News for hackers. Stuff that matters.
Re:Benchmarking Opus 5 on SlopCodeBench by ACCount37 on Tuesday July 28, 2026 @06:47AM (#49081974)
You should. Feel like a conspiracy theorist when saying things like this.

Users are not reliable or consistent model evaluators. Users adapt to models - the moment they get a model that performs better, their expectations rise, their tasks get harder and their prompts get shorter.

"They made the model worse" is PEBKAC in 9 cases out of 10.

Re:Benchmarking Opus 5 on SlopCodeBench by svnt on Tuesday July 28, 2026 @12:04PM (#49085955)
There are few conspiracies where the vectors between "capitalist organization makes more money" and "user can't reliably distinguish tiers of product quality" overlap.
Re:Benchmarking Opus 5 on SlopCodeBench by ACCount37 on Tuesday July 28, 2026 @05:54PM (#49090428)
I wish the users weren't so fucking stupid with the "they made the model worse" stuff.

Then that 1 out of 10 case where the model was actually made worse (whether intentionally or by mistake) would stand out instead of being swallowed by the noise floor.