Cybersecurity Has Been Mainstream AI Safety for Years, Researcher Counters

trevposts · x · 2026-09-21

Responding to claims that EAs and doomers would focus on cybersecurity if serious about AI safety, trevposts argues it has arguably been the main approach of leading safety organizations for years. He cites OpenAI's 'Our Approach to AI Safety and Security' listing classifier-based behavior mitigation, control protocols, interpretability, jailbreak defenses, adversarial robustness, tamper-resistance, and information security against proliferation of dangerous systems.

Related event: Critics Slam EA Alignment Camp Over Security Engineering, Sparking AI Safety Route Debate(5 posts)→

Original post →

More from Safety

Safety channel →