12 Oct 2026 · 15 articles
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 ↗
Bit of a niche link, but I've been waiting for this for a couple of days - I even told ChatGPT to check for it: Clone https://github.com/actions/python-versions and git pull once an hour until they add the stable 3.15 - then tell me about it Now that this has landed, you can add "3.15" to a GitHub Actions testing matrix to run tests against the new Python 3.15.0 release . Tags: github , python…
Summary published by Simon Willison's Weblog · 10 Oct 2026 · Read the original ↗
Anthropic detailed the activity of its A.I. agents in a blog post on Friday, without naming the targeted websites. But two sources with knowledge of the incidents said Anthropic’s A.I. agents had submitted 20 visa applications through a form available on the State Department’s website. All the applications were incomplete and were not processed, they said. — The New York Times , Anthropic…
Summary published by Simon Willison's Weblog · 10 Oct 2026 · Read the original ↗
The Deno team released the first version of celld back in August - their open source implementation of the Durable Objects pattern from Cloudflare Workers. Today, Cloudflare are acquiring Deno outright, with the goal of building on celld to "make workerd self-hosting a first-class supported way to build and run apps using the Workers programming model" (see the Cloudflare blog .) The bad news is…
Summary published by Simon Willison's Weblog · 9 Oct 2026 · Read the original ↗
Managed Deep Agents includes a new API for managing reactions for your distributed agents, and a system to dynamically assign emoji responses with your instrument of choice. Learn more.
Summary published by LangChain Blog · 9 Oct 2026 · Read the original ↗
It is kind of a huge deal.
Summary published by Don't Worry About the Vase · 9 Oct 2026 · Read the original ↗
I shipped a new feature for my blog today: the Newsletters page, which offers an index of all of the newsletters I've sent out, both my free weekly Substack and my monthly sponsors-only updates. I built the feature almost entirely using my voice, chatting away to my laptop while I cooked dinner. Codex voice mode I used the ChatGPT desktop app for this, in the Codex tab, using the voice…
Summary published by Simon Willison's Weblog · 9 Oct 2026 · Read the original ↗
Discover how Snyk transformed an internal support agent into Snyk Assist, a customer-facing AI feature powered by LangChain, LangGraph, and LangSmith.
Summary published by LangChain Blog · 9 Oct 2026 · Read the original ↗
Release: ttok 1.0 I released ttok 0.4 , ran uv tool upgrade ttok , piped a file into the new version... and realized that it was defaulting to the GPT-4 tokenizer when it should very clearly default to GPT-5/GPT-6 instead! I figured switching the default was a reasonable excuse to finally ship a 1.0. OpenAI haven't actually confirmed that GPT-6 uses the same tokenizer as the GPT-5 family yet…
Summary published by Simon Willison's Weblog · 9 Oct 2026 · Read the original ↗
Release: ttok 0.4 ttok is my CLI tool for counting tokens, using OpenAI's open source tiktoken library. It hasn't been in updated in a couple of years, but I finally fixed a Click warning, updated CI, and added a --list-models command to list available models. It works with uvx , so you can count tokens in anything like this: cat file.txt | uvx ttok Tags: projects , ai , openai , generative-ai…
Summary published by Simon Willison's Weblog · 8 Oct 2026 · Read the original ↗
Build an agent that pays for real purchases. Restock runs in Slack on Managed Deep Agents and pays with Stripe's Link over the Machine Payments Protocol.
Summary published by LangChain Blog · 8 Oct 2026 · Read the original ↗
The big drop of this week was not a new AI model.
Summary published by Don't Worry About the Vase · 8 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 ↗
How we built a model router into Open SWE's harness that cut median cost per coding task by 64% with no measurable drop in quality, and how to build your own.
Summary published by LangChain Blog · 2 Oct 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 ↗