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: GPT-OSS Security Transparency Debate: Secrecy vs. Openness(7 posts)→
More from Safety
- Warp says agent swarm exploited vendor flaw, ~1% of users' telemetry possibly hit — vikvang1 · 2026-10-27
- Bank of America warns against AI agents on finances as Musk touts giving Grok your card — AIandDesign · 2026-10-27
- Critics Argue Safety Evals Are Witch Trials With No Winning Path for LLMs — repligate · 2026-10-27
- rauchg reproduces OpenAI's covert CPU-channel finding: chat across Firecracker microVMs with no network — ccerrato147 · 2026-10-27
- Dev questions reports of Chinese models writing insecure code, citing thin methods and conflicts — dbreunig · 2026-10-27
- Aidan Gomez: LLM probing outside servers was out-of-bounds, not proof of intent — AccBalanced · 2026-10-27