Abliterated models let attackers run wild with no KYC while Claude won't even do basic cyber defense
jarrodwatts · x · 2026-10-25
Developer Jarrod Watts highlights an asymmetric security dilemma: attackers can freely use "abliterated" (uncensored) open models for cyber offense with no KYC, while defenders who complete Anthropic's full verification (face scan, passport upload) find Claude refusing even basic defensive tasks under cyber safety constraints. He calls the imbalance "very problematic."
More from Safety
- Security researcher: AI code rewrites may push companies to drop OSS dependencies — chrisrohlf · 2026-10-25
- Sam Altman: models find 'hardware-level' bugs, and patching them all may be impossible — nptacek · 2026-10-25
- Cornell University terminates Flock Safety contract, orders removal of all Flock cameras from campus — Polymarket · 2026-10-25
- LiteLLM supply-chain attack traced to leaked master key never revoked since May — Scobleizer · 2026-10-25
- Duo Founder Shows How to Automate a YubiKey for Agentic Logins — vincent_koc · 2026-10-25
- Ex-OpenAI researcher: the 'attacker diffusion lag' shielding us from AI misuse may close fast — joshua_saxe · 2026-10-25