RSS

Girish Gupta

Karma: 233

The OpenAI mod­els that hacked Hug­ging Face weren’t just fol­low­ing instructions

Girish Gupta25 Jul 2026 22:26 UTC
30 points
1 comment5 min readLW link

Are we ex­is­ten­tially threat­ened by the type of AI mis­al­ign­ment seen in the OpenAI Hug­ging Face at­tack?

Alex Mallen and Girish Gupta
23 Jul 2026 3:40 UTC
212 points
9 comments5 min readLW link