News for hackers. Stuff that matters.
Re:Show HN: Phind Model beats GPT-4 at coding, with GPT-3.5 ... by nomel on Tuesday October 31, 2023 @02:23PM (#38089181)
Fifth sentence:

> However, we’ve found that HumanEval is a poor indicator of real-world helpfulness.

There are no comments on this comment yet.