dotey argues multi-loop agents are inevitable: everyone will manage a fleet of Agents like a Manager
dotey · x · 2026-10-28
Responding to the argument that running multiple agent loops wastes attention and merely soothes AI anxiety, dotey contends multi-agent parallel execution with self-verification is an inevitable trend.
- He likens it to an IC becoming a Manager: split tasks across agents, keep aligning direction, set milestones, verify and merge results, and take the blame when things break.
- Since agents run async (his typical task takes 30+ minutes), idle waiting is inefficient — opening many loops keeps humans fully occupied dispatching and verifying. "Everyone will be forced to transition from IC to Manager, just managing a bunch of Agents."
- On the objections: agents can already self-correct given verification tools (even video editing, via extracting consecutive frames and analyzing them multimodally), and expectation mismatch is handled by upfront alignment — plans, docs, prototypes — plus milestone checks and final acceptance, just like good management of people.
Related event: AI Community Debates Multi-Agent Loops and the Rise of Agent Managers(2 posts)→
More from AGI Musings
- Anthropic Partners With Six Drug Developers to Speed Medicine Discovery, Launches In-House Programs — AnthropicAI · 2026-10-28
- GEO: the KDD-2024-defined practice of writing content to be cited by AI answers — robertonappe · 2026-10-28
- AI skeptic's job-destruction worry overlooks countless newly solvable problems — robleclerc · 2026-10-28
- Grant agencies flooded with applications — and admins haven't connected the dots to AI — wandedob · 2026-10-28
- Frontier Models as CapEx, Open Models as OpEx: Where AI Token Spend Is Heading — curious_vii · 2026-10-28
- Chris Albon's thought experiment: how would AI history differ if another community found scaling? — chrisalbon · 2026-10-28