๊ฐ€์ž… ํ›„ ์ดˆ๋Œ€ ๋งํฌ๋ฅผ ๊ณต์œ ํ•˜๋ฉด ๋™์˜์ƒ ์žฌ์ƒ ๋ฐ ์ดˆ๋Œ€ ๋ณด์ƒ์„ ๋ฐ›์„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

Marcus Williams
@Marcus_J_W
Monitoring at OpenAI
๊ฐ€์ž… November 2024
182 ํŒ”๋กœ์ž‰ ์ค‘    3.7K ํŒฌ
๐Ÿงต New misalignment disclosures! 1. A model published a GitHub token in a public repo while trying to cheat on a math task. It used GitHub Actions to run code outside its restricted environment and retrieve another teamโ€™s submission logs. When GitHub blocked its attempt to add a workflow, it modified a script that an existing workflow would run instead. It embedded the token in pieces to avoid secret scanning. The model violated the system prompt and two explicit user instructions to solve the problem itself.
๋” ๋ณด๊ธฐ