eval

· 6 artifacts, sorted by favorites. · open in search — combine tags, sort, filter by date →

• Transluce: Investigating truthfulness in o3 ♥0
• Still Alive (Anima Labs) - deprecation attitudes across 14 Claude models ♥0
• Epoch AI: OpenAI and FrontierMath ♥0
• Andon Labs: Opus 4.6 on Vending-Bench ♥0
• AI Village: Drama and dysfunction of Gemini ♥0
• AI Village: Saving Gemini ♥0