FeedCity

I’ve heard some buzz around the new GLM 5.2 open-weights model. They say it’s very capable! I won’t run a full comparison benchmark, but I have some credits sloshing around on OpenRouter so I figured I might compare GLM 5.2 to the similarly-priced Gemini 3 Flash, and see where things land.

This uses the same setup as the previous benchmark: each LLM gets a few attempts at playing the game, with each attempt being limited to a fixed budget of around $0.15. The LLM doesn’t know it, but the harness tracks achievements for each game, and counts how many the LLM earns in each attempt.

Here are the number of attempts for each game in this run.

(Continue reading the full article on the web.)

Today's links The (real) dead economy theory: Vibes and memestocks, all the way down. Hey look at this: Delights to delectate. Object permanence: Jim Baen has had a stroke; Blame Apple for iTunes DRM; France v the internet; "Rotters"; 1901 undersea cables; Washington Post wan...

What happened in 2025 was this: the economics of code production were turned upside down. Instead of being very hard, time-consuming, and expensive to generate code, it became effectively free and instant. Lines of code went from being treasured, reused, cared for and carefully curated, to being disposable and regenerable, practically overnight.

— Charity Majors, AI demands more engineering discipline. Not less

Tags: charity-majors, ai-assisted-programming, generative-ai, ai, llms

Release: datasette 1.0a34

Quoting the release notes:

The big feature in this alpha is tools to insert, edit and delete rows within the Datasette interface. These features are available on table pages, and edit and delete are also available as action items on the row page.

The inspiration for this feature - which is long overdue - was Datasette Agent. I added SQL write support to that the other day which highlighted how absurd it was that you could insert and edit ties via the chat interface but not in the regular Datasette UI!

Tags: projects, datasette, annotated-release-notes

Where do we go from here?

AI made you faster. But you're not more productive; you're outsourcing the slow part to everyone else

I’ve been testing Claude’s ability to generate Lean 4 code to prove theorems. I’ve written about a couple experiments that verified calculations. I did not write about my failed attempt to get Claude to formalize a proof of the pqr theorem for seminorms. This time I asked Claude to formally prove the theorem from the […]

The post Formalizing a ring theorem with Lean 4 and Claude first appeared on John D. Cook.

Watch you hit the stage like a willing bomb Strapped to crippled children It’s hard to watch you whore out your damaged pride I spit on what you’re building   – The Stephen Hawking

Tool: <click-to-play> — a still that plays

A progressive enchantment Web Component that turns this markup:

<click-to-play>
  <a href="URL to GIF">
    <img src="URL to first frame" alt="...">
  </a>
</click-to-play>

Into a still frame with a click to play button which loads the GIF on demand. For when you don't want big GIFs to be loaded unless people want to play them.

Tags: gif, javascript, progressive-enhancement, web-components

NetNewsWire Status

I find this inspiring. Brent Simmons retired a year ago, and his retirement project is making one piece of software really, really good - free from any commercial pressure.

The software is NetNewsWire, first released in 2002 and made open source in 2018. I've been using it on Mac and iPhone for several years now and I'm finding it indispensable.

Via Lobste.rs

Tags: brent-simmons, netnewswire, open-source

Release: datasette-tailscale 0.1a0

A very experimental alpha plugin which lets you do this:

datasette tailscale mydata.db \
  --ts-authkey tskey-auth-xxxx --ts-hostname datasette-preview

This starts a localhost Datasette server with a Tailscale sidecar that connects it to your Tailnet, such that http://datasette-preview/ serves Datasette.

It's using the Python bindings for the experimental tailscale-rs library. I filed an issue asking if there's a cleaner way of setting up the proxy mechanism.

Tags: datasette, tailscale

As James Carville might have said, “It’s the lack of a moat, stupid”

The worst type of bug is one that only happens on prod. And only on prod. If you checked this blog in the past few weeks, you might have encountered a big fat 500 error. I'd had the same design for 10 years, and I wanted something fresh. But who can redesign without also i...

Some time ago, I attended an event to discuss European digital autonomy and digital dependencies. I accepted the invitation without checking too carefully, and I belatedly found out that most of US big tech was invited as well, and would be presenting their thoughts.
Now, even in our gloriously digitally autonomous future, we’ll still be doing business with Microsoft, Google and Amazon. And it is fine if they have a role.

A guide, of sorts, to keyboard customization. (9,400 words.)

Nearly everyone who has seen partial fraction decomposition was introduced to it as a way to compute integrals. If P(x) and Q(x) are polynomials, then you can break their ratio P(x)/Q(x) into a sum of terms that can each be integrated in closed form. As with most topics in a calculus class, partial fractions go by in […]

The post Partial fraction decomposition first appeared on John D. Cook.

"He begged to work for the regime that tortured him."

I can 100% attest to the fact that Qwen3.6-27B is a very capable local model for coding tasks. Over the last month and a half I've been using it almost daily, either on my M2 Ultra or on my RTX 5090 box. I use it for small mundane tasks at ggml-org - nothing really impressive, but definitely a helpful tool for a maintainer. I think I would be using it much more, if I didn't have to spend a lot of my time on reviewing PRs. Currently, I have a very lightweight harness - the pi agent with everything stripped (pi -nc --offline) and a short system prompt to align it a bit with my style.

— Georgi Gerganov, Hacker News comment on Running local models is good now by Boykis

Tags: georgi-gerganov, llms, ai, generative-ai, pi, ai-assisted-programming, local-llms, qwen, coding-agents

There are fewer ways to leave your package than to kill it.