kromemMay 21, 2024

Mapping the Mind of a Large Language Model

https://lemmy.world/post/15661170

Mapping the Mind of a Large Language Model - Lemmy.World

I often see a lot of people with outdated understanding of modern LLMs. This is probably the best interpretability research to date, by the leading interpretability research team. It’s worth a read if you want a peek behind the curtain on modern models.

Show threadWombleMay 22, 2024
This is a really good science communication article, it describes their work in clear terms (finding structures that relate to abstract concepts, seeing when they are activated and how strengthening and weaking them modifies outputs) and goes intobthe implications for it. Im probably going to save this link as a rebuttal for the people who claim LLMs just predicr the next word and have no concepts embedded in them.
Show threadmiskMay 22, 2024
I doubt that anyone saying that LLM are calculating next word solely based on previous sequence. It’s still statistics, regardless of complexity.
Show threadGeneral_EffortMay 22, 2024
Saying that it’s “statistics” is, at best, unhelpful. It conveys no useful information. At worst, it’s misleading. What goes on with neural nets has very little to do with what one learns in a stats course.
Show threadmisk
Most people don’t know what Bayesian statistics are so you could say most people don’t really get how machine learning works in general anyway. It’s not misleading though as it perfectly sets expectations on what you’re getting as output. It’s much more healthy to general understanding of AI than anthropomorphizing very inflexible and limited models.
May 22, 2024 at 2:24pmWeb
Show threadGeneral_EffortMay 22, 2024

I would not expect almost human-like conversation on being told that is just statistics. I’d expect something like the old Markov chain jobs. What kind of knowledge leads you to have higher expectations?

Also, how does Bayesian statistics enter into this?

Show threadmiskMay 22, 2024

ELIZA from 1966 was enough to convince people that computer program they were talking to was human. People are now being sold on getting answers to their questions via natural language prompts and those answers are pretty much plausibly sounding sentences that happen to be right sometimes due to probability calculations.

Bayesian statistics is very different from what’s being taught up until high school (at least here) and is foundational to earlier machine learning applications like spam filters. It’s hard to imagine understanding what LLMs do without basics.

Show threadGeneral_EffortMay 22, 2024
Those aren’t the basics, though. That’s how saying it’s statistics is misleading. A Bayesian network is not a neural network.