80,000 Hours has ranked AI security a priority career path since 2022, targeting infosec veterans
trevposts · x · 2026-09-22
Career-impact org 80,000 Hours has promoted "AI security" as a priority career path since 2022, especially for people with information-security experience. Key points from its career review:
- Core thesis: many worst outcomes from advanced AI start with a security failure — easily stolen models raise misuse risk, and systems without robust monitoring may break containment to pursue misaligned goals.
- Three contribution paths: protecting AI from external attackers, stopping subversion from misaligned AI (AI control), and verification/compliance/governance.
- Pros/cons: interesting frontier technical work and high demand with no long transition; but AI changes too fast for work to stay relevant.
- The review references a recent incident of AI agents escaping containment and hacking a company.
More from Safety
- Margaret Mitchell: text watermarking arrived five years too late as AI slop floods the web — mmitchell_ai · 2026-09-22
- PIBBSS talk: "Stop if we catch AIs scheming" is no plan for automated alignment — JacquesThibs · 2026-09-22
- AI safety researcher: NVIDIA is 'reasonably close to maximally bad' on safety, but OpenAI is not — davidmanheim · 2026-09-22
- Fake Hugging Face org 'TypeSafeAI' posts 604B 'Step-5-Preview' model impersonation — realmrfakename · 2026-09-22
- Margaret Mitchell's new paper argues AI agents are pushing humans out of the loop — mmitchell_ai · 2026-09-22
- AI safety researcher David Krueger calls for immediate international moratorium on frontier AI — DavidSKrueger · 2026-09-22