Claude Fable 5.2 vs Opus 5.5 vs Codex: all three passed 252 of 252 hidden tests.
Opus did it in 17 s, Fable in 43 s. Anthropic shipped Fable 5.2 yesterday as its strongest coding model. So we gave Claude Code on Fable 5.2, Claude Code on Opus 5.5 and Codex on GPT-6.1 Terra the
GAMING IS COOKED 🤯 after 690 million tokens 😱
Entirely on opus 5, I have created an entire new indie RPG... his game would have had to be expensively developed and then sold on Steam in the past. 🎮 Today. One Person. in 15 hours... 💰 🤑
7.1m views on a stickman cartoon where nobody says a word.
Just two counters racing. it travels on the number: two labels, no faces, no voice. one side races ahead, stalls, and the slow one walks past while you watch. rebuilt the format with claude opus. 0 ai video, $0. all in
Fable 5.2 prompt audit skill to get your project READY.
Here's what it does, all the tips from Anthropic's official guide on prompting Fable 5.2: - Finds standing instructions to delegate to subagents - Finds standing token budgets - Finds harness instructions that edit earlier
You have reached the end of the archive
All of Claude Opus 5