FeedCity

Release: llm-mcp-client 0.1a0

See this blog entry.

Tags: llm, model-context-protocol

Tool: Slack Emoji Maker

I wanted to create a new Slack emoji, and their tool recommends a square that's 128x128 and has a transparent background... so I had Fable build me this simple image editor against those requirements.

Tags: tools, slack

Release: datasette-agent 0.4a0

• New await context.browser_task() mechanism allowing agent tools to run code directly in the user's browser. #33

This is an exciting new capability: it makes it easy for Datasette Agent plugins to provide tools that execute custom JavaScript in the user's browser.

Tags: datasette, llm-tool-use, datasette-agent

The pricing gun should have been a dead technology years before it actually was. But state laws artificially kept it around as a shield against the scary barcode.

Second order linear differential equations with polynomial coefficients form their own area of study. This seems like a narrow class of equations, but it’s very important in applications. This class of equations seems like a mathematically natural topic, but why is it so important in applications? I did a PhD in differential equations without ever […]

The post Why polynomial coefficients? first appeared on John D. Cook.

Combinatorial problems can be interesting for their own sake, but they are more interesting when there is a connection to a problem outside combinatorics, and the more unexpected the connection the better. Counting the number of unlabeled rooted trees [1] with n nodes is a pure mathematics problem. Designing numerical methods for solving differential equations […]

The post Counting rooted trees first appeared on John D. Cook.

The textbook version of the Runge-Kutta method for solving differential equations has 4 stages and has 4th order error. For lower order versions of RK the number of stages s also matches the order of the error p. But in order to achieve error on the order of p ≥ 5, you need more than p […]

The post Runge-Kutta order versus stages first appeared on John D. Cook.

Today's links Why businesses lie about AI: Humoring the boss all the way into bankruptcy. Hey look at this: Delights to delectate. Object permanence: Vinge x NYT; Syklarov x publishers; Human hair castles; Gingrich's bot army; Accessibility v Web DRM; David Byrne x WinXP; Fur...

Pepper-spray drones, China’s chip Manhattan Project, Commonwealth Fusion’s fundraise, and a proposed Dulles Airport renovation.

The good folks at Hikmicro have sent me their D02 Infrared Camera to review. It's part of their "Eco" series of thermal imagers - designed to be easy to use around the home and relatively cheap. Despite the no-fills appearance, it packs in a lot of features which put some more expensive models to shame. It even works with Linux. Shove in a USB-C cable to grab the photos or even use it as a…

Releases, advisories, and articles from across the package management world

What failure of the context callback means.

The post Making an agile version of a Windows Runtime delegate in C++/WinRT, part 10 appeared first on The Old New Thing.

deepseek-ai/DeepSeek-V4-Flash-0731 The latest release in DeepSeek's V4 family, "with substantially enhanced agentic capabilities". It's 304 billion parameters - 167GB on Hugging Face - but it appears to punch well above its weight. Artificial Analysis rank it ahead of MiniMa...

Tuesday was Stateless MCP day - the rollout of MCP 2.0, or the 2026-07-28 Model Context Protocol specification to use the more formal but less memorable name. This is the most significant change to the MCP spec since it first launched, and has also served to reignite my pers...

Oxide and Friends: The Open Weight Revolution with Simon Willison On Monday Bryan Cantrill and Adam Leventhal invited me to join their podcast to talk about the wild week we've had - with Kimi K3 showing open weight models can stand toe-to-toe with proprietary frontier ones,...

smevals - a small eval suite for evaluating models, prompts, and harnesses I've been working with Jesse Vincent's Prime Radiant applied AI research lab building out this evals framework to help answer questions about the capabilities of different models. The result is smeval...

I was digging into the Runge-Kutta method for solving differential equations and a line from [1] piqued my curiosity. These calculations, which are not reproduced in Kutta’s paper (they are however in Huen (1900)), are very tedious. The calculations are a set of eight constraints that the parameters of a fourth-order Runge-Kutta method must satisfy. […]

The post Solving the RK4 design equations first appeared on John D. Cook.

Hi, folks… I’ll have the last article in the series on Maxis Software for you next week. Today, I’m happy to say that the new ebook, covering the historical year 1999, is available, and on a far more timely basis than the last one at that. My thanks go to Richard Lindner, for developing the […]

July! What a month! Things I did this July Gave a talk, for ClimateAction.tech’s “Responsible AI Series”, “What I know about local language models”. “Responsible AI” can feel like a bit of an oxymoron at times, but I hope I shared something useful. Participated in the Ze...

I wish I could say I was comforted