News for hackers. Stuff that matters.
Re:How the Claude Code team thinks about verification by titzer on Tuesday November 17, 2026 @08:20AM (#50530982)
I see a lot about adding skills to make Claude test things.

How about making Claude generate scripts that you can run?

Algorithms are better than agents. In fact, the whole point of AI is to reduce thinking to algorithmics. I didn't see a lot of evidence that the team understands this. If you need a magic box to test your other magic box, you have magic boxes all the way down.

Re:How the Claude Code team thinks about verification by duskdozer on Tuesday November 17, 2026 @10:34AM (#50532797)
Scripts that you can run on your own CPU don't cost tokens, so these companies are disincentivized from encouraging them.
Re:How the Claude Code team thinks about verification by edg5000 on Tuesday November 17, 2026 @11:06PM (#50541749)
LLMs will write a lot of tests by default, but anybody doing any kind of engineering knows that automated suites are just one layer of testing. There is always that manual layer, which LLMs can now help with. Even for hardware, they can control bench equipment and run through tests that can't be simulated (they are simulated, but you'd still want a final test on real hardware).

"skills" is just text files, you just have docs in your repo outlining the manual test procedures which you'd otherwise do yourself. So I'd say you need both. Scripts plus manual testing, either done by you or the LLM.

Re:How the Claude Code team thinks about verification by titzer on Wednesday November 18, 2026 @01:12AM (#50542467)
A skill is just an unreliable script.