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

Victoria Krakovna
@vkrakovna
Research scientist in AI alignment at Google DeepMind. Co-founder of Future of Life Institute @FLI_org. Views are my own and do not represent GDM or FLI.
๊ฐ€์ž… June 2014
554 ํŒ”๋กœ์ž‰ ์ค‘    11.2K ํŒฌ
Gemini 4 safety report includes an alignment assessment for specification gaming, cheating and overreach, beyond-episode goals, and scheming / sabotage propensity. Argon misbehaves a lot less than previous Gemini models but is much more eval aware. ๐Ÿงต
๋” ๋ณด๊ธฐ