Is "superhuman" AI forecasting BS? Some experiments on the "539" bot from the Centre for AI Safety

post by titotal (lombertini) · 2024-09-18T13:07:40.754Z · LW · GW · 3 comments

This is a link post for https://open.substack.com/pub/titotal/p/is-superhuman-ai-forecasting-bs-some?r=1e0is3&utm_campaign=post&utm_medium=web&showWelcomeOnShare=true

Contents

3 comments

3 comments

Comments sorted by top scores.

comment by Peter Njeim (peter-njeim) · 2024-09-19T00:51:12.511Z · LW(p) · GW(p)

Just a quick English correction. Proper nouns shouldn't be modified to match regional spelling varieties. There is no such thing as the "Centre for AI Safety", only the Center for AI Safety (CAIS). Here are the ABC, BBC, and CBC correctly referring to it.

comment by kqr · 2024-09-21T05:48:36.417Z · LW(p) · GW(p)

Thanks for taking the time to dive into this. I've spent the past few evenings iterating on a forecasting bot while doing embarrassingly little research myself[1], and it seems like I have stumbled into the same approach as Five Thirty Nine, and my bot has the exact same sort of problems. I'll write more later about why I think some of those problems are not as big as they may seem.

But your article also gave me some ideas that might lead to improvements. Thanks!

[1]: In this case, I prioritise the two weeks in the lab over the hour in the library. I'm doing it not to make a good forecasting bot but to learn the APIs involved.

comment by devrandom · 2024-09-20T09:07:23.974Z · LW(p) · GW(p)

There seem to be substantial problems with low probability events, coherent predictions over time, short term events, probabilities adding up to more than 100%, etc

 

A probabilistic oracle being inconsistent is completely besides the point.  If I have a probabilistic oracle that has high accuracy but is sometimes inconsistent, I can just post-process the predictions to force them into a consistent format. For example, I can normalize the probabilities to 100%.

The economic value is in the overall accuracy. Being consistent is a cosmetic consideration.