@max_paperclips: We need some kind of cybersec/acc movement at this point. incorporate interpretability too, there's a LOT of tools alre…

X AI KOLs Timeline News
cybersecurity interpretability open-source ai-safety internet-hardening collaboration

Summary

A tweet advocating for an open, collaborative cybersecurity and AI-safety movement that incorporates interpretability, arguing existing open models are sufficient to start hardening the internet.

We need some kind of cybersec/acc movement at this point. incorporate interpretability too, there's a LOT of tools already out & already available, it doesn't need to be "solved" to start being useful. Just, finally, ACTUALLY harden the internet. The current open models are good enough for this, and safe enough. Clearly this can't be something that's locked away ala Project Glasswing, and needs to be an open and collaborative effort.
Original Article
View Cached Full Text

Cached at: 08/08/26, 02:59 AM

We need some kind of cybersec/acc movement at this point. incorporate interpretability too, there’s a LOT of tools already out & already available, it doesn’t need to be “solved” to start being useful.

Just, finally, ACTUALLY harden the internet. The current open models are good enough for this, and safe enough. Clearly this can’t be something that’s locked away ala Project Glasswing, and needs to be an open and collaborative effort.

Similar Articles