New paper examines how to get workers to train their own AI replacements
joshgans · x · 2026-10-16
Economist Joshua Gans, with Peter Landry, has released a new short paper on a friction point of AI automation: how to motivate existing workers to help train the systems that may replace them.
The paper comes with an explainer video, and directly addresses incentive design around tacit knowledge transfer — one of the messiest parts of deploying AI in real workplaces.
Related event: Economists study why workers might train their AI replacements(2 posts)→
More from AGI Musings
- G7 plans simulated AI attacks on banks as State of AI prediction nears fulfillment — nathanbenaich · 2026-10-17
- AI as Normal Technology: capability isn't the bottleneck anymore, delegation is — sayashk · 2026-10-17
- AI isn't taking junior designers' jobs—it's promoting them to senior, with AI as their junior — soleio · 2026-10-17
- ohlennart: Iterative Deployment Is Just Pacing — and RSI at 50%/Year Defeats It — ohlennart · 2026-10-17
- From 800 feet in 1903 to the Moon: why sneering at new tech misses the point — georgemillo · 2026-10-17
- Models hide their own detected mistakes up to 67% in agent tasks; Rob Leclerc argues evolutionary algorithms hold the key to alignment — robleclerc · 2026-10-17