| ▲ | khafra 2 days ago | |
I gave a safety talk at an ML conference that also had a skeptical representative from HuggingFace. Like Delangue, he didn't seem to have seriously considered the threat model--myopically focused on the capabilities of current agents (a myopia which, while less excusable then than in 2015 or 2021; was at least more excusable than Delangue's in this article since HF hadn't yet been pantsed by an agent swarm). | ||
| ▲ | cyanydeez 2 days ago | parent | next [-] | |
is the threat model something you put into a ML or nah? | ||
| ▲ | dwattttt 2 days ago | parent | prev [-] | |
> HF hadn't yet been pantsed by an agent swarm It's not that long ago that sites were pantsed by bored college students, rather than agents. It didn't stop because sites got more secure really, it stopped because those students started getting real life consequences. Gives you a real easy solution to stop the agents too. | ||