Brundage: AI Security Progress Lags Capability Gains—the Strongest Case for Slowdown
Miles_Brundage · x · 2026-09-18
Miles Brundage adds: he would be working on AI security if he had much to contribute there. He laments that progress on security has not been commensurate with the pace of AI, which is perhaps the strongest argument for slowdown. He clarifies that he means security proper—not safety rebranded as security because some people dislike the term safety.
More from AGI Musings
- Detecting covert instruction-following via internal representations parallels J-space work — dioscuri · 2026-11-02
- Paras Chopra: Mastering AI means building self-improving systems, not solving problems directly — paraschopra · 2026-11-02
- Databases to distributed systems: every systems skill is merging into AI inference and hardware — Abhishekcur · 2026-11-02
- Limitless analogy: smarter people may gain far more from superintelligence — McDonaghMatthew · 2026-11-02
- Hunting for the most concrete "curing cancer with AI" roadmap of 2025 — iskander · 2026-11-02
- Avoiding AI brain rot: Miles Cranmer's lecture on learning with AI — _ScottCondron · 2026-11-02