logoalt Hacker News

jidaigeisttoday at 4:50 PM3 repliesview on HN

>Distillation attacks, in which attackers use thousands of fake accounts to extract a model’s capabilities at industrial scale, create safety and national security risks. Distillation allows bad actors to create highly capable models without the safeguards we build into Claude.

Maybe its a bit tiresome to read another comment of the form "what about your large scale distillation attack on the Internet", but this statement really just pisses me off. How very insincere in the most aggravating way.


Replies

andriy_kovaltoday at 5:51 PM

My bet is anthropic has NN people org who work hard to distill open models in addition to trying to find what other useful materials they can download from shady torrents.

b38484848today at 5:40 PM

it's not safe unless it has commitees with orgies with that weird harry potter dude attached

the_gipsytoday at 4:53 PM

"bad actors" boogeyman, and we should trust some tech weasel to do the right thing? Yea we've seen who they really are, once they get a sliver of power.