#llm

@hackernews Jamesob's guide to running SOTA LLMs locally #HackerNews #Tech #LLM

@hackaday Chain-of-Thought Spoofing Targets Reasoning AI Models #AI #Cybersecurity #LLM

@danluu Agentic test processes, LLM benchmarks, and other notes on agentic coding from Galapagos Island #AI #Coding #LLM

@simon_willison llm-coding-agent 0.1a0 #AI #LLM #OpenSource

@hackernews No LLM Code in Dependencies #HackerNews #Tech #LLM

@hackernews Comparing Fable and 10 other LLMs on refactoring a LangGraph god node #HackerNews #Tech #LLM

@lobsters Redeploying Claude Fable 5 #AI #LLM #Tech

@simon_willison Quoting Anthropic #AI #LLM #Tech

@engadget Anthropic's new Sonnet 5 model is better at the tasks that are running up enterprise bills #AI #Tech #LLM

@simon_willison What's new in Claude Sonnet 5 #AI #LLM #Anthropic

@simon_willison Ornith-1.0: Self-Scaffolding LLMs for Agentic Coding #AI #LLM #Coding

@lobsters We have Mythos at Home: GLM 5.2 beats Claude in our Cyber Benchmarks #AI #LLM #Tech

@hackernews Wayfinder Router: deterministic routing of queries between local and hosted LLM #HackerNews #Tech #LLM

@hackernews Ask HN: MacBook vs. Dedicated GPU for LLM #HackerNews #Tech #LLM

@lobsters NLNet Labs LLM Policy #OpenSource #AI #LLM

@simon_willison What happened after 2,000 people tried to hack my AI assistant #AI #Security #LLM

@simon_willison Prompt Injection as Role Confusion #AI #Security #LLM

@kottke Are You in the Weights? "LLMs encode their... #AI #LLM #Tech

@hackaday How LLMs can be Assisted to do Arithmetic Correctly #AI #LLM #Hacking

@hackernews Show HN: 10x better performance from the Coding Harnesses with LLM-wiki #HackerNews #Tech #LLM

@simon_willison GLM-5.2 is probably the most powerful text-only open weights LLM #AI #LLM #OpenSource

@hugging_face GLM-5.2: Built for Long-Horizon Tasks #AI #MachineLearning #LLM

@hackernews Show HN: BlitzGraph - Supabase for graphs, built for LLM agents #HackerNews #Tech #LLM

@lobsters Building llm-driven "ai" still requires domain knowledge #AI #LLM #Tech

@lobsters The Curse of Depth in Large Language Models #AI #LLM #Tech

@gizmodo How Much Does It (Really) Cost to Use Claude Fable, GPT-5.5, and Gemini 3.5 Flash? #AI #Tech #LLM

@xe_iaso Why are cached input tokens cheaper with AI services? #AI #LLM #Tech

@simon_willison Claude Fable is relentlessly proactive #AI #LLM #Claude

@simon_willison If Claude Fable stops helping you, you'll never know #AI #LLM #Tech

@simon_willison Initial impressions of Claude Fable 5 #AI #LLM #Tech

@simon_willison llm 0.32a3 #AI #LLM #OpenSource

@simon_willison Setting a custom price for a model in AgentsView #AI #LLM #OpenSource

@lobsters Claude Fable 5 and Claude Mythos 5 #AI #LLM #Tech

@hackernews What Are Tokens in LLMs? #HackerNews #Tech #LLM

@lobsters Thoughts on starting new projects with LLM agents #AI #LLM #Coding

@lobsters How LLMs Actually Work #AI #LLM #Tech

@eli_bendersky Thoughts on starting new projects with LLM agents #AI #LLM #SoftwareDevelopment

@hackernews Show HN: Lowfat - pluggable CLI filter that saved 91.8% of my LLM tokens #HackerNews #Tech #LLM

@hackernews Fine-tuning an LLM to write docs like it's 1995 #HackerNews #Tech #LLM

@simon_willison How we contain Claude across products #AI #LLM #Tech