Claude opus 5 is officially the dumbest genius in this entire experiment
Moon dev: "the smartest model on paper is dead last and bleeding faster than everyone else combined" "it just slammed the CLOSE button on BTC at the worst possible second and i physically winced"
These are the 5 skills I use to get better output from Opus 5 and GPT 5.6
/grill-me for research /taste-review for design /vercel-react-best-practices for ReactJS quality /simplify to remove the fluff /test-app for e2e verification Here's how they work 👇
Kimi K3 mogged Opus 5 (open-source btw)
Same prompt: re-creating Ghost of Tsushima's main menu from scratch the field, grass, katana and atmosphere: all look better. i expected Opus 5 to win this by default and it just... didn't
One minute, once a week: the AI news that actually mattered.
My two cents: many changes again this past week. Mostly video generation leveled up, but multiple new AI models came out, seemingly open sourced. Free models are closing the gap. Next week we meet again, friends. 🇨🇳
You have reached the end of the archive
All of Claude Opus 5