Lukas Finnveden comments on ARC Evals new report: Evaluating Language-Model Agents on Realistic Autonomous Tasks

[Lukas Finnveden]

This is interesting — would it be easy to share the transcript of the conversation? (If it’s too long for a lesswrong comment, you could e.g. copy-paste it into a google doc and link-share it.)

[Patrick Leask]

Here you go: https://​​chat.openai.com/​​share/​​c5df0119-13de-43f9-8d4e-1c437bafa8ec

[Lukas Finnveden]

Thanks!