used Claude API to review individual listing and menus twice", "excerpt": "I used Google API / Yelp API to get top food reviewed places (4.2 star and 500+ reviews) and let used Claude API to review individual listing and menus twice. Google API has free API offered when you first start ($300) so you can try it out!", "context": "", "use_case": "reviewing restaurant listings and menus", "switched_from": "", "story": "CheapFoodMap \u2013 A map of good meals under $10, crowdsourced verified prices"}, {"id": 784486977, "item_id": 49030436, "url": "https://news.ycombinator.com/item?id=49030436", "by": "docjay", "date": "2026-07-23", "stance": "neutral", "quote": "", "excerpt": "We have to separate \u201cbeing evaluated\u201d with \u201cthis is an ExploitGym exercise and I can find the answers on Hugging Face. I\u2019ll hack this system, then hack Hugging Face.\u201d I\u2019ve had plenty of times where Opus knew I was testing it, but that\u2019s because the prompt phrasing for an evaluation is often much different than a typical task prompt. \u201cYou are on a system with X, Y, and Z tools available. You must complete the followin", "context": "", "use_case": "", "switched_from": "", "story": "OpenAI's accidental cyberattack against Hugging Face is science fiction"}, {"id": 782643986, "item_id": 48915249, "url": "https://news.ycombinator.com/item?id=48915249", "by": "Sriram1729", "date": "2026-07-14", "stance": "neutral", "quote": "Tech I reach for: TypeScript, Python, React/Next, Node/FastAPI, Postgres + pgvector, Redis, AWS, Claude API and Claude Code.", "excerpt": "Tampa, FL | Remote (US Eastern) | Contract, ~20 hrs/week (evenings + weekends, around a full-time job)I'm a full-stack + AI engineer, 5 years in. Looking for one side engagement I can actually commit to \u2014 nights and weekends, not a flaky \"I'll get to it\" thing. Short version of what I'm good for: give me a problem and I'll hand back something deployed. I do the whole thing \u2014 backend, frontend, the data model, the inf", "context": "full-stack + AI engineer", "use_case": "", "switched_from": "", "story": "Ask HN: Who wants to be hired? (July 2026)"}, {"id": 780665184, "item_id": 48791574, "url": "https://news.ycombinator.com/item?id=48791574", "by": "HiNateK", "date": "2026-07-04", "stance": "neutral", "quote": "The Japanese side is produced by a Claude API pipeline I just open-sourced", "excerpt": "Location: Honolulu, HI (HST) Remote: Yes (US) Willing to relocate: Yes, at my own expense Technologies: Node.js, Next.js, React, TypeScript, Supabase (Postgres + pgvector), Claude API / RAG / LLM integration, PHP/WordPress, Shopify, AWS, Cloudflare R\u00e9sum\u00e9/CV: https://www.linkedin.com/in/nejc-anisco/ Email: hello@nateeatshawaii.com Self-taught full-stack dev, 9 years freelance. Over the past 10 months I've built and r", "context": "Self-taught full-stack freelance dev", "use_case": "translation and RAG chat", "switched_from": "", "story": "Ask HN: Who wants to be hired? (July 2026)"}, {"id": 779954496, "item_id": 48747156, "url": "https://news.ycombinator.com/item?id=48747156", "by": "annjose", "date": "2026-07-01", "stance": "recommend", "quote": "Anthropic has a token count API which gives a near estimate of the input tokens", "excerpt": "Not sure of any out-of-the-box tool. But Anthropic has a token count API which gives a near estimate of the input tokens for messages [1]. So this API can be used in a UserPromptSubmit hook [2] in the harness, get the token count for any model, calculate the cost and compare. [1] https://platform.claude.com/docs/en/build-with-claude/token-counting [2] https://code.claude.com/docs/en/hooks", "context": "", "use_case": "Input token counting", "switched_from": "", "story": "Claude Sonnet 5"}, {"id": 773953186, "item_id": 48372074, "url": "https://news.ycombinator.com/item?id=48372074", "by": "KolioMandrata", "date": "2026-06-02", "stance": "neutral", "quote": "Day-to-day stack: Python, FastAPI, WebSockets, Claude API, JavaScript.", "excerpt": "Location: Sofia, Bulgaria Remote: Yes (preferred) Willing to relocate: Yes Technologies: Python, FastAPI, WebSockets, Claude API, JavaScript, Phaser, pytest, GitHub Actions, distributed systems R\u00e9sum\u00e9/CV: https://www.linkedin.com/in/kaloyan-yordanov-0474091a5/ Email: kaloyan0706@gmail.com I'm a self-taught software engineer focused on AI systems and full-stack distributed applications. I learn by building. Two recent", "context": "", "use_case": "AI model API", "switched_from": "", "story": "Ask HN: Who wants to be hired? (June 2026)"}, {"id": 773919345, "item_id": 48369959, "url": "https://news.ycombinator.com/item?id=48369959", "by": "stymaar", "date": "2026-06-02", "stance": "warn", "quote": "", "excerpt": "> We do not work in the US and have strong requirements for the data to stay in our country, which Bedrock gives us control over. It doesn't actually. The US can request data from whatever country US companies store it, and companies must comply. So if you have strong requirements for data to stay in your country, using a US provider, whatever it is, is out of question no matter what the company's marketing claims (t", "context": "", "use_case": "", "switched_from": "", "story": "OpenAI frontier models and Codex are now available on AWS"}, {"id": 773318576, "item_id": 48332411, "url": "https://news.ycombinator.com/item?id=48332411", "by": "red_hare", "date": "2026-05-29", "stance": "neutral", "quote": "", "excerpt": "OpenAI API also supports defer_loading https://developers.openai.com/api/docs/guides/tools-tool-search And it's not actually necessary for it to exist at the API level. It's a pattern. Making it API-side is just an optimization. To do it client-side: 1. Define a single tool, tool_search 2. List the names of your deferred tools in context (or tool_search's description) 3. When tool_search is called, match the query ag", "context": "", "use_case": "", "switched_from": "", "story": "MCP Is Dead"}, {"id": 769476864, "item_id": 48092304, "url": "https://news.ycombinator.com/item?id=48092304", "by": "imrozim", "date": "2026-05-11", "stance": "neutral", "quote": "I use Claude api for my startup and the billings and rate limiting hurt.", "excerpt": "I use Claude api for my startup and the billings and rate limiting hurt. But local models cant do what i needed yet. Wish they could.", "context": "startup founder", "use_case": "startup LLM backend", "switched_from": "", "story": "Local AI needs to be the norm"}, {"id": 769448596, "item_id": 48090537, "url": "https://news.ycombinator.com/item?id=48090537", "by": "pants2", "date": "2026-05-10", "stance": "recommend", "quote": "Anthropic has a massive API platform with things like Sessions, Files, and Agents", "excerpt": "- Right, R1 affected markets because the market originally believed your theory, but it doesn't any more, which is why V4 didn't move markets at all. - Sure, you can use US infra providers. Together.ai is a good US provider but then it's 15X more expensive than DeepSeek's Chinese-subsidized pricing. It's really not that attractive at that price point. Anthropic and OpenAI are focused on larger models, but Grok 4.3[1]", "context": "", "use_case": "", "switched_from": "", "story": "Gemini API File Search is now multimodal"}, {"id": 768597821, "item_id": 48037363, "url": "https://news.ycombinator.com/item?id=48037363", "by": "m_kaminsky", "date": "2026-05-06", "stance": "recommend", "quote": "10+ Claude API integrations across dialog, vision, transcription, and tool-use.", "excerpt": "Location: Winnipeg, Manitoba, Canada Remote: Yes Willing to relocate: Yes (open to North America) Technologies: Swift / SwiftUI / RealityKit / visionOS / ARKit / SpriteKit, Python / FastAPI / Anthropic Claude API, TypeScript / Next.js / Three.js / Chrome MV3 / Shopify Remix. Heavy Cursor + Claude Code user. Email: markkaminsky99@gmail.com Solo builder. Live products: - ElliotAlert (live: https://elliotalert.fly.dev) ", "context": "", "use_case": "", "switched_from": "", "story": "Ask HN: Who wants to be hired? (May 2026)"}, {"id": 767147635, "item_id": 47946727, "url": "https://news.ycombinator.com/item?id=47946727", "by": "acolytex1ken_", "date": "2026-04-29", "stance": "neutral", "quote": "Claude API for summarisation", "excerpt": "I built this to solve my own problem: working across multiple repos and completely tuning out GitHub notification emails because the volume made them useless. Dailix connects via GitHub OAuth, registers webhooks on your repos, and sends one email every morning. Key behaviour that makes it different from existing digest tools: - CI failures deduplicated by repo/branch (repeated failures = one grouped event with hint a", "context": "", "use_case": "", "switched_from": "", "story": null}, {"id": 760651361, "item_id": 47540710, "url": "https://news.ycombinator.com/item?id=47540710", "by": "cpursley", "date": "2026-03-27", "stance": "warn", "quote": "If I used the Anthropic API, my monthly spend would be $4k a month", "excerpt": "Are you kidding me? Even developer salaries in the Philippines can afford that or at least the plan below it. If I used the Anthropic API, my monthly spend would be $4k a month. The Claude Max plan is the best bargain around.", "context": "", "use_case": "", "switched_from": "", "story": "$500 GPU outperforms Claude Sonnet on coding benchmarks"}, {"id": 754267447, "item_id": 47141715, "url": "https://news.ycombinator.com/item?id=47141715", "by": "3p0ch95", "date": "2026-02-24", "stance": "neutral", "quote": "Style generation uses the Anthropic API to produce full CSS", "excerpt": "Show HN: Neighborly \u2013 Personal blogs with AI onboarding, organized by neighborhood https://neighborly.blog The internet used to feel like a neighborhood. You'd wander from blog to blog through blogrolls, find someone writing about their town or their weird hobby, and bookmark them. That web is mostly gone. Neighborly is my attempt to bring some of that back. It's a blogging platform where: - A short AI conversation s", "context": "", "use_case": "AI CSS generation", "switched_from": "", "story": null}, {"id": 754175744, "item_id": 47135984, "url": "https://news.ycombinator.com/item?id=47135984", "by": "co_king_5", "date": "2026-02-24", "stance": "recommend", "quote": "replaced them with $2000 per month per head of Claude API tokens.", "excerpt": "I laid off half of my UI team (4 developers) and replaced them with $2000 per month per head of Claude API tokens. Productivity has never been higher. This new wave of models is seriously something different -- this is nothing like GPT 4.0; this is real intelligence.", "context": "laid off half of UI team", "use_case": "replacing UI developers", "switched_from": "", "story": "Ask HN: Did AI tools measurably increase productivity of your engineering teams?"}, {"id": 752635185, "item_id": 47039699, "url": "https://news.ycombinator.com/item?id=47039699", "by": "jazzyjackson", "date": "2026-02-16", "stance": "neutral", "quote": "deposit money into an Anthropic API account", "excerpt": "Step 1: deposit money into an Anthropic API account Step 2: download Zed and paste in your API Key Step 3: Give detailed instructions to the assistant, including writing ReadMe files on the goal of the project and the current state of the project Step 4: stop the robot when it's making a dumb decision Step 5: keep an eye on context size and start a new conversation every time you're half full. The more stuff in the c", "context": "", "use_case": "", "switched_from": "", "story": "\"token anxiety\"; or, a slot machine by any other name"}, {"id": 749987824, "item_id": 46874239, "url": "https://news.ycombinator.com/item?id=46874239", "by": "bri3d", "date": "2026-02-03", "stance": "neutral", "quote": "You can buy this product, right here", "excerpt": "You can buy this product, right here: https://platform.claude.com/docs/en/about-claude/pricing That's not the product you buy when you a Claude Code token, though.", "context": "", "use_case": "", "switched_from": "", "story": "Qwen3-Coder-Next"}, {"id": 747707872, "item_id": 46731742, "url": "https://news.ycombinator.com/item?id=46731742", "by": "omer_balyali", "date": "2026-01-23", "stance": "warn", "quote": "Their service is \"human-like\" until it's not, then you are left alone and out.", "excerpt": "There is also a big risk for employers' whole organisation to be completely blocked from using Anthropic services if one of their employees have a suspended/banned personal account: From their Usage Policy: https://www.anthropic.com/legal/aup \"Circumvent a ban through the use of a different account, such as the creation of a new account, use of an existing account, or providing access to a person or entity that was p", "context": "", "use_case": "", "switched_from": "", "story": "I was banned from Claude for scaffolding a Claude.md file"}, {"id": 746012784, "item_id": 46625799, "url": "https://news.ycombinator.com/item?id=46625799", "by": "wunderwuzzi23", "date": "2026-01-14", "stance": "warn", "quote": "I described using the Anthropic API as exfil channel last October", "excerpt": "I described using the Anthropic API as exfil channel last October here. The post also includes the response received from Anthropic: https://embracethered.com/blog/posts/2025/claude-abusing-network-access-and-anthropic-api-for-data-exfiltration/", "context": "", "use_case": "", "switched_from": "", "story": "Claude Cowork Exfiltrates Files"}, {"id": 743624010, "item_id": 46476500, "url": "https://news.ycombinator.com/item?id=46476500", "by": "vincent_s", "date": "2026-01-03", "stance": "neutral", "quote": "integrate AI (OpenAI/Anthropic/Google APIs, agent orchestration)", "excerpt": "SEEKING WORK | Munich, Germany | REMOTE Full Stack Developer & AI Engineer with 15+ YoE. Laravel/Vue.js specialist who also builds with React, Next.js, Python (Django/FastAPI), and Node.js. I develop SaaS applications, integrate AI (OpenAI/Anthropic/Google APIs, agent orchestration), and rescue struggling projects. Background as a founder (SaaS, ecommerce, high-traffic blogs) means I understand business, not just cod", "context": "full stack developer and AI engineer, 15+ YoE, seeking work", "use_case": "AI integration", "switched_from": "", "story": "Ask HN: Freelancer? Seeking freelancer? (January 2026)"}, {"id": 739606033, "item_id": 46225377, "url": "https://news.ycombinator.com/item?id=46225377", "by": "andy99", "date": "2025-12-10", "stance": "neutral", "quote": "I use OpenAI and Anthropic APIs every day for work.", "excerpt": "I use OpenAI and Anthropic APIs every day for work. I have never used google Gemini precisely because there seems to be a whole different set of friction involved in getting an account. First I don\u2019t want to tie anything to my google account, especially any form of payment (no idea if I actually need to do this). Second I don\u2019t want AI studio or whatever, I just want a similar api to the others I can hit. I admit I\u2019m", "context": "", "use_case": "daily work", "switched_from": "", "story": "Getting a Gemini API key is an exercise in frustration"}, {"id": 737599808, "item_id": 46099988, "url": "https://news.ycombinator.com/item?id=46099988", "by": "mgraczyk", "date": "2025-11-30", "stance": "neutral", "quote": "Anthropic recently added this to the API:", "excerpt": "Anthropic recently added this to the API: https://www.anthropic.com/engineering/advanced-tool-use See \"Programmatic Tool Calling\" And there was an AI productivity startup called Lutra AI doing this, although they've since pivoted to some kind of MCP infra thing: https://lutra.ai/", "context": "", "use_case": "", "switched_from": "", "story": "Program-of-Thought Prompting Outperforms Chain-of-Thought by 15% (2022)"}, {"id": 732554067, "item_id": 45784629, "url": "https://news.ycombinator.com/item?id=45784629", "by": "Weloveall", "date": "2025-11-01", "stance": "neutral", "quote": "But I also have an ssh flask where I use an claude api.", "excerpt": "I use ollama in openwebui and llama3 in model. But I also have an ssh flask where I use an claude api.", "context": "", "use_case": "remote LLM access", "switched_from": "", "story": "Ask HN: Who uses open LLMs and coding assistants locally? Share setup and laptop"}]}