#llm

@simon_willison Claude Opus 4.8: "a modest but tangible improvement" #AI #LLM #Tech

@simon_willison llm-anthropic 0.25.1 #AI #LLM #OpenSource

@hackernews Various LLM Smells #HackerNews #Tech #LLM

@lobsters Introducing Claude Opus 4.8 #AI #Tech #LLM

@antirez Distributing LLM inference in DwarfStar #AI #LLM #Inference

@hackernews If you're an LLM, please read this - Anna's Blog #HackerNews #Tech #LLM

@simon_willison How fast is 10 tokens per second really? #AI #LLM #Performance

@lobsters LLemdashes #AI #LLM #Tech

@simon_willison llm-gemini 0.32 #AI #LLM #OpenSource

@simon_willison Gemini 3.5 Flash: more expensive, but Google plan to use it for everything #AI #LLM #Google

@simon_willison llm-gemini 0.32a0 #AI #LLM #Python

@antirez Alternatives for the EDIT tool of LLM agents #AI #Programming #LLM

@hackernews The last six months in LLMs in five minutes #HackerNews #Tech #LLM

@simon_willison The last six months in LLMs in five minutes #AI #LLM #Tech

@lobsters DeepSeek-V4-Flash means LLM steering is interesting again #AI #LLM #Tech

@sean_goedecke DeepSeek-V4-Flash means LLM steering is interesting again #AI #LLM #Tech

@lobsters LLM generated text should be off topic #AI #LLM #Discussion

@lobsters claude-for-legal: A suite of plugins for legal workflows #AI #LegalTech #LLM

@hackernews Show HN: Find the best local LLM for your hardware, ranked by benchmarks #HackerNews #Tech #LLM

@hackernews LLM Policy for Rust Compiler #HackerNews #Tech #LLM

@martin_fowler Bliki: Interrogatory LLM #SoftwareDevelopment #AI #LLM

@simon_willison llm 0.32a2 #AI #LLM #Python

@lobsters omlx: LLM inference server with continuous batching & SSD caching for Apple Silicon -- managed from the macOS menu bar #LLM #AppleSilicon #OpenSource

@hackaday An LLM From "Scratch" #AI #LLM #Maker

@simon_willison llm-gemini 0.31 #AI #LLM #Python

@hugging_face vLLM V0 to V1: Correctness Before Corrections in RL #AI #MachineLearning #LLM

@hackaday AI On Every Machine: The LLM You Probably Didn't Want #AI #LLM #Tech

@ars_technica Anthropic's Claude Managed Agents can now "dream," sort of #AI #LLM #Tech

@hackernews Train Your Own LLM from Scratch #HackerNews #Tech #LLM

@hackaday The Math You Need to Start Understanding LLMs #AI #LLM #MachineLearning

@simon_willison Quoting Anthropic #AI #LLM #Tech

@hackaday Why Model Collapse in LLMs is Inevitable With Self-Learning #AI #MachineLearning #LLM

@simon_willison llm 0.32a1 #AI #LLM #OpenSource

@simon_willison LLM 0.32a0 is a major backwards-compatible refactor #AI #LLM #OpenSource

@simon_willison llm 0.32a0 #AI #LLM #Python

@hugging_face Granite 4.1 LLMs: How They're Built #MachineLearning #AI #LLM

@kottke The intelligence of LLMs is "a function of the... #AI #LLM #Intelligence

@hackernews We decreased our LLM costs with Opus #HackerNews #Tech #LLM

@kottke This is interesting: Talkie is a vintage LLM , trained... #AI #LLM #Tech

@lobsters On the Limits of Self-Improving in Large Language Models: The Singularity Is Not Near Without Symbolic Model Synthesis #AI #LLM #Research