Yann LeCun
speaker
384 appearances
5 recordings
4 series
first heard Mar 2024
last heard 20 Jun
Yann LeCun’s voice in public audio — every appearance, attributed to the second.
Trend
recordings per month · last 12 monthsRecordings per month over the last 12 months — 4 in all, peaking in Jan 2026 with 2.
Appearances
But there's probably more complex scenarios of this type, which an NLM may never have encountered and may not be able to determine whether it's possible or not. So that link from the low level to the high level. The thing is that the high level that language expresses is based on a common experience of the low level, which LLMs currently do not have.
When we talk to each other, we know we have a common experience of the world. A lot of it is similar.
No, I agree with what you just said, which is that to be able to do high-level common sense, to have high-level common sense, you need to have the low-level common sense to build on top of.
And that's not there in LLMs. LLMs are purely trained from text. So then the other statement you made, I would not agree with the fact that implicit in all languages in the world is the underlying reality. There's a lot about underlying reality which is not expressed in language.
You don't need to communicate the stuff that is common.
I just think that most of the information of this type that we have accumulated when we were babies is just not present in text, in any description, essentially.
I mean, that's the 16,000 hours of wake time of a four-year-old and 10 to the 15 bytes, you know, going through vision, just vision, right? There is a similar bandwidth, you know, of touch and a little less through audio. And then text doesn't, language doesn't come in until like, you know, a year in life. And by the time you are nine years old, you've learned everything.
about gravity, you know, about inertia, you know, about gravity, you know, the stability, you know, you know, about the distinction between animate and inanimate objects, you know, by 18 months, you know, about like why people want to do things and you help them if they can't, you know, I mean, there's a lot of things that you learn mostly by observation, really not even through interaction.
In the first few months of life, babies don't really have any influence on the world. They can only observe, right? And you accumulate a gigantic amount of knowledge just from that. So that's what we're missing from current AI systems.
Right. So because of the autoregressive prediction, every time an LLM produces a token or a word, there is some level of probability for that word to take you out of the set of reasonable answers. And if you assume, which is a very strong assumption, that the probability of such error is that those errors are independent across a sequence of tokens being produced.
What that means is that every time you produce a token, the probability that you stay within the set of correct answers decreases, and it decreases exponentially.
Yeah. And that drift is exponential. It's like errors accumulate, right? So the probability that an answer would be nonsensical increases exponentially with the number of tokens.
No, it's basically a struggle against the curse of dimensionality. So the way you can correct for this is that you fine-tune the system by having it produce answers for all kinds of questions that people might come up with. And people are people, so a lot of the questions that they have are very similar to each other, so you can probably cover 80% or whatever.
of questions that people will ask by collecting data. And then you fine-tune the system to produce good answers for all of those things. And it's probably going to be able to learn that because it's got a lot of capacity to learn. But then there is... you know, the enormous set of prompts that you have not covered during training. And that set is enormous.
Like within the set of all possible prompts, the proportion of prompts that have been used for training is absolutely tiny. It's a tiny, tiny, tiny subset of all possible prompts. And so the system will behave properly on the prompts that has been either trained, pre-trained or fine-tuned.
But then there is an entire space of things that it cannot possibly have been trained on because the number is gigantic. So whatever training the system has been subject to to produce appropriate answers, you can break it by finding out a prompt that will be outside of the set of prompts it's been trained on, or things that are similar, and then it will just spew complete nonsense.
I mean, people have come up with things where you put essentially a random sequence of characters in a prompt, and that's enough to kind of throw the system into a mode where it's going to answer something completely different than it would have answered without this. So that's a way to jailbreak the system, basically go outside of its conditioning, right?
Yeah, some people have done things like you write a sentence in English or you ask a question in English and it produces a perfectly fine answer. And then you just substitute a few words. by the same word in another language. And all of a sudden, the answer is complete nonsense.
So the problem is that there is a long tail. Yes. This is an issue that a lot of people have realized in social networks and stuff like that, which is there's a very, very long tail of things that people will ask. And you can fine-tune the system for the 80% or whatever of the things that most people will ask.
And then this long tail is so large that you're not going to be able to fine-tune the system for all the conditions. And in the end, the system ends up being kind of a giant lookup table, right, essentially, which is not really what you want. You want systems that can reason, certainly that can plan. So the type of reasoning that takes place in LLM is very, very primitive.
Showing 161–180 of 384 · page 9 of 20
← Previous
Next →