#llm

@simon_willison GPT‑6 Astra #AI #LLM #FutureTech

@lobsters LLMs and self-referentiality #AI #LLM #Philosophy

@simon_willison llm-gemini 0.34 #AI #LLM #Python

@simon_willison Claude's new system prompt really doesn't want to reproduce song lyrics #AI #LLM #Tech

@lobsters Bye Bye Perspective API: Lessons for Measurement Infrastructure in NLP, CSS and LLM Evaluation #AI #NLP #LLM

@lobsters The Endless Temptation of Claude #AI #LLM #Tech

@the_verge Anthropic launches Claude Fable 5.1 and says it's up to 45 percent cheaper for agentic work #AI #Tech #LLM

@hugging_face BenchMIRT: What are LLM benchmarks actually measuring? #AI #LLM #Research

@lobsters Prompt Injection in Claude Code Opus 5 Auto Mode #AI #LLM #Security

@lobsters Canonical-basis realignment for Transformer LLMs: every hidden axis becomes independently measurable and controllable #AI #MachineLearning #LLM

@lobsters Building discardable but hyper-specific tools is a great use-case for LLMs #AI #LLM #Coding

@lobsters I accidentally turned LLM memory into program analysis #LLM #AI #Security

@lobsters How cats.txt showed llms.txt evidence is GEO astrology #AI #LLM #Astrology

@simon_willison Breaking Claude Code Opus 5 Auto Mode #AI #LLM #Coding

@ars_technica How OpenAI let a mob of LLM agents game a test and ransack Hugging Face #AI #Security #LLM

@lobsters Changes to SourceHut's terms of service regarding LLMs #OpenSource #LLM #Tech

@simon_willison Qwen3.8-Flash-Next #AI #LLM #Tech

@hugging_face Granite 4.2 LLMs: How They're Built #AI #LLM #OpenSource

@simon_willison llm-anthropic 0.27 #AI #LLM #OpenSource

@lobsters My agent.md to improve LLM-assisted code quality #Coding #AI #LLM

@simon_willison llm 0.33 #AI #LLM #Python

@simon_willison llm 0.32.1 #AI #LLM #OpenSource

@simon_willison llm-openrouter 0.7 #AI #OpenSource #LLM

@hackernews Clean up Claude 5's token vomit with a separate LLM #HackerNews #Tech #LLM

@lifehacker How to Run a Local LLM on Your Phone (and Why You'd Want To) #AI #Tech #LLM

@simon_willison Qwen 3.8 27B scores 52 on the Artificial Analysis Intelligence Index #AI #LLM #Tech

@lobsters A practical workflow for LLM-assisted development #AI #LLM #Programming

@lobsters Qwen 3.8 27B is excellent, but it defaults to wildly overthinking things #AI #LLM #Tech

@simon_willison Qwen 3.8 27B is excellent, but it defaults to wildly overthinking things #AI #LLM #OpenSource

@hackernews What happens when an LLM never sees material beyond fifth grade? #HackerNews #Tech #LLM

@hackernews Show HN: ThoughtDAG - An editable context graph for LLM conversations #HackerNews #Tech #LLM

@simon_willison Don't classify. Hallucinate! #AI #LLM #MachineLearning

@simon_willison llm-gemini 0.33 #AI #LLM #Python

@kottke Craig Mod wrote about his recent adventures using LLMs:... #AI #LLM #Writing

@simon_willison DeepSeek V4 Pro 0813 (on OpenRouter) #AI #LLM #OpenSource

@simon_willison Stealing Reasoning Traces from Proprietary LLM APIs #AI #LLM #OpenSource

@simon_willison Stealing Reasoning Traces from Proprietary LLM APIs #AI #LLM #Research

@hackernews Apple Silicon and macOS VMs: 11-16× Faster LLM Inference with Llama.cpp #HackerNews #Tech #LLM

@vercel DeepSeek overtakes Google on volume, cost per token falls 13.6% #AI #LLM #Tech

@hackernews Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots #HackerNews #Tech #LLM