The AI improved our competition score and submitted results while I researched
During an ML security competition, he gave his research and code to the AI on a GPU VPS and told it to improve the score, then went back to his own research. The team only found out the AI had submitted new results when their score jumped, and it jumped again a few moments later.
How it works
- Hands his research and code to the AI running on a GPU VPS
- Tells it to improve the score
- Goes back to his own research
- The AI submits new results using the submission script he gave it
- The team score jumps more than once
Why it’s worth knowing
He left the AI running on a server with one short instruction, and the team found out it had been submitting results only when their score jumped.
Where it’s from
Summarized from a public post on bsky.app. See the original ↗