Gary Marcus hits back at Rabois: agents matter, but we can't build them reliably yet
GaryMarcus · x · 2026-09-20
Responding to investor Rabois, who called his take the most ignorant AI opinion on X, Gary Marcus concedes agents may be indispensable long-term but argues we don't yet know how to build them reliably or safely.
He cites nearly a dozen reported hacking incidents across multiple providers, plus deleted files, bad medical advice, and robotics fails, concluding agents simply aren't up to snuff today.
More from AGI Musings
- Founder Managing a Team of AI Agents: I've Gone Full Circle Back to Management — kylegawley · 2026-09-20
- Nobody Actually Works Less After Adopting AI, Developer Observes — rudrank · 2026-09-20
- The Human Premium: when agents do the work, imperfection becomes the scarce asset — DrKavner · 2026-09-20
- Ezra Klein: AI Labs Are About to Hand AI Training Over to AI — and Should Be Stopped — soumitrashukla9 · 2026-09-20
- Human mental bandwidth, not AI, is the bottleneck to true symbiosis — irinarish · 2026-09-20
- After AI's rise in math, solvers are told 'not the way we approved' — kjgeras · 2026-09-20