| ▲ | a2ff6eeb0 2 hours ago |
| It seems like making progress on math is letting the AI run fully autonomously for a few days, occasionally asking it to keep going. I'm not sure people need to organize a mathathon to wait for a computer to give a printout. They mainly need tokens. |
|
| ▲ | jhonof an hour ago | parent | next [-] |
| I think the purpose of an event like this would be to optimize the process so that it isn't just occasionally asking an AI to keep going. |
|
| ▲ | charlieyu1 2 hours ago | parent | prev [-] |
| Are they actually autonomous? I’d say subject knowledge at the prompt stage plays a large part towards getting proper results |
| |
| ▲ | a2ff6eeb0 an hour ago | parent | next [-] | | When Claude made progress on the Riemann conjecture, here are the kind of prompts used: > Jarred's input was mostly limited to sending Claude messages of encouragement (mostly variants of “keep going” or “believe in yourself”).2 This seems to have helped Claude overcome some initial skepticism that it could make meaningful progress. | |
| ▲ | hgoel an hour ago | parent | prev [-] | | Prompting for some of the results was almost the "Computer, do a breakthrough. Make no mistakes." meme. Just someone telling the model to keep trying a couple of times. Unfortunately we don't actually know what kind of prompting was done for the more prominent results. |
|