The daily ledger

llm-anthropic 0.31

Release: llm-anthropic 0.31 Anthropic released Fable 5.2 and Mythos 5.2 today. Fable 5.2 is currently ranked first on Artificial Analysis. Anthropic say it "solved two open problems in the physics of black holes", so…

Locating the source of a mysterious beep with Claude

Our house has a box room, full of boxes that we still haven't unpacked from our last move. A couple of weeks ago something in that room started intermittently beeping. The beeps were far enough apart that standing in…

The Web Is More Than Enough, by Paul Ford

My comment on The Web Is More Than Enough, by Paul Ford — Hacker News. OK, this comment convinced me to give that a shot. Here's a thing I made in Three.js this morning - a Nudibranch themed Faberge Egg:…

Hide your slop PR descriptions behind <details><summary>

Most of the changes I make to my projects these days come in the form of PRs opened for me by Claude Code or Codex. The PR is my unit of work - I use them to bundle commits together, iterating on them until a feature is…

How I Engineered My Full-Stack Developer Portfolio (635 UI Layers, 3D Orbit & Terminal Contact)

Watching 40 collaborative cursors assemble all 635 UI layers of my developer portfolio in 46.1 seconds puts the entire architecture into perspective. Here is a complete breakdown of how I designed and engineered…

Continuous Batching Beats Static and Dynamic by Up to 2.91× in vLLM

For anyone running an inference server: a zero-variance control, five traffic traces, and an engine-vs-scheduler split show where the gains come from. The post Continuous Batching Beats Static and Dynamic by Up to 2.91×…

Ask AI to Refine Your Ideas, Not Invent Them

Studies of short stories, metaphors, and 486 participants point one way, an 800-person experiment points the other, and the author weighs both. The post Ask AI to Refine Your Ideas, Not Invent Them appeared first on…

TDD With AI Agents: Design the Tests First, Let the Agent Implement

Learn how to use test-driven development (TDD) with AI agents in Python. Design the tests first, then let a coding agent write code that passes them.

How to Estimate the Recall of AI Agents with Capture-Recapture

A fisheries estimator from the 1890s, tested on 294 CUAD contracts, landed within 2 points of true recall for most agents with a 10% hand audit. The post How to Estimate the Recall of AI Agents with Capture-Recapture…

Quantile Regression Caught the House Price OLS Missed by $55K

On 88 house sales, OLS predicted $164K for a $219K home, while a 90% interval from 5th and 95th percentile models spanned $136K to $227K. The post Quantile Regression Caught the House Price OLS Missed by $55K appeared…

Quiz: TDD With AI Agents: Design the Tests First, Let the Agent Implement

Check your grasp of TDD with AI agents in Python. Write the contract and tests first, then let a coding agent implement code that passes them.

LernerPython blog, from Reuven Lerner: Pandas 3.1 CSV loading: Multi-threaded, but PyArrow is still faster

Reading a CSV into a Python Pandas data frame? Before version 3.1, loading CSV was single-threaded and slow. My test file took 1.03s. In 3.1, it’s now multi-threaded and much faster, taking 252 ms. However, it’s still…

Graham Dumpleton: Muru: import once, fork many

Every time Muru has started an application in this series, starting with a first look at Muru, one of the first lines of output has been something like: muru.host[88644]: preloaded app:application in 1 ms In how it fits…

Armin Ronacher: AI and Irontown

For our last movie night we watched Princess Mononoke. I remembered loving that movie when I was younger, but watching it as an adult made me once again realize how Miyazaki has a way of expressing diverging sides…

PyPI's redesigned project pages with clearer security signals are now live