News for hackers. Stuff that matters.

A comment on Benchmarking Opus 5 on SlopCodeBench.

Re:Benchmarking Opus 5 on SlopCodeBench by nikhilsimha on Tuesday July 28, 2026 @11:24AM (#49085333)
the last note about the agent sending emails without approvals is a very common problem!
[ Parent | on HN ]

There are no comments on this comment yet.