- cross-posted to:
- aicompanions@lemmy.world
- cross-posted to:
- aicompanions@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I often see a lot of people with outdated understanding of modern LLMs.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.
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 into the implications for it. I’m probably going to save this link as a rebuttal for the people who claim LLMs just predict the next word and have no concepts embedded in them.
I doubt that anyone saying that LLM are calculating next word solely based on previous sequence. It’s still statistics, regardless of complexity.
Youd be surprised at the level of unthinking hatred around them, but even discarding that Ive seen it said often that LLMs have no internal model of what they are talking about as they are just next word generators. This quite clearly contradicts that interpretation.
Yes, but people forget that our brains, and therefore our minds, are also “simply” statistics, albeit very complex.
Yeah I found this kind of reductionist talk pushes people to overlook the emerging properties of the system, which is where the meat of the topic is. It’s like looking at a living cell and saying “yeah well this is just chemistry”.
Yes, good topic, good research…
( you have a few typos : intobthe … into the, predicr … predict, im … i am. )
I think the most interesting thing in this article is the fact that some concepts central to semantics (analogy, connotation) or psychology (bias) kind of emerge naturally in multi layered neural networks of sufficient size. Also that it can sound like different personalities (overconfident, secretive, delusional) if you manipulate the weight or the proximity of features. I’d like to see the same kind of study but for midjourney…
There is no mind. It’s pretty clear that these people don’t understand their own models. Pretending that there’s a mind and the other absurd anthropomorphisms doesn’t inspire any confidence. Claude is not a person jfc.
Ah yes, it must be the scientists specializing in machine learning studying the model full time who don’t understand it.