logoalt Hacker News

incrudibleyesterday at 8:48 PM1 replyview on HN

Is it actually better though? Can you even measure it? Unguided, Claude will just produce mediocrity which by its own existence becomes almost worthless, and the newer versions become increasingly difficult to guide while also being obnoxious to read. If I did not have to interact with it, it would not be a big deal, but then also I could not get value out of it.


Replies

datadrivenangelyesterday at 10:11 PM

It's a little smarter and more effective in some ways, especially those that can be benchmarked. I suspect that they've lost something that is hard to benchmark for.