logoalt Hacker News

bottlepalm • yesterday at 9:24 PM • 1 reply • view on HN

Absolutely because none of these models are ever trained fresh. We see the same quirks and personalities carry over into every subsequent generation of OpenAI, Anthropic, and xAI models. So Gemini having this latent madness is *extremely* concerning as they reach the point of super intelligence.


Replies

fragmede • today at 12:50 AM

Except they could have trained it out of the most recent version so using info from two years ago doesn't seem reasonable unless you've just got an axe to grind.