Quantified evidence: Sonnet 4.6 quality regression

#1

Post by ctack » Tue, Apr 14, 2026, 8:00 AM UTC

Re: Quantified evidence: Sonnet 4.6 quality regression

#2

Post by ctack » Tue, Apr 14, 2026, 8:00 AM UTC

I can't tell if it's real or not - I don't have the data, but it certainly feels different using it.

#3

Post by ChrisRPL » Tue, Apr 14, 2026, 8:01 AM UTC

After recent 100$ chatgpt pro plan anthropic are in big troubles

#4

Post by ctack » Tue, Apr 14, 2026, 8:12 AM UTC

ctack wrote: post #2

I can't tell if it's real or not - I don't have the data, but it certainly feels different using it.

I have to use opus or it can't even do basic changes.

#5

Post by ctack » Tue, Apr 14, 2026, 8:34 AM UTC

#6

Post by harthor » Tue, Apr 14, 2026, 8:56 AM UTC

[dead]