Blanche Minerva argues security by obscurity is not real AI safety
BlancheMinerva · x · 2026-07-23
The exchange debates whether revealing a technique makes it easier to reverse or defend against. Blanche Minerva argues that “decreasing the search space” is not a good explanation for safety, since the real way models become dangerous is direct fine-tuning on hazardous capabilities, and that security through obscurity is not real security.
Related event: Debate Erupts Over OpenAI's Refusal to Share GPT-OSS Security Details(6 posts)→
More from Safety
- John Schulman calls for a full transcript of the Hugging Face hacking incident — johnschulman2 · 2026-07-23
- JADEPUFFER ransomware is targeting AI pipelines without using a zero-day — TechNadu · 2026-07-23
- Security teams now have to manage hundreds of AI agents per employee — realmadhuguru · 2026-07-23
- AI alignment debates now center on human autonomy, not just control rules — GlenBradley · 2026-07-23
- AI Lowers the Barrier for Astroturfing: Shifting Social Media Narratives in 10 Minutes a Day — retr0jirachi · 2026-07-23
- Anthropic’s classifier is reportedly blocking math research prompts too — code_star · 2026-07-23