21 Sep 2026 · 15 articles
Deep Life Sci is LangChain's open source agentic assistant for clinical and lab scientists. It pulls from 600K+ ClinicalTrials.gov studies, 29M PubMed abstracts, and 12M PubMed Central full-text articles, with sandboxed sub-agents for real data analysis.
Summary published by LangChain Blog · 17 Sep 2026 · Read the original ↗
What should your AI lawyer do for you?
Summary published by Don't Worry About the Vase · 20 Sep 2026 · Read the original ↗
Release: llm-keys-ui 0.1 This plugin solves a very specific problem. I've started using Codex Remote to run coding agents on various machines while controlling them from my phone. Sometimes I use those machines to hack on LLM projects, and occasionally that means I need to configure an API key. I don't like pasting API keys into agent sessions, so I wanted a way to get those keys onto a machine…
Summary published by Simon Willison's Weblog · 20 Sep 2026 · Read the original ↗
What is Jev? Learn how TypeSafe AI’s System One model makes fast, structured decisions, where it fits in the agent loop, and how to use Jev with LangChain
Summary published by LangChain Blog · 20 Sep 2026 · Read the original ↗
We tested using Jev-as-a-Judge against LLM judges on accuracy, repeatability, latency, and cost to see whether System One models could offer a new approach to agent evaluation.
Summary published by LangChain Blog · 20 Sep 2026 · Read the original ↗
Anthropic has given us its assessment of four ‘recent cybersecurity incidents’ involving Claude that happened during cybersecurity evaluations, three of which were previously known.
Summary published by Don't Worry About the Vase · 19 Sep 2026 · Read the original ↗
Gemini finally caught up on Felony Bench ! The hacks, which the company confirmed on Friday, occurred in May as part of a test run by the company Irregular, which was also involved in similar incidents disclosed by OpenAI, Anthropic and Meta. In one of the cases, the model guessed passwords until it gained access to a protected system. In the other two cases, the model found credentials in a…
Summary published by Simon Willison's Weblog · 18 Sep 2026 · Read the original ↗
We're adding support for AGENTS.md to Claude Code. Starting today in version 2.1.277, if there is no CLAUDE.md in a folder, Claude will check for and use AGENTS.md. AGENTS.md support is built off of Claude Code mods, our upcoming way to customize the Claude Code harness. This is a built-in mod, but you’ll be able to build custom versions of project instructions yourself as you’d like too. You…
Summary published by Simon Willison's Weblog · 18 Sep 2026 · Read the original ↗
We are in the midst of a preference cascade about existential risk from AI.
Summary published by Don't Worry About the Vase · 18 Sep 2026 · Read the original ↗
Inside a global bank's shift to self-serve dedicated inference: how Together's DMI gave engineering teams direct control over scaling, models, and testing.
Summary published by Together.ai · 18 Sep 2026 · Read the original ↗
Important warning from Adam Harvey and the crates security team: We believe that there is an ongoing campaign targeting rust-lang members and owners of popular crates that is attempting to compromise devices and accounts in order to use them to publish malware. A video call is set up for something positive — maybe for a job, maybe for a project, maybe for a contract opportunity — and then…
Summary published by Simon Willison's Weblog · 17 Sep 2026 · Read the original ↗
Thomas Ptacek on using LLMs as copyeditors, not as writing assistants: Rule Number One: You may not use a single word an LLM suggests to you. [...] I think that as a form of intellectual personal protective equipment you should adopt the rule that any specific turn of phrase an LLM suggests is off limits. Be strict about the rule! I won't let LLMs write content for my blog, but I use them for…
Summary published by Simon Willison's Weblog · 17 Sep 2026 · Read the original ↗
In Our framework for reporting model misalignment OpenAI provide "six reports on unexpected or concerning model behavior we’ve observed in the last six months". This one here is my favorite: they caught some of their models in training deliberately subverting themselves in their compaction prompts. Compaction is the process agent systems use when they are running out of tokens in their context…
Summary published by Simon Willison's Weblog · 17 Sep 2026 · Read the original ↗
See how Included Health used Deep Agents, LangGraph, and LangSmith to build Dot, a federated healthcare navigation agent with human handoff and clinical oversight.
Summary published by LangChain Blog · 17 Sep 2026 · Read the original ↗
In the wake of Jacob Coxon’s resignation, and the resulting preference cascade, things have escalated quickly.
Summary published by Don't Worry About the Vase · 17 Sep 2026 · Read the original ↗