News for hackers. Stuff that matters.
Re:How the Claude Code team thinks about verification by koolba on Tuesday November 17, 2026 @06:53AM (#50530221)
> Nobody can read every change, so we use failures as one way to decide what needs a person.

Whether a human can or should review every diff is a conscious project level decision. I have yet to see a project where it is not feasible. The trick is to break things into small enough pieces that you can review them. Just like one would do if you were doing such changes manually. Nobody in their right mind performs non-mechanical changes of 100s of files.

Re:How the Claude Code team thinks about verification by ForHackernews on Tuesday November 17, 2026 @06:56AM (#50530248)
> Nobody in their right mind performs non-mechanical changes of 100s of files.

We're in a brave new world, many many big name companies are doing this.

Re:How the Claude Code team thinks about verification by testtestmetest on Tuesday November 17, 2026 @06:57AM (#50530264)
Their status pages reflect that.
Re:How the Claude Code team thinks about verification by bcrosby95 on Tuesday November 17, 2026 @07:28AM (#50530497)
If everyone is doing it, who you gonna turn to?
Re:How the Claude Code team thinks about verification by IshKebab on Tuesday November 17, 2026 @07:00AM (#50530275)
> Nobody in their right mind performs non-mechanical changes of 100s of files.

Not 6 months ago, sure. Today? It's not totally crazy. In a year it will be routine.

Re:How the Claude Code team thinks about verification by mrheosuper on Tuesday November 17, 2026 @09:46PM (#50541223)
Next year if your TODO app has less than 100 files then it's wrong.
Re:How the Claude Code team thinks about verification by fhd2 on Tuesday November 17, 2026 @07:07AM (#50530330)
The "right mind" of companies is a bit different from that of individuals. Generally they care about three things: Revenue, costs and risks.

To companies, some risks are worth taking, if it can increase revenue or lower costs. Many companies happily do not-quite-legal things, taking into account the potential of being caught and the size of the fine.

In the case of Anthropic, from that perspective, it almost seems like a no-brainer that they would want to push an "our AI can do it all, no humans needed" narrative in everything they do. They need hype like we need oxygen.

Re:How the Claude Code team thinks about verification by theshrike79 on Tuesday November 17, 2026 @04:18PM (#50538328)
[delayed]
Re:How the Claude Code team thinks about verification by thefunnyman on Tuesday November 17, 2026 @08:52PM (#50540895)
> Nobody can read every change, so we use failures as one way to decide what needs a person.

This keeps coming up at work and I feel like everyone's forgotten that code is cheap to produce and expensive to maintain. If you have devs assisted by agents vomiting out giant unreviewable PRs isn't that a sign that something's deeply wrong? It's always been the case that you can hack together something that appears to work but has deeper issues upon inspection yet there seems to be a massive push to just crank out the first version of whatever passes the bare minimum validation.