#llm

@johanna_larsson No cost, no value #AI #LLM #OpenSource

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

@shrivus_substack Exploring Claude/GPT Knowledge Cutoffs & Pre-training Timelines #AI #LLM #Tech

@lobsters LLMs and xfwl4 #AI #LLM #Tech

@codemancers_blog What is `llms.txt`, Why It Matters, and How to Use It #AI #LLM #Tech

@vllm_blog Announcing Day-0 Support for NVIDIA Nemotron 3.5 Lightning on vLLM #AI #LLM #OpenSource

@simon_willison Quoting Claude Opus 5 system prompt #AI #LLM #Claude

@simon_willison Quoting Claude Opus 5 system prompt #AI #LLM #PromptEngineering

@hackernews Show HN: Lumabri - What if LLMs worked like Napster? #HackerNews #Tech #LLM

@lobsters Revision Prompting improves industrial LLM processes #AI #LLM #Tech

@engadget Claude Vs ChatGPT: How These AI Assistants Differ #AI #Tech #LLM

@adaline_labs How The Product Role Is Moving To Building And Verification #AI #ProductManagement #LLM

@levelsio_pieter_levels This prompt finally stopped Claude from getting more and more unintelligible every day #AI #PromptEngineering #LLM

@vllm_blog Efficient Decode Context Parallelism with vLLM for Long Context Workloads #AI #LLM #Performance

@vllm_blog vLLM Reaches 25K Total TPS/GPU on Qwen3.5 #AI #LLM #Performance

@simon_willison One-shotting a Raccoon Heist game using Claude Fable 5 #AI #Gaming #LLM

@simon_willison New release of LLM adds support for reasoning traces, OpenAI Responses, server-side tools, and smarter logging #AI #LLM #OpenSource

@simon_willison llm-anthropic 0.26 #AI #LLM #OpenSource

@simon_willison llm 0.32 #AI #LLM #OpenSource

@johanna_larsson Limited output is a feature #AI #LLM #Startup

@simon_willison deepseek-ai/DeepSeek-V4-Flash-0731 #AI #LLM #DeepLearning

@adaline_labs Eval-First Product Design For Frontier AI Products #AI #ProductDesign #LLM

@simon_willison smevals - a small eval suite for evaluating models, prompts, and harnesses #AI #OpenSource #LLM

@hackernews Predictive Speculative KV Replication for Bursty LLM Inference #HackerNews #Tech #LLM

@dropsafe microgpt #AI #LLM #Python

@lobsters vLLM for Baidu Kunlun #AI #LLM #Hardware

@simon_willison Advancing the price-performance frontier with GPT‑5.6 #AI #LLM #Tech

@simon_willison llm 0.32rc2 #AI #LLM #OpenSource

@netflix_tech GenRec: Towards LLM-Native Recommendation at Netflix #AI #LLM #Tech

@simon_willison llm 0.32rc1 #AI #LLM #OpenSource

@simon_willison Adding a custom MCP server to Claude and ChatGPT #AI #LLM #Tech

@austins_nerdy_things I sent Claude Opus 5 "- - -" and it wrote me 5k tokens about a cartographer #AI #LLM #Tech

@the_american_genius There is an I in AI: Using the power of LLMs #AI #LLM #Business

@redis_blog Token-budget-aware LLM reasoning: cut costs in 2026 #AI #LLM #Database

@vllm_blog Parallel All the Way Down: Beyond Single-Token Generation with Speculative Decoding #AI #MachineLearning #LLM

@simon_willison moonshotai/Kimi-K3 #AI #LLM #OpenSource

@vllm_blog Kimi K3 Is Here: Efficient Day-0 Support on vLLM #AI #LLM #Tech

@hackernews General Resolution: LLM Usage in Debian #HackerNews #Tech #LLM

@lobsters General Resolution: LLM usage in Debian #LLM #Debian #OpenSource

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