After 9/9: what's next for open-source model security, from formal verification to red teams
saranormous · x · 2026-10-22
saranormous asks where open-source models go after "9/9": beyond simply applying more tokens, can formal verification, safe distributions, or other approaches get the ecosystem to a defense-dominant posture — especially for the many orgs that have no red team at all?
Related event: Debating the Future of Open-Source Model Security After 9/9(2 posts)→
More from AGI Musings
- 'Cyberpocalypse' debate: prosaic cybersecurity is collapsing now, end-state contested — davidmanheim · 2026-10-22
- Kelsey Piper inside Anthropic: Claude alone now outperforms human+AI at plotting bioweapons — tszzl · 2026-10-22
- Ex-Meta researcher proposes breeding agents like dog breeds: keep 1 of 6 every 6 months — francoisfleuret · 2026-10-22
- 36 preprints in 3 months: BootLoops AI harness drives cross-field science — DeryaTR_ · 2026-10-22
- qntm's 'Lena': the sci-fi story of the first executable human brain snapshot — louisvarge · 2026-10-22
- In the AI age, taste beats function: competition shifts up the stack — vaibhavbetter · 2026-10-22