News for hackers. Stuff that matters.
Re:Anthropic appears to be A/B testing reduced effort levels... by gwerbin on Saturday August 22, 2026 @09:35PM (#49405489)
> I don't even try to steer it away from that with harness, because it doesn't work and just ends up agonizing over whether it should write some comment. Three paragraphs waffling on that on verbose output

If I give it the specific instruction to "elide all revisions, corrections, and past mistakes" it usually works. You can also have Sonnet do a cleanup writing/style pass in a subagent. I impression is that Opus has been deliberately trained to keep track of all such revisions by default as a kind of ad-hoc memory mechanism. It's probably good for autonomous coding and beating benchmarks, and I presume reduces flailing when a separate session needs to pick up the work.

There are no comments on this comment yet.