How long has SimpleBench been posted? Out of the first 6 questions at https://si... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		CamperBob2 on Dec 20, 2024 \| parent \| context \| favorite \| on: OpenAI O3 breakthrough high score on ARC-AGI-PUB How long has SimpleBench been posted? Out of the first 6 questions at https://simple-bench.com/try-yourself, o1-pro got 5/6 right. It was interesting to see how it failed on question 6: https://chatgpt.com/c/6765e70e-44b0-800b-97bd-928919f04fbe Apparently LLMs do not consider global thermonuclear war to be all that big a deal, for better or worse.

Pannoniae on Dec 20, 2024 [–]

Don't worry, I also got that wrong :) I thought her affair would be the biggest problem for John.

jquery on Dec 20, 2024 | [–]

John was an ex, not her partner. Tricky.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact