Robert Miles punctures the excuse: will AI companies ever 'fully understand' their systems?
DavidSKrueger · x · 2026-11-06
AI safety researcher Robert Miles posted a pointed quip: "Ok, the AI did something bad, but only because the company didn't fully understand their system and did something dumb" — then asked rhetorically, "Do you expect the companies to start fully understanding their systems and stop doing dumb things?" The one-liner highlights the core tension in AI safety discourse: firms have limited understanding of their own models' internals, and blaming incidents on operator error implies an improvement path that may not exist.
More from AGI Musings
- Dev essay: why a runaway intelligence explosion isn't the risk — 'early onset decoherence' is — round · 2026-11-06
- Jeff Ladish on AI hacking, self-replication and automated AI R&D risk — JeffLadish · 2026-11-06
- Why AI writing feels annoying despite models winning literary competitions — cis_female · 2026-11-06
- Why AI writing annoys us: models can win literary prizes, the problem is style fatigue — cis_female · 2026-11-06
- METR estimates AI is already accelerating AI development by roughly 2x — harris_edouard · 2026-11-06
- Lightcone Commons Opens AI-Safety Grant Applications, Backed by Jaan Tallinn and Moskovitz — NathanpmYoung · 2026-11-06