Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

LLMs use a surprisingly simple mechanism to retrieve some stored knowledge

news.mit.edu

Post reply on HN
Print view View original

81–90 of 156 posts

Re: LLMs use a surprisingly simple mechanism to retrieve some stored knowledge

#81

Post by mikewarot »

I wonder if this relation still holds with newer models that have have even more compute thrown at them?

My intuition is that the structure inherent to language makes Word2Vec possible. Then training on terabytes of human text encoded with Word2Vec + Positional Encoding makes it possible to then have the ability to predict the next encoding at superhuman levels of cognition (while training!).

It's my sense that the bag of words (as input/output method) combined with limited context windows (to make Positional Encoding work) is a huge impedance mismatch to the internal cognitive structure.

Thus I think that given the orders of magnitude more compute thrown at GPT-4 et al, it's entirely possible new forms of representation evolved and remain to be discovered by humans probing through all the weights.

I also think that MemGPT could, eventually, become an AGI because of the unlimited long term memory. More likely, though, I think it would be like the protagonist in Memento[1].

[1] https://en.wikipedia.org/wiki/Memento_(film)

[edit - revise to address question]

Re: LLMs use a surprisingly simple mechanism to retrieve some stored knowledge

#82

Post by FeepingCreature »

erisinger wrote: post #76
vlovich123 wrote: post #72

Earlier quoted context omitted.

As I understand it a local maxima means you’re at a local peak but there may be higher maximums elsewhere. As I read it, transformers are a local maximum in the sense of outperforming all other ML techniques as the AI technique that gets the closest to human intelligence. Can you help my little brain understand the problem by elaborating? Also you may want to chill with the personal attacks.

Not a personal attack. These posters are smarter than I am, just ribbing them about misusing the terminology. "Maxima" is plural, "maximum" is singular. So you would say "a local maximum," or "several local maxima." Not "a local maxima" or, the one that really got me, "getting trapped in local maxima's." As for the rest of it, carry on. Good discussion.

A local maxima, that is, /usr/bin/wxmaxima...

Re: LLMs use a surprisingly simple mechanism to retrieve some stored knowledge

#83

Post by darby_eight »

fspeech wrote: post #53
krainboltgreene wrote: post #44

Earlier quoted context omitted.

> have access to virtually the entire internet It isn't even close to 1% of the internet, much less virtually the entire internet. According to the latest dump, Common Crawl has 4.3B pages, but Google in 2016 estimated there are 130T pages. The difference between 130T and 4.3B is about 130T. Even if you narrow it down to Google's searchable text index it's "100's of billions of pages" and roughly 100P compared to Com…

130T unique pages? That seems highly unlikely as that averages to over 10000 pages for each human being alive. If gp merely wants texts of interest to self as opposed to an accurate snapshot it seems LLMs should be quite capable, one day.

It doesn't seem that hard to believe given how much automatically generated "content" (mostly garbage) there is.

I think a more interesting question is how much information there is on the internet, especially after optimal compression. I'm guessing this is a very difficult question to answer, but also much higher than LLMs currently store.

Re: LLMs use a surprisingly simple mechanism to retrieve some stored knowledge

#84

Post by darby_eight »

CraigJPerry wrote: post #34
ramses0 wrote: post #22

Earlier quoted context omitted.

Is there some sort of "LLM-on-Wikipedia" competition? ie: given "just wikipedia" what's the best score people can get on however these models are evaluated. I know that all the commercial ventures have a voracious data-input set, but it seems like there's room for dictionary.llm + wikipedia.llm + linux-kernel.llm and some sort of judging / bake-off for their different performance capabilities. Or does the training tr…

>> Or does the training truly _NEED_ every book every written + the entire internet + all knowledge ever known by mankind to have an effective outcome? I have the same question. Peter Norvig’s GOFAI Shakespeare generator example[1] (which is not an LLM) gets impressive results with little input data to go on. Does the leap to LLM preclude that kind of small input approach? [1] link should be here because I assumed as…

[dead]

Re: LLMs use a surprisingly simple mechanism to retrieve some stored knowledge

#85

Post by blueboo »

retrofrost wrote: post #48

This is amazing work, but to me it highlights some of the biggest problems in the current AI zeitgeist, we are not really trying to work on any neuron or ruleset that isnt much different from the perceptron thats just a sumnation function. Is it really that suprising that we just see this same structure repeated in the models. Just because feedforward topologies with single neuron steps are the easiest to train and r…

The bitter lesson, my dude. http://www.incompleteideas.net/IncIdeas/BitterLesson.html

If you find a simpler, trainable structure you might be onto something

Attempts to get fancy tried and died

Re: LLMs use a surprisingly simple mechanism to retrieve some stored knowledge

#86

Post by uoaei »

This is the "random linear projections as memorization technique" perspective on Transformers. It's not a new idea per se, but nice to see it fleshed out.

If you dig into this perspective, it does temper any claims of "cognitive behavior" quite strongly, if only because Transformers have such a large capacity for these kinds of "memories".

Re: LLMs use a surprisingly simple mechanism to retrieve some stored knowledge

#87

Post by victorbjorklund »

foobiekr wrote: post #78
visarga wrote: post #51

Earlier quoted context omitted.

> Just because feedforward topologies with single neuron steps are the easiest to train and run on graphics cards does that really make them the actual best at accomplishing tasks? You are ignoring a mountain of papers trying all conceivable approaches to create models. It is evolution by selection, in the end transformers won.

"won" They barely work for a lot of cases (i.e., anything where accuracy matters, despite the bubble's wishful thinking). It's likely that something will sunset them in the next few years.

That is how evolution works. Something wins until something else comes along and win. And so on forever.

Re: LLMs use a surprisingly simple mechanism to retrieve some stored knowledge

#88

Post by erisinger »

FeepingCreature wrote: post #82
erisinger wrote: post #76

Earlier quoted context omitted.

Not a personal attack. These posters are smarter than I am, just ribbing them about misusing the terminology. "Maxima" is plural, "maximum" is singular. So you would say "a local maximum," or "several local maxima." Not "a local maxima" or, the one that really got me, "getting trapped in local maxima's." As for the rest of it, carry on. Good discussion.

A local maxima, that is, /usr/bin/wxmaxima...

Touché...

Re: LLMs use a surprisingly simple mechanism to retrieve some stored knowledge

#89

Post by xanderlewis »

ldjkfkdsjnv wrote: post #66
retrofrost wrote: post #48

This is amazing work, but to me it highlights some of the biggest problems in the current AI zeitgeist, we are not really trying to work on any neuron or ruleset that isnt much different from the perceptron thats just a sumnation function. Is it really that suprising that we just see this same structure repeated in the models. Just because feedforward topologies with single neuron steps are the easiest to train and r…

Cannot understand people claiming we are in a local maxima, when we literally had an ai scientific breakthrough only in the last two years.

Which breakthrough in the last two years are you referring to?

Re: LLMs use a surprisingly simple mechanism to retrieve some stored knowledge

#90

Post by retrofrost »

mikewarot wrote: post #70
Kerb_ wrote: post #62

Earlier quoted context omitted.

You can think chemotherapy is a local maxima for cancer treatment and hope medical research seeks out other options without having the resources to do it yourself. Not all of us have access to the tools and resources to start experimenting as casually as we wish we could.

MNIST and other small and easy to train against datasets are widely available. You can try out anything you like even with a cheap laptop these days thanks to a few decades of Moore's law. It is definitely NOT out of your reach to try any ideas you have. Kaggle and other sites exist to make it easy. Good luck! 8)

My pet project has been trying to use elixir with NEAT or HyperNEAT to try and make a spiking network, then when thats working decently drop some glial interactions I saw in a paper. It would be kinda bad at purely functional stuff, but idk seems fun. The biggest problems are time and having to do a lot of both the evolutionary stuff and the network stuff. But yeah the ubiquity of free datasets does make it easy to train.
Post reply on HN