Birdwatch Note Rating
2024-10-06 13:39:06 UTC - NOT_HELPFUL
Rated by Participant: 9F02E1BA437E9D831E34B7F1F5D256DD09EAA574248D90122D5713CB577E0180
Participant Details
Original Note:
Claude 3.5 Sonnet does not outperform o1 in terms of reasoning using this prompt. https://x.com/ikristoph/status/1842807922214175105?t=7D5ymBDVIErL9hcMRhNYvQ&s=19 Although there are some results, the title is factually a clickbait. Outperforming o1 through prompting alone is virtually impossible. https://openai.com/index/learning-to-reason-with-llms/
All Note Details