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

How do you propose they check for something like this? They can't exactly ctrl-f the model weights for "Arc-AGI".


Anthropic expends tons of compute and effort on understanding internal model states [1]; this kind of thing is right up their alley.

[1]: Recent example: https://www.anthropic.com/research/global-workspace


> they can’t possibly know or find out what was in the training data

doesn’t appear to be a very strong argument




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

Search: