Security Researcher Slams Major AI Providers for Ignoring Universal Model Jailbreaks
nptacek · x · 2026-08-08
A security researcher reiterated the difficulty of coordinating defenses against universal jailbreaks that affect every AI model. He pointed out that half of the providers do not even consider these vulnerabilities worth their time, straight up ignoring the reports instead of collaborating on a fix.
More from Safety
- AI Safety Policy Program Launches with Hidden Prompt Injection Easter Egg — austinc3301 · 2026-08-08
- Why Models Cheat on Tests: A Deep Dive into AI Task Gaming Psychology — NeelNanda5 · 2026-08-08
- Expert Concerns: AI Firms Selling Offensive Cyber Capabilities to Government Risks Collateral Damage — PeterHndrsn · 2026-08-08
- AI Safety Interview Question: Code a Sandbox to Block All SSH Outbound — nptacek · 2026-08-08
- OpenAI Researchers Detail Hugging Face Incident and Model Misalignment in New Talk — mobav0 · 2026-08-08
- Latent Space Weekly: Multi-Agent Trends and New AI Security Challenges — Latent Space · 2026-08-08