The tricky thing about predictions made by public entity or persona is that, the fact that they are making public predictions creates a major influence on the outcome itself. People react to predictions made by them.
I used to read it regularly. I can’t imagine anyone looking to them for predictions, as even a casual reader could probably outline the magazine’s views on most any topic. Let me skim 4-5 recent issues, and I could probably replicate anything they would predict with like 85% accuracy!
I will say that my favorite part of the magazine was the wacky ads for big shots working for African countries, various UN things, NGOs, etc.
https://www.readtrung.com/p/the-economist-cover-curse-explai...
...Normie?
What does that even mean in this context
Now being serious, LLMs are nondeterministic loosy compression algorithm which return "what a plausible answer to that question would be". They have no world model, no truth verification and formally will be excellent while having no verifiable content.
"There is a book about a boy in a magical school, with friends, who fights a big bad and its called ..."
should have Harry Potter as the highest possible response. But that is not the answer based on a truth model, just a statistical average. You could have been looking for Earthsea series. Or it could have the heat turned up and decide to go for a hallucinated answer over the statistically most likely token.
If you want a verifiable answer your best options would be to have the heat turned to 0, but that means it cannot create new responses. Or if you have heat, to ask 4 times and sample the avg. But at that point what is the advantage over just googling it?
And one shooting your answer and hoping its the bell curve answer is going to have decent results but its also proveably going to fail in a non insignificant number of cases
I don't see how that helps? If you just want the same answer multiple times in a row, you could just write down the seed of your pseudorandom number generator?
> And one shooting your answer and hoping its the bell curve answer is going to have decent results but its also proveably going to fail in a non insignificant number of cases
Setting the temperature to 0 doesn't guarantee you get a good answer either.
Now, if the hunter can accurately predict the prey's choice, they obviously simply need to select that same choice to always win. The similar logic works for the prey; but this means they can't both be perfect predictors of the future — if the hunter predicts that the prey will choose T, they will choose T as well, but that means the the prey will predict the hunter choosing T and will choose F instead, so the hunter has actually to predict that the prey will choose F, and so they will choose F as well, but that means the the prey will predict the hunter choosing F and will choose T instead...
Like, if you output a probability distribution among n options, and then there is a continuous map from the probability distribution you describe in your output, to another probability distribution over those options…
Err, hm, maybe you need a stronger hypothesis on the continuous map? If it is contractive then it will definitely have a fixed point. I don’t remember the hypothesis needed.
Also, consider the game of hunter-and-prey from my reply to the sibling comment. Again, the prediction that the prey will make some choice is arguably not a prediction at all.
https://en.wikipedia.org/wiki/Fedspeak
Quote from Greenspan himself:
> As Fed chairman, every time I expressed a view, I added or subtracted 10 basis points from the credit market. That was not helpful. But I nonetheless had to testify before Congress. On questions that were too market-sensitive to answer, 'no comment' was indeed an answer. And so you construct what we used to call Fed-speak. I would hypothetically think of a little plate in front of my eyes, which was the Washington Post, the following morning's headline, and I would catch myself in the middle of a sentence. Then, instead of just stopping, I would continue on resolving the sentence in some obscure way which made it incomprehensible. But nobody was quite sure I wasn't saying something profound when I wasn't. And that became the so-called Fed-speak which I became an expert on over the years. It's a self-protection mechanism ... when you're in an environment where people are shooting questions at you, and you've got to be very careful about the nuances of what you're going to say and what you don't say.
https://www.richmondfed.org/publications/research/econ_focus...
"Notably, in 1974, Federal Reserve chair Arthur Burns felt it necessary to make clear that high nominal interest rates would need to continue “for a time” as an anti-inflation measure;"
"A later chair, Paul Volcker, having presided over a period of very restrictive monetary policy, chose in March 1982 to make an explicit indication that nominal interest rates would and should fall in the period ahead."
https://www.federalreserve.gov/econres/feds/files/2021033pap...