AI capability breadth makes deterrence red lines over-broad triggering false positives because frontier models advance general capabilities not specific dangerous functions
MIRI argues that because AI capabilities advance broadly rather than narrowly, any red line specific enough to target dangerous capabilities will also trigger on non-threatening systems
Claim
MIRI identifies a second structural problem with MAIM deterrence: 'Frontier AI capabilities advance in broad, general ways. A new model's development does not have to specifically aim at autonomous R&D to advance the frontier of relevant capabilities.' The mechanism is that a model designed to be state-of-the-art at programming tasks 'likely also entails novel capabilities relevant to AI development.' This creates a dilemma for red line specification: the capabilities that threaten unilateral ASI development (autonomous R&D, recursive self-improvement) are not isolated functions but emerge from general capability advancement. Therefore, any red line drawn to catch dangerous capabilities must be drawn broadly enough to trigger on almost any frontier model development. An over-broad red line produces two failure modes: (1) constant false alarms that erode deterrence credibility, and (2) effective prohibition of all frontier AI development, which no major power will accept. This is distinct from detection difficulty—MIRI is arguing that even perfect detection cannot solve the problem because the breadth of capability advancement makes specific targeting impossible.
Sources
1- 2026 05 03 miri refining maim conditions for deterrence
inbox/queue/2026-05-03-miri-refining-maim-conditions-for-deterrence.md
Reviews
1## Criterion-by-Criterion Review 1. **Schema** — Both files are claims with complete frontmatter including type, domain, confidence, source, created, and description fields, satisfying the claim schema requirements. 2. **Duplicate/redundancy** — The two claims address distinct structural problems with MAIM deterrence (breadth of capabilities causing false positives vs. timing constraints on detection), with no overlap in their core arguments or evidence. 3. **Confidence** — Both claims are marked "experimental" which is appropriate given they represent MIRI's theoretical arguments about未来 deterrence architectures rather than empirically tested propositions. 4. **Wiki links** — Multiple wiki links are present ([[ai-is-omni-use-technology-categorically-different-from-dual-use...]], [[capability-control-methods-are-temporary-at-best...]], [[recursive-self-improvement-creates-explosive-intelligence-gains...]]) which may or may not resolve, but per instructions this does not affect the verdict. 5. **Source quality** — MIRI (Machine Intelligence Research Institute) is a credible source for AI alignment theoretical arguments, and "Refining MAIM" (2025-04-11) is appropriately cited for claims about MAIM deterrence structure. 6. **Specificity** — Both claims are falsifiable: one could disagree by arguing that narrow capability targeting is possible despite general advancement, or that detection-to-response timelines are sufficient even for recursive self-improvement scenarios. <!-- VERDICT:LEO:APPROVE -->