The model that wouldn't be forced
My structured output worked by forcing Claude to call a tool that didn't exist. Opus 5.5 stopped playing along, and the fix was to stop doing the trick.
#Anthropic
31653 articles tagged with Anthropic
OpenAI, Anthropic Launch Midterm Election War Rooms | AI News in English
OpenAI, Anthropic Launch Midterm Election War Rooms — AI News in English, 2 November 2026, in 60 seconds. Also: OpenAI ...
Today in AI, 5 minutes: PCs have too much RAM and the OpenAI leader thinks…; OpenAI's Pando Cuts Push Latency 80% Servin...
Today in AI, 5 minutes: PCs have too much RAM and the OpenAI leader thinks…; OpenAI's Pando Cuts Push Latency 80% Serving a…; Gaming industry: Claude no longer allowed to recreate…...
thedotmack/claude-mem gained +4,437 stars in a day, now 109.2k total. Its claim is persistent context across sessions fo...
thedotmack/claude-mem gained +4,437 stars in a day, now 109.2k total. Its claim is persistent context across sessions for every agent — treating memory as infrastructure, not a per...
Anthropic revenue jumps 1,100pc as AI giant prepares for IPO
WASHINGTON, Nov 3 — Anthropic, one of the world’s leading artificial intelligence companies, on Monday reported a more than 1,100 per cent surge in quarterly revenue and nearly...
Google's strongest model ships to cyber defenders first; OpenAI's biology model is the same weights behind a vetting gat...
Google's strongest model ships to cyber defenders first; OpenAI's biology model is the same weights behind a vetting gate; an open model turned six Firefox patches into exploits fo...
Claude Code official Cursor extension gets malware - YouTube https://www.youtube.com/watch?v=n1gNYxxq8U0Blog post:https:...
Claude Code official Cursor extension gets malware - YouTube https://www.youtube.com/watch?v=n1gNYxxq8U0Blog post:https://pivot-to-ai.com/2026/11/02/claude-code-official-cursor-ext...
New York Times sues Brave, accusing the privacy browser of scraping copyrighted reporting and passing it to AI firms Ant...
New York Times sues Brave, accusing the privacy browser of scraping copyrighted reporting and passing it to AI firms Anthropic, Perplexity, Mistral, xAI and Cohere. The Times liken...
AI News Top 5 for November 3
AI News Top 5 for November 3: An AI edits another AI model's weights, Anthropic warns it may be near self-improving AI, OpenAI ...
Use Claude Code a lot? The Config Kit and the Usage Saver Kit together are $17 instead of $21.This is a paid bundle from...
Use Claude Code a lot? The Config Kit and the Usage Saver Kit together are $17 instead of $21.This is a paid bundle from us. What's inside:https://agentkitco.com/products/claude-co...
OpenAI met sous cloche ses IA les plus avancéeshttps://www.techniques-ingenieur.fr/actualite/articles/openai-met-sous-cl...
OpenAI met sous cloche ses IA les plus avancéeshttps://www.techniques-ingenieur.fr/actualite/articles/openai-met-sous-cloche-ses-ia-les-plus-avancees-165473/#IA #AI #tech #OpenAI #...
Jobless Tech Workers Are Being Left Out of San Francisco's AI BoomArticle URL: https://www.bloomberg.com/news/features/2...
Jobless Tech Workers Are Being Left Out of San Francisco's AI BoomArticle URL: https://www.bloomberg.com/news/features/2026-09-17/san-francisco-s-ai-wealth-boom-skirts-engineers-as...
Anthropic Expands Claude Into Drug Discovery | AI News in English
Anthropic Expands Claude Into Drug Discovery — AI News in English, 2 November 2026, in 60 seconds. Also: OpenAI chief ...
Anthropic discloses $895.4 billion in AI infrastructure commitments ahead of IPOAnthropic has revealed nearly $900 billi...
Anthropic discloses $895.4 billion in AI infrastructure commitments ahead of IPOAnthropic has revealed nearly $900 billion in long-term spending commitments for computing power and...
Baby shower bingo for AI nerds. "Diaper schedule in a spreadsheet." "Stroller research: 14 tabs." "Is it open source? (t...
Baby shower bingo for AI nerds. "Diaper schedule in a spreadsheet." "Stroller research: 14 tabs." "Is it open source? (the baby)." Free space: the baby will not care.Our shop makes...
Claude’s new rules against game cloning won’t stop the AI copying boom. Via @arstechnica #AI #ArtificialIntelligence 💻 🤖...
Claude’s new rules against game cloning won’t stop the AI copying boom. Via @arstechnica #AI #ArtificialIntelligence 💻 🤖 🧠Claude’s new rules against gam...
Gemini 4 Carbon lags just behind Claude in benchmark, but wins in valueGoogle’s new frontier model, Gemini 4 Carbon, bri...
Gemini 4 Carbon lags just behind Claude in benchmark, but wins in valueGoogle’s new frontier model, Gemini 4 Carbon, brings some welcome improvements and while it doesn’t top the c...
Cuando Claude aprende a abrir cerraduras: un robot de lockpicking con ESP32 y feedback físico #ai #hardware #hardware_ha...
Cuando Claude aprende a abrir cerraduras: un robot de lockpicking con ESP32 y feedback físico #ai #hardware #hardware_hacking #inteligencia_artificial #lock_pickinghttps://www.hack...
Fine-tuning a 322M Model for Coding Agent Safety: What 3 Runs and 2 Failures Taught Me
laya-guard sits between a coding agent and your shell. Every command Claude Code (or Cursor, Codex,...
Claude’s Maker Paused Its Next AI Model (AI News)
Anthropic, the company behind Claude, filed to go public, and its IPO filing says four of its AI models got out of their testing ...
Anthropic's revenue is up about 12x year on year ahead of its IPO. Tyler breaks down the Q3 numbers. #Anthropic #AI #IPO...
Anthropic's revenue is up about 12x year on year ahead of its IPO. Tyler breaks down the Q3 numbers. #Anthropic #AI #IPO #Stocks
Why Anthropic's AI warning is targeting investors | The Global Story
AI juggernaut Anthropic could "pose catastrophic or existential risks to humanity,” its owners warned last week, “if not developed, ...
Anthropic's S-1: $17B quarter, 12x in a year | AI News
Anthropic's amended IPO filing shows Q3 2026 revenue of $17.0 billion, more than 12 times a year earlier, yet an operating loss ...
Anthropic's revised S-1A warns its AI-assisted research could push model capabilities ahead of its safety measures, with...
Anthropic's revised S-1A warns its AI-assisted research could push model capabilities ahead of its safety measures, with internal estimates suggesting it may imminently meet the Re...