8 Oct 2026 · 15 articles
If you are familiar with my previous posts on model welfare for new Claude models, you can skip the Introduction and The Story So Far.
Summary published by Don't Worry About the Vase · 5 Oct 2026 · Read the original ↗
Deep Agents now lets you bind tools to skills, pin skills at runtime, and reload skills mid-thread, so agents with expansive skill repositories stay context-efficient and effective.
Summary published by LangChain Blog · 7 Oct 2026 · Read the original ↗
LangChain just released new capabilities in Managed Deep Agents. Agents can now schedule follow-ups, reconfigure themselves on every run, and react to Slack messages.
Summary published by LangChain Blog · 7 Oct 2026 · Read the original ↗
Release: llm-openai-decisions 0.1a0 OpenAI released their new Jev-style Decisions API , as previously announced at last week's DevDay. Since I already have an llm-typesafe plugin for talking to Jev, I had GPT-6 Astra read the new OpenAI API documentation and build an llm-openai-decisions plugin inspired by llm-typesafe . Unlike Jev, the new gpt-6-luna decision model supports image input in…
Summary published by Simon Willison's Weblog · 6 Oct 2026 · Read the original ↗
https://github.com/openai/math https://github.com/openai/math/tree/main/preprints Comments URL: https://news.ycombinator.com/item?id=49984923 Points: 1265 # Comments: 1432
Summary published by Hacker News - Newest: "AI" · 6 Oct 2026 · Read the original ↗
Release: llm-mistral 0.16 Adds support for reasoning models, such as the newly released Mistral Large 4 . Tags: llm , mistral , llm-reasoning
Summary published by Simon Willison's Weblog · 6 Oct 2026 · Read the original ↗
Mistral are back in the game. Today they're releasing a preview of Mistral Large 4, a 1 trillion parameter, 49 billion active parameter model trained on their own cluster of 3,800 NVIDIA Grace Blackwell GPUs. The preview is available via their API. They promise to release the open weights model at the "end of this month". The model only supports two reasoning levels - "none" and "high" - via the…
Summary published by Simon Willison's Weblog · 6 Oct 2026 · Read the original ↗
My comment on Mistral Large 4 — Hacker News. wren6991 : The benchmark is saturated. Frontier models are tested with an armadillo in fishnet tights jaywalking on Mars. OK well I couldn't resist this one: llm -m claude-opus-5.5 'Generate an SVG of an armadillo in fishnet tights jaywalking on Mars' llm -m gpt-6.1-sol 'Generate an SVG of an armadillo in fishnet tights jaywalking on Mars' llm -m…
Summary published by Simon Willison's Weblog · 6 Oct 2026 · Read the original ↗
Article URL: https://github.com/FeSens/openTPU Comments URL: https://news.ycombinator.com/item?id=49980715 Points: 338 # Comments: 394
Summary published by Hacker News - Newest: "AI" · 6 Oct 2026 · Read the original ↗
Introducing EmbeddingGemma 2, an open multimodal embedding model optimized for privacy-first use cases
Summary published by Google DeepMind · 6 Oct 2026 · Read the original ↗
Enterprises can now run open models at production scale on a dedicated B300 inference cluster, built by Together AI, IBM Cloud, and NVIDIA
Summary published by Together.ai · 6 Oct 2026 · Read the original ↗
Together Link brings frontier open models like GLM 5.3 and Kimi K3 into the coding agent your team already uses, cutting model spend by over 50%.
Summary published by Together.ai · 5 Oct 2026 · Read the original ↗
Article URL: https://github.com/allenv0/SCM Comments URL: https://news.ycombinator.com/item?id=49952111 Points: 178 # Comments: 74
Summary published by Hacker News - Newest: "AI" · 4 Oct 2026 · Read the original ↗
LangChain introduces LangSmith Fine-Tuning and SmithTune, a CLI built for post-training models. Train specialized models without building data pipelines by hand.
Summary published by LangChain Blog · 24 Sep 2026 · Read the original ↗
Managed Deep Agents is the simplest way to build, deploy, and run agents in production. The 0.8 release adds support for user-owned credentials, user-level memory, HTTP channels, file transfer in Slack and a pre-built tool for web search.
Summary published by LangChain Blog · 24 Sep 2026 · Read the original ↗