Does it still try to 'unplug' itself if it gets something wrong, or did they RL ... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		dpoloncsak 5 months ago \| parent \| context \| favorite \| on: Improved Gemini 2.5 Flash and Flash-Lite Does it still try to 'unplug' itself if it gets something wrong, or did they RL that out yet?

jjani 5 months ago [–]

Not sure if you're joking or serious? Every model has "degenerate" behavior it can be coerced into. Sonnet is even more apologetic on average.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact