✳flâneur — a map of the web's best reading
Recursive forecasting: Eliciting long-term forecasts from myopic fitness-seekers — AI Alignment Forum
alignmentforum.org · 3,184 words · saved by 1 readers
We’d like to use powerful AIs to answer questions that may take a long time to resolve. But if a model only cares about performing well in ways that…
x Recursive forecasting: Eliciting long-term forecasts from myopic fitness-seekers — AI Alignment Forum Outer Alignment Redwood Research AI Frontpage 29 Recursive forecasting: Eliciting long-term forecasts from myopic fitness-seekers by Jozdien , Alex Mallen 28th Apr 2026 9 min read 2 29 We’d like to use powerful AIs to answer questions that may take a long time to resolve. But if a model only cares about performing well in ways that are verifiable shortly after answering (e.g., a myopic fitness seeker ), it may be difficult to get useful work from it on questions that resolve much later. In t
Explore this link on the map →saved by
related reading
- The behavioral selection model for predicting AI motivations — LessWronglesswrong.com
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- Pitfalls in Evaluating Language Model Forecastersarxiv.org
- Training LLMs to Predict World Events (Guest Post with Mantic) - Thinking Machines Labthinkingmachines.ai
- Fitness-Seekers: Generalizing the Reward-Seeking Threat Model — LessWronglesswrong.com
- Forecasting is Way Overrated, and We Should Stop Funding It — LessWronglesswrong.com
- How AI Will Save Prediction Markets — LessWronglesswrong.com
- The Parable of Predict-O-Matic — LessWronglesswrong.com
- What 2026 looks like — AI Alignment Forumalignmentforum.org
- Models Don't "Get Reward" — LessWronglesswrong.com
- Mediumai-alignment.com
- 🔮 IT’S OVER - The Oracle by Polymarketnews.polymarket.com