News for hackers. Stuff that matters.

dantheman252

Re:LLMs Can Teach Themselves to Better Predict the Future on Tuesday February 11, 2025 @03:36PM (#43018029)
Hey Artem, NewsCatcher has been a great resource in our news pipelines!
Re:LLMs Can Teach Themselves to Better Predict the Future on Tuesday February 11, 2025 @02:33PM (#43017270)
We are currently focused on our plans for the next phase of this but cleaning things up and open sourcing is something we could consider in the future!
Re:LLMs Can Teach Themselves to Better Predict the Future on Tuesday February 11, 2025 @02:32PM (#43017250)
I don't forsee this destroying prediction-based markets in the near-term. It might make them more efficient, but you could have different LLMs competing in the same way humans do now. Its also interesting how this could create markets for more things that aren't considered on as much now because they are too difficult to estimate. At the end of the day though, LLMs are limited by the information provided to them.
Re:LLMs Can Teach Themselves to Better Predict the Future on Tuesday February 11, 2025 @02:29PM (#43017209)
We haven't gone down that road yet but would certainly an interesting proof point! :-)
Re:LLMs Can Teach Themselves to Better Predict the Future on Tuesday February 11, 2025 @01:35PM (#43016426)
Danny here, one of the authors of this paper. If anyone has any questions or anything feel free to AMA!
I don't think they reuse the boosters that they do a splashdown with. So reuse vs trash.
Interesting that this was done in academia. Now days this would just be hidden within some company not useable by others.