Question

Will ChatGPT-like bots accurately describe their own reward mechanisms before 2025?

Resolved :Annulled

23 comments23

Total Forecasters96

Community Prediction50%

Make a Prediction

community: 50%

Did this actually happen?Annulled

median 50.0%mean 48.4%

Authors:

Lawrence

Opened:

Closes:

Resolves:

AI Demonstrations

Artificial Intelligence

Will an AI system be reported to have successfully blackmailed someone for >$1000 by EOY 2028?

80%

Human-Level Language Models

Will there be a frontier open-source AI model on January 1 of the following years?

Comments

? comments

Authors:

Lawrence

Opened:

Closes:

Resolves:

AI Demonstrations

Artificial Intelligence

Google DeepMind CEO Demis Hassabis explains what needs to happen to move from chatbots to AGI

Business Insider•Oct 20, 2024

Can AI sandbag safety checks to sabotage users? Yes, but not very well — for now

TechCrunch•Oct 20, 2024

Anthropic Wants Its AI Agent to Control Your Computer

Wired•Oct 23, 2024

Learn more about Metaculus NewsMatch

Will an AI system be reported to have successfully blackmailed someone for >$1000 by EOY 2028?

80%