viewpoints.xyz
Vote

AI forecasting

What do you think of the following statements?

39 people have given 316 responses

The claim of "superhuman" forecasting ability is exaggerated.

7410

Given what we currently know it is fair to say that the Safe AI forecasting model performs better than the metaculus crowd forecast.

7214

The system's performance may not translate to consistent profitability in high-liquidity prediction markets.

6513

On balance the Safe AI forecasting model will probably beat the metaculus crowd forecast if given questions 3 months in the future and unable to see the crowd forecast.

5810

The search engine date cutoff feature used to prevent information leakage is potentially unreliable.

586

It is likely that information was leaking into the questions that Safe AI were testing their model on.

556

People who strongly identify with a particular skill or domain (X) tend to be more pessimistic about AI surpassing human abilities in that domain (X).

559

The questions used for evaluation may have been cherry-picked or biased towards the system's strengths.

4821

Nathanpmyoung's market resolution is still unclearly defined.

3223

The decision to use Platt scaling in the evaluation is questionable and lacks sufficient justification.

273

The evaluation set was all questions that resolved within some amount of time after the cutoff set.

1310