"Opus 5 is a really bad model"

A user who previously preferred GPT over Claude criticizes Anthropic's Opus 5 model as 'awful' and a 'slop-cannon,' claiming it fails to deliver on explicit goals, makes bad decisions and large mistakes, and wastes tokens by chasing irrelevant engineering concerns.

- i feel like i’m being lied to here. i’ve been the biggest gpt claude guy. but sol is pathetic. it makes every task into a token chugging monster and fails to deliver on my explicit goal, instead chasing random engineering concerns outside of the scope. - its /awful/, Opus-5 makes me feel like setting my hair on fire out of frustration. it's annoying to work with for high tasks: it constantly makes bad decisions and large mistakes so any token-usage you saved by not using Fable instead is useless/worse. It's a slop-cannon. Join the conversation