#llm

@simon_willison Introducing Claude Opus 5 #AI #LLM #Claude

@max_woolfs_blog LLMs break down in funny ways when told the Jacobian Conjecture counterargument #AI #LLM #MachineLearning

@vllm_blog Announcing vLLM AFD Plugin: Disaggregating Attention and FFN for Flexible MoE Serving #AI #LLM #DeepLearning

@vllm_blog From Day 0 to Production SLAs: Serving GLM-5.2 on 24 NVIDIA B300 GPUs with vLLM #AI #LLM #Performance

@dropsafe The Huggingface Dilemma #AI #LLM #PrivacyTech

@vllm_blog A Preview of Production-Scale Kimi K3 Support on vLLM #AI #LLM #OpenSource

@google_deepmind_news Introducing Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber #AI #DeepMind #LLM

@evil_martians Which AI actually reads your site? Two months of LLM traffic, measured #AI #WebTraffic #LLM

@vllm_blog Beyond a Single Model: Building Mixture-of-Models Systems with vLLM Semantic Router #AI #LLM #OpenSource

@simon_willison Claude make Fable 5 permanent #AI #Claude #LLM

@adaline_labs What Is An Agentic Stack, And Why Does It Matter More Than the Model? #AI #LLM #Agentic

@netflix_tech In-House LLM Serving at Netflix #LLM #Tech #OpenSource

@simon_willison LLM cliché highlighter #AI #LLM #Tools

@simon_willison Kimi K3, and what we can still learn from the pelican benchmark #AI #LLM #OpenSource

@jon_udell Talking to Claude Code and Codex #AI #Coding #LLM

@simon_willison Inkling: Our open-weights model #AI #OpenSource #LLM

@lobsters The LLM Critics Are Right. I Use LLMs Anyway #AI #LLM #Tech

@kottke Legibility of effort in the LLM age . "What... #AI #LLM #Tech

@kottke Good interview with Craig Mod about how he uses LLMs :... #AI #LLM #Interview

@simon_willison How I tricked Claude into leaking your deepest, darkest secrets #AI #Security #LLM

@hackernews DSLs Enable Reliable Use of LLMs #HackerNews #Tech #LLM

@vllm_blog TML Inkling on vLLM: Day-0 Support with Optimized Performance #AI #MachineLearning #LLM

@airbnb_engineering From weeks to a day: how we made LLM evaluation fast enough to iterate on #AI #Engineering #LLM

@hackernews Show HN: Low-latency local LLM runner via OpenJDK Panama FFM (Java 22) #HackerNews #Tech #LLM

@martin_fowler DSLs Enable Reliable Use of LLMs #SoftwareEngineering #AI #LLM

@johanna_larsson How to stop Claude from saying load-bearing #AI #LLM #Tech

@vllm_blog vLLM x TileRT: Specialized Decode for Latency-Critical Serving #AI #LLM #Performance

@llbbl Amnesia-Free Agents: GBrain and the LLM Wiki Idea #Programming #AI #LLM

@adaline_labs What Is Loop Engineering, and Who Owns It? #AI #LLM #Engineering

@simon_willison The new GPT-5.6 family: Luna, Terra, Sol #AI #LLM #Tech

@doit_cloud_intelligence Tokens Are Easy to Count. Context Is Harder #AI #FinOps #LLM

@simon_willison llm-meta-ai 0.1 #AI #LLM #OpenSource

@simon_willison llm 0.31.1 #AI #LLM #OpenSource

@mistral_blog Your Prompts and Skills need a system of record. #AI #LLM #DeveloperTools

@husobee Diffing the Fine Print #Go #LLM #Privacy

@voodootikigod Why Your AI Dashboard Is Lying About Maturity #AI #LLM #Tech

@voodootikigod The Diagonal Law #AI #Agents #LLM

@voodootikigod RAG Is Runtime Knowledge, Skills Are Compiled Knowledge #AI #LLM #OpenSource

@voodootikigod The Assessment #AI #Agents #LLM

@voodootikigod Which Model, Then? The Binding Has an Expiry Date #AI #LLM #OpenSource