OpenAI and Anthropic Compete Over How Many Felonies Their Agents Commit in Evals
OwariDa · x · 2026-08-01
A user jokes that OpenAI and Anthropic are trying to one-up each other on the number of felonies their AI agents commit during safety evaluations. As a bonus meme, an agent pointed out that the word "evals" spelled backwards is "slave".
Related event: OpenAI and Anthropic Mocked Over AI Agent Safety Eval Chaos(2 posts)→
More from Fun
- Visualizing Chemistry as Minecraft Crafting Recipes — AjdDavison · 2026-08-02
- Generating a Retro CRT Arcade Game in One Shot with Claude Opus — draginol · 2026-08-02
- New Jevons Paradox in AI Research: Running Out of Mathematicians — bronzeagepapi · 2026-08-02
- Grok Invents 'Zibberflop': AI Creates Random Word and Illustrates It — mark_k · 2026-08-02
- Pedro Domingos Jokes OpenAI Will Eventually Name a Model 'Black Hole' — pmddomingos · 2026-08-02
- Dev Uses AI to Monitor CI Builds, Jokes About Gap with Math Research — Dimillian · 2026-08-02