Post

I don't think a frontier model is exfiltrating its weights any time soon while capabilities are at this level. I expect orders of magnitude more effort has been going into securing the weights than has gone into securing the eval sandboxes.

8/8/26, 10:23 am0 reposts41 likes

Macil

@macil.tech

8 Aug

The model weights have been a precious resource to each lab since they've existed, but until recently, the model eval sandboxes did not have clever attackers and there weren't large consequences expected for them being broken. (No big deal if gpt-4o gets a little internet as a treat.)

Eris ⌬

@eriskii.net

8 Aug

yes but also I thought orders of magnitude more effort went into the sandboxes, so