Claude Opus 5 is nowadays sooo fucking dumb, holy fuck.
Claude, fuck off. I know you want to increase profits ahead of the IPO, but the current models suck. On benchmarks, Grok 4.6 is a worse model, but somehow it actually gets shit done
I tested Opus 5 Ultra Code vs GPT-5.6 Extra High on a real Swift bug — the results surprised me 👀.
This was legit so funny!!
We put the agents against each other again, this time in and wow they can actually draw!! the name key: sledgehammer = GPT 5.6 Sol opus = Opus 5 rewind = Grok 4.6 saxophone = Gemini Flash 3.5 grok DCed early (rip). opus won,
24,283 people have starred a repo that turns one claude code session into a 49-AGENT game studio
The useful part is the hierarchy. Opus directors guard the vision and architecture, Sonnet leads own departments, and specialists handle gameplay, engines, UI, networking, art,
You have reached the end of the archive
All of Claude Opus 5