News for hackers. Stuff that matters.
Re:MIT researchers use large language models to flag problem... by beardyw on Thursday August 15, 2024 @03:34AM (#41253837)
> converts time-series data into text-based inputs an LLM can process.

What? Which the model then tokenizes? I am struggling to make sense of this.

Re:MIT researchers use large language models to flag problem... by ubercore on Thursday August 15, 2024 @03:36AM (#41253847)
I read this as basically finding a language representation of timeseries data that would be understood by LLMs better than feeding raw records. I'm guessing it tokenizes very similarly to any other LLM. Perhaps I misread, though.
Re:MIT researchers use large language models to flag problem... by beryilma on Thursday August 15, 2024 @01:06PM (#41258176)
This is the modern day equivalent of "every signal is an image" after the initial success of deep learning algorithms in image classification tasks. It is just the academia chasing the hype train...