LLMs can teach themselves to better predict the future
1–10 of 92 posts
Re: LLMs can teach themselves to better predict the future
#2Danny here, one of the authors of this paper. If anyone has any questions or anything feel free to AMA!
Re: LLMs can teach themselves to better predict the future
#3"Improving forecasting ability" is a central plot point of the recent fictional account of How AI Takeover Might Happen in 2 Years [0]. It's an interesting read, and is also being discussed on HN [1].
... [T]hese researchers are working long hours to put themselves out of a job. They need AI agents that can think ahead, so engineers train agents to forecast. They hold out training data before 2024, instructing models to ponder for hours to predict events in 2025. Then, they apply the same trick as before, distilling pondering into a gut reaction. Forecasting ability is a broad foundation. The researchers build specialized ML research skills on top of it, training U3 to predict the results of every ML paper and ML experiment ever recorded.
[0] https://www.lesswrong.com/posts/KFJ2LFogYqzfGB3uX/how-ai-tak...
Re: LLMs can teach themselves to better predict the future
#4"Improving forecasting ability" is a central plot point of the recent fictional account of How AI Takeover Might Happen in 2 Years [0]. It's an interesting read, and is also being discussed on HN [1]. ... [T]hese researchers are working long hours to put themselves out of a job. They need AI agents that can think ahead, so engineers train agents to forecast. They hold out training data before 2024, instructing models…
Great read! Thanks for sharing.
Re: LLMs can teach themselves to better predict the future
#5Danny here, one of the authors of this paper. If anyone has any questions or anything feel free to AMA!
Hey Danny, Really nice read.
Do you plan to share the source code to see if we could replicate this?
Re: LLMs can teach themselves to better predict the future
#6but is it really reasoning? honest question re the underlying architecture of transformers
also, self play seems quite an intuitive approach. There's another interesting paper from deep mind about play
Re: LLMs can teach themselves to better predict the future
#7but is it really reasoning? honest question re the underlying architecture of transformers also, self play seems quite an intuitive approach. There's another interesting paper from deep mind about play
You can call it blorbblorb if it makes you feel better. Reasoning is a social construct which, for many people, is grounded in humanity. Others ground it using other socially transmitted ontologies.
We don't usually discuss how people choose to ground their ontological beliefs, but why not? Why did you choose to ground "reasoning" in the way you do? If you didn't choose, why not?
Re: LLMs can teach themselves to better predict the future
#8[dead]
Re: LLMs can teach themselves to better predict the future
#9Danny here, one of the authors of this paper. If anyone has any questions or anything feel free to AMA!
Assuming LLMs eventually get really really good at this.
Do you see this destroying prediction-based markets (i.e. the stock market and Polymarket)?
Markets exist because there's uncertainty about the future. If LLMs can predict with extremely high accuracy, would there no longer be a need for markets?
Re: LLMs can teach themselves to better predict the future
#10but is it really reasoning? honest question re the underlying architecture of transformers also, self play seems quite an intuitive approach. There's another interesting paper from deep mind about play
You can call it blorbblorb if it makes you feel better. Reasoning is a social construct which, for many people, is grounded in humanity. Others ground it using other socially transmitted ontologies. We don't usually discuss how people choose to ground their ontological beliefs, but why not? Why did you choose to ground "reasoning" in the way you do? If you didn't choose, why not?
But, according to the paper, that's not what's happening
It's examining published news / research / whatever (input), making statistical predictions, and then comparing (playing) it against other predictions to fine-tune the result