#llm

@raspberry_pi_news Turn text input into actions with Needle, a 14MB function-calling LLM #AI #LLM #RaspberryPi

@litellm_blog Day 0 Support: GPT-6 Sol and GPT-6 Luna #AI #LLM #OpenAI

@litellm_blog Day 0 Support: Xiaomi MiMo V2.6 #AI #LLM #OpenSource

@litellm_blog Getting Started with Fireworks AI on LiteLLM #AI #LLM #Tutorial

@litellm_blog Day 0 Support: Claude Opus 5.5 #AI #LLM #OpenAI

@inverted_passion Modern LLMs have tiny GPTs hidden inside them #AI #LLM #Science

@simon_willison Jev introduces a new shape of LLM - System One, aka Decision Models #AI #LLM #DecisionModels

@vincent_schmalbach OpenAI Codex Is Retiring the Last Model that Behaves Like an Assistant #AI #LLM #OpenAI

@litellm_blog Claude Code server-side auto mode through LiteLLM #AI #LLM #OpenAI

@litellm_blog Day 0 Support: Grok 4.7 #AI #LLM #OpenAI

@vllm_blog PD Serving of Qwen3.8-2.4T #AI #LLM #Performance

@simon_willison llm-keys-ui 0.1 #AI #LLM #OpenSource

@litellm_blog TypeSafe Jev on LiteLLM #AI #LLM #OpenSource

@adlrocha_beyond_the_code @adlrocha - LLMs are Rediscovering the Memory Hierarchy #AI #LLM #ComputerScience

@lobsters The Implications of Linguistic Illegibility for LLM Security #AI #Security #LLM

@elevenlabs_blog What is a context window? What every LLM user should know #AI #LLM #Tech

@litellm_blog Reduce agent context with TypeSafe Jev and LiteLLM #AI #LLM #Agents

@litellm_blog Day 0 Support: Qwen3.8-Omni-Flash #AI #LLM #OmniModel

@litellm_blog Auto-Router: Switching Tiers Without Encrypted Content Failures #AI #LLM #OpenSource

@simon_willison How To Write With An LLM #AI #Writing #LLM

@simon_willison Bonsai 2 27B: Near-Lossless Compression in a 9x Smaller Footprint #AI #LLM #Compression

@simon_willison Self-generated prompt injections in compaction summaries #AI #LLM #Security

@lobsters I Don't Like LLMs #AI #LLM #TechDebate

@simon_willison Claude Cowork and chat are now one Claude #AI #LLM #Tech

@kottke Paul Ford: Aided by LLMs, people & companies are... #AI #LLM #FutureOfTech

@bytebytego_newsletter How LLMs Can Find a Needle in a Haystack #AI #LLM #SystemDesign

@zach_holman As Someone Who Has Written This Blog Post, #AI #Writing #LLM

@google_deepmind_news Introducing Gemini 3.8 Live and 3.8 Live Extended Thinking #AI #DeepMind #LLM

@vllm_blog vLLM x Novita AI: Chord, Faster INT4 MoE for Kimi K2.x. Up to 1.3x on H200, 2.15x on Untuned B300 #AI #LLM #Performance

@vllm_blog How we trained the fastest DSpark for Kimi-K3 using GB300 NVL72 #AI #LLM #Performance

@hackernews Show HN: StemJSON - a language for LLMs to extend native mobile apps on the fly #HackerNews #Tech #LLM

@litellm_blog Auto Router: Maximize Quality & Savings with Our Fuse LLM Classifier #AI #LLM #OpenSource

@vllm_blog Kimi K3 Performance Optimizations in vLLM: The Road to 2.8× Throughput #AI #Performance #LLM

@litellm_blog Auto Router: 45% Lower Cost on 25 SWE-bench Tasks #AI #CostOptimization #LLM

@litellm_blog Auto-Router Updates: Harness-Aware Routing #AI #OpenSource #LLM

@hackernews Training a 3.8B LLM to 0.384 CORE for $998 - Hugo Vergnes #HackerNews #Tech #LLM

@vllm_blog Following the Bottleneck: Optimizing MiniMax M3 on AMD Instinct MI355X #AI #LLM #Hardware

@lobsters I Don't Want to Interact With Stochastic Parrots #AI #LLM #Ethics

@hackernews Procedural Graphs: Self-Evolving Execution Structures for LLM Agents #HackerNews #Tech #LLM

@wiz_blog Off Guard: Breaking LiteLLM from authentication bypass to cloud compromise #CloudSecurity #CyberSecurity #LLM