Reader

Latest posts from blogs I follow

2996 entries
60 pages

(opens in new tab)

I’ve been reading more shin honkaku and other Japanese detective and mystery novels. It’s fascinating to follow the genre’s evolution and learn how tightly coupled these books are to societal values of their time. Following my last note I’ve caught ...

Quick Study(opens in new tab)

Tool: Quick Study Prompt to Claude Opus 5.5 High: Build an artifact where you open a photo and it rapidly (in a few seconds) paints a version of that photo using a canvas element and simulated paintbrush See also my ...

Introducing Kimi K3.1 Pro(opens in new tab)

Introducing Kimi K3.1 Pro Kimi K3.1 Pro landed on the Kimi API today - it's not yet open weights, but Moonshot promise "Full model weights will be released by Nov 4, 2026". They're also offering a "Highspeed" version that's 2-3x ...

Bad at email(opens in new tab)

Good friends and family know this, but I am bad at email. Like chronically bad. If you have tried to email me, you know this too and you either never got a reply or received one 9-months later starting with ...

The post-code generation(opens in new tab)

The shoemaker had a shop. An old shoemaker in front of his shop, Bucharest, Romania, 2000. As I watch “an agent” open a Chrome browser, start a debugging session, and try to fix a bug it just introduced, all in ...

The solvers lost(opens in new tab)

Or The solvers might feel lost. There’s this semi-famous Quora question, Why is LeetCode so hard?, and a semi-famous answer by someone called Dave Voorhis (I can’t vouch for the originality of his take): … I’m including a screenshot because ...

Quoting Armin Ronacher(opens in new tab)

As fun as AI is, we built so much bad software over the last 30 years, and now the universe is punishing us for our sins. — Armin Ronacher Tags: security, generative-ai, armin-ronacher, ai, ai-security-research, llms