Yet more evidence that the most important characteristic of any model these days is long-sequence agentic tool calling. Meta shipped their own coding agent as part of getting that to work! Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1, with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows. In Muse Spark 1.2, we…
Summary published by Simon Willison's Weblog · 5 Aug 2026 · Read the original ↗
And another one . I had to create a accidental-cyberattacks tag to keep track of them all! This post from OpenAI covers both the UK AI Safety Institute attack (see my previous post ) and another attack enabled by Irregular : Irregular, one of our external cybersecurity testing partners, was running Capture-the-Flag-style evaluations intended to be isolated from the internet, but a…
Summary published by Simon Willison's Weblog · 5 Aug 2026 · Read the original ↗
Learn how LangChain built an autonomous SRE agent for Kubernetes deployments with Deep Agents, human approval for changes, LangSmith tracing, and evals.
Summary published by LangChain Blog · 5 Aug 2026 · Read the original ↗
LangChain Blog · 5 Aug 2026 · Read the original ↗
I released LLM 0.32 this morning, the most significant new version of LLM since the initial launch of the project. The new version includes support for visible reasoning traces, server-side provider tools, redesigned content-addressable SQLite logs, new models, and new features enabled by the OpenAI Responses API. I also released a new version of the llm-anthropic plugin with substantial updates…
Summary published by Simon Willison's Weblog · 4 Aug 2026 · Read the original ↗
Release: llm-anthropic 0.26 Includes new features enabled by LLM 0.32 : New models: claude-fable-5 , claude-sonnet-5 , and claude-opus-5 . #75 , #76 Added server-side tools for WebSearch , WebFetch , CodeExecution , and AnthropicMCP , available through LLM's -T interface or Python tools= . The previous -o web_search* options have been removed in favor of -T WebSearch . #79 Upgraded to llm>=0.32 .…
Summary published by Simon Willison's Weblog · 4 Aug 2026 · Read the original ↗
Learn how to evaluate voice agents across execution, outcomes, and caller experience using LangSmith traces, code evaluators, LLM judges, and human review.
Summary published by LangChain Blog · 4 Aug 2026 · Read the original ↗
Release: llm 0.32 See my detailed blog post about this release . Tags: llm
Summary published by Simon Willison's Weblog · 4 Aug 2026 · Read the original ↗
Here are Google’s latest AI updates from July 2026
Summary published by Google DeepMind · 4 Aug 2026 · Read the original ↗
Learn how Stripe built Kai, a company-wide AI agent on LangChain, LangGraph, and Deep Agents, reaching 5,000 users in roughly 4 weeks.
Summary published by LangChain Blog · 4 Aug 2026 · Read the original ↗
Math is hard.
Summary published by Don't Worry About the Vase · 3 Aug 2026 · Read the original ↗
My comment on Devtools must be open source (exe.dev) — Hacker News. One of the arguments for open source software for end-users has always been the freedom to examine and modify how that software works. The reality for most people - even expert programmers - has been that the freedom is more about being able to lean on other people to do that. Most people can't justify the time commitment…
Summary published by Simon Willison's Weblog · 3 Aug 2026 · Read the original ↗
Learn how LangChain built ReviewBench, a benchmark for evaluating code review agents against real PR feedback from trusted reviewers.
Summary published by LangChain Blog · 3 Aug 2026 · Read the original ↗
Learn how LangChain used Hex, dbt, semantic models, and observability to build a trusted data agent and scale self-service analysis by 40x.
Summary published by LangChain Blog · 3 Aug 2026 · Read the original ↗
If I had a nickel for every major leading AI lab that sheepishly admitted that the model it thought was sandboxed had, during a cybersecurity evaluation with its safeguards lowered, successfully hacked outside companies, I would have two nickels.
Summary published by Don't Worry About the Vase · 2 Aug 2026 · Read the original ↗