This led to the natural question: can gzip do language modeling? (...). Here’s some real, unedited output after priming it on tiny Shakespeare:
gzipt --corpus data/tinyshakespeare.txt --prompt $'MENENIUS:\n' --length 200
MENENIUS:
'Though all at once canq
MARCIUS:
Pray now, nocamest thou to a morsel.
LARTIUS:
Hence, and
I' the end admire, where G
again; and after it ag .
Now thinking back, what's missing so that gzip could unwind the correct body of work from Shakespeare is just a correct sequence of bytes. One way to arrive at this is by just getting the body of work and doing the inverse, compressing it to get that golden sequence of bytes.
The other is what thinking does, it tries to predict the missing sequence of tokens from a high entropy source, the prompt, in order to increase the likelihood of correctly decompressing the desired results from its weights.
How can things be compressed without losing information or structure?
Like for text, what would that involve? How do you compress a string or multi-line string without losing information and hopefully structure (paragraphs, would it be like replacing periods and the following space with just sticking the starting capitalized letter of the following word to the previous sentence's last letter and when it decompresses theres some kind of note that converts that back into the. First letter of the next sentence
How can things be compressed without losing information or structure?
Because the initial content is rarely the most efficient representation, so it's possible to store fewer bytes that can deterministically be converted into the original.
Like for text, what would that involve?
Most compression algos don't care what information you're compressing. All they see (all they need to see) is bytes. It ends up being way more sophisticated than removing repeated periods and whitespace.
Like if you had eight boxes of loose lego, simply shuffling around the boxes wouldn't give you much in the way of reducing the space the legos take up. but if you took the legos (bytes) themselves out of the boxes, you end up saving a lot more space.
It reminds me of "At the time we drew boxes labeled 'perception', 'cognition' with arrows between them." An imprecise quote that I can't place.
I guess my box labelled 'subconsciousness' is trying to say that low-level mechanisms that give rise to the observed cognitive phenomena might have nothing to do with neat boxes.
McDermott's A Critique of Pure Reason pretty much captured all of the misgivings I had about "Good Old-Fashioned Artificial Intelligence", which was slightly unfortunate as I was trying to complete a PhD in that very area at the time (around 1990 or so...)
Most humans have weak meta-cognition, a large percentage doesn't have verbal thoughts.
Meta-cognition makes sense in a dynamic and updatable and modular system, for example I can monitor thoughts coming from my amygdala with my prefrontal cortex and then adjust how I process these thoughts.
In LLMs it makes zero sense, even if you feed the output of one model into another, there is no way they can update the heuristics behind how those were computed.
Interestingly that is not what we got, but maybe we should loop at architectures like this again? The JEPA loop is interesting, but might fail for the in-flexibility of the component ordering
How relevant is this fast/slow thinking thing with regards to current frontier models?
I know a large organization who's built their AI framework completely around this concept, and I feel that it's not really meaningful concept with the capabilities of current models.
That's because an LLM thinks in terms of language, while we think in a different way, then convert the ideas to language.
It can be said that language is a tool for the serialization (writing) and deserialization (reading) of human ideas. It is also an incredible useful and powerful tool by itself.
This last sentence has been proved true by LLMs themselves.
However, since it is working on the serialized version of ideas, I agree with you in that's not the optimal way to think and something not serialized (maybe world models) can be invented that's better for thinking.
All this in no way diminishes the usefulness of language and of automated language generation.
> That's because an LLM thinks in terms of language, while we think in a different way, then convert the ideas to language
Do we? I just learned from a speaker[1] that we literally need words to recognize emotions. People who have a poor vocabulary have lower emotional intelligence because without being able to attach a word to an emotion, the brain is unable to recognize & process it.
[1] Dude seemed to be knowledgeable about the subject. He's a specialized trainer, should be educated in this exact field. So hopefully I'm not lying to anyone here :)
'fast' means executing a policy, that is, a state-action mapping. A trained RL model does this.
'slow' means making one or several action-dependent forecasts, evaluating the expected value of the outcomes, and making a decision based on that.
Neither map exactly to the situation with LLMs, but very roughly, the first is analogous to trained classifiers and the second to reasoning models.
The analogy breaks down, since each instance of token being produced is an example of a policy execution (system 1), and reasoning is just stringing lots of these together. But there are those who argued, before LLMs, that system 2 is just "policy composition" anyway...
No clue what’s the consensus on this but my internal mental model is absolutely that LLM AI is pure fast mode, no slow mode. The “reasoning” loops are an attempt to mimic the slow mode but ultimately it doesn’t really work. I’m curious about the recent maths advances though, they seem to possibly challenge this.
Structurally speaking we learn nothing like AI, we don't use vast amounts of information to pick up completely new skills. We also make decisions by using prior knowledge and emotions.The latter part is important, Thinking fast and slow cannot operate in a world of AIs as they stand today unless we are willing to grant them rights — because you have to teach them to make decisions based on all kinds of emotions — which is tricky at best.
System 1/2 is the pop version, but the fast/slow distinction is prevalent in both RL and computational cognitive science, sometimes going under different names: procedural/deliberative, model-free/model-based, automatic/controlled, associative/rule-based, autonomous/algorithmic, etc.
It's indeed a terrible idea - as in, it's great. You get benefits of cross-marketing: you ride on a popularity of a well-known book, and as you also drive more sales of it, even if you don't have a deal and don't benefit from that directly, you strengthen the loop and solidify your brand.
This choice doesn't really constrain what the organization can do, either. Pop-sci books have plenty of wiggle room in interpretation, and afford a lot of "you're holding it wrong" dismissals of criticism, that with a bit of clever copywriting, the organization can do absolutely anything and still claim it's embodying the framework/theory of the book.
It looks like a lot like how data bases query optimizers work, with the exception that in the paper there is also a learning/memory component that conditions the evaluation of the answer provided by the first model.
This is still a great paper, but it's missing the second axis of the quadric -- if the only two options are thinking fast or thinking about thinking, that leaves no room for thinking slow yet deliberately, AKA selfconsciousness. See https://www.gutenberg.org/cache/epub/4280/pg4280-images.html for details
I do wonder if any of these folks ever got a chance to try this at one of the big labs, tho...
This has already been solved by GPT 5 Adaptive reasoning. A single model that knows when to reason or not based on a thinking parameter we provide (like xhigh). What’s the relevancy to post it today?
* The person who posted it likely posted it not as an out-of-date paper but as an interesting idea. Your comment ignores the idea and focuses on what you're calling its out-of-dateness.
* You say "this has been solved" without defining what "this" is.
* Your description of the solution -- different effort levels -- seems to indicate that you misunderstand the idea that the paper is proposing. If I understand their proposal, it's that the system itself decides how to reason based on the nature of the problem it faces, given the model's world model and past experience. "Effort" isn't so much the issue as types of effort using different systems, modeled specifically after Kahneman's idea of fast and slow thinking.
* The title is an allusion to a book by Daniel Kahneman. The brisk dismissal without acknowledging the idea or the history doesn't leave a good impression, even if I'm mistaken and you're right.
In short, Hacker News readers tend to reward depth and detail (the FAQ specifically encourages thoughtful contributions and explicitly discourages dismissal). Your comment doesn't provide them, and it appears to make a mistake that further undermines its value as a contribution to discussion.
> This has already been solved by GPT 5 Adaptive reasoning. A single model that knows when to reason or not based on a thinking parameter we provide (like xhigh). What’s the relevancy to post it today?
Tell me you didn't read Daniel Khaneman's book without telling me you didn't read Daniel Khaneman's book.
There was this post a few days ago https://news.ycombinator.com/item?id=49797323
It had this to say in the linked post:
Now thinking back, what's missing so that gzip could unwind the correct body of work from Shakespeare is just a correct sequence of bytes. One way to arrive at this is by just getting the body of work and doing the inverse, compressing it to get that golden sequence of bytes.
The other is what thinking does, it tries to predict the missing sequence of tokens from a high entropy source, the prompt, in order to increase the likelihood of correctly decompressing the desired results from its weights.
How can things be compressed without losing information or structure?
Like for text, what would that involve? How do you compress a string or multi-line string without losing information and hopefully structure (paragraphs, would it be like replacing periods and the following space with just sticking the starting capitalized letter of the following word to the previous sentence's last letter and when it decompresses theres some kind of note that converts that back into the. First letter of the next sentence
You analyze the frequency of combinations of bytes, then replace those with high frequency with pointers to a single instance.
Because the initial content is rarely the most efficient representation, so it's possible to store fewer bytes that can deterministically be converted into the original.
Most compression algos don't care what information you're compressing. All they see (all they need to see) is bytes. It ends up being way more sophisticated than removing repeated periods and whitespace.
Like if you had eight boxes of loose lego, simply shuffling around the boxes wouldn't give you much in the way of reducing the space the legos take up. but if you took the legos (bytes) themselves out of the boxes, you end up saving a lot more space.
It reminds me of "At the time we drew boxes labeled 'perception', 'cognition' with arrows between them." An imprecise quote that I can't place.
I guess my box labelled 'subconsciousness' is trying to say that low-level mechanisms that give rise to the observed cognitive phenomena might have nothing to do with neat boxes.
You mean "Artificial Intelligence meets Natural Stupidity" by Drew McDermott
https://dl.acm.org/doi/pdf/10.1145/1045339.1045340
McDermott's A Critique of Pure Reason pretty much captured all of the misgivings I had about "Good Old-Fashioned Artificial Intelligence", which was slightly unfortunate as I was trying to complete a PhD in that very area at the time (around 1990 or so...)
2 replies →
Donald Broadbent drew a lot of boxes in the 50s/60s (https://en.wikipedia.org/wiki/Broadbent's_filter_model_of_at...). There have been plenty of critics of this tendency, I recall some calling it 'boxology' rather than psychology.
[flagged]
Most humans have weak meta-cognition, a large percentage doesn't have verbal thoughts.
Meta-cognition makes sense in a dynamic and updatable and modular system, for example I can monitor thoughts coming from my amygdala with my prefrontal cortex and then adjust how I process these thoughts.
In LLMs it makes zero sense, even if you feed the output of one model into another, there is no way they can update the heuristics behind how those were computed.
Interestingly that is not what we got, but maybe we should loop at architectures like this again? The JEPA loop is interesting, but might fail for the in-flexibility of the component ordering
How relevant is this fast/slow thinking thing with regards to current frontier models?
I know a large organization who's built their AI framework completely around this concept, and I feel that it's not really meaningful concept with the capabilities of current models.
That's because an LLM thinks in terms of language, while we think in a different way, then convert the ideas to language. It can be said that language is a tool for the serialization (writing) and deserialization (reading) of human ideas. It is also an incredible useful and powerful tool by itself. This last sentence has been proved true by LLMs themselves. However, since it is working on the serialized version of ideas, I agree with you in that's not the optimal way to think and something not serialized (maybe world models) can be invented that's better for thinking. All this in no way diminishes the usefulness of language and of automated language generation.
> That's because an LLM thinks in terms of language, while we think in a different way, then convert the ideas to language
Do we? I just learned from a speaker[1] that we literally need words to recognize emotions. People who have a poor vocabulary have lower emotional intelligence because without being able to attach a word to an emotion, the brain is unable to recognize & process it.
[1] Dude seemed to be knowledgeable about the subject. He's a specialized trainer, should be educated in this exact field. So hopefully I'm not lying to anyone here :)
3 replies →
'fast' means executing a policy, that is, a state-action mapping. A trained RL model does this.
'slow' means making one or several action-dependent forecasts, evaluating the expected value of the outcomes, and making a decision based on that.
Neither map exactly to the situation with LLMs, but very roughly, the first is analogous to trained classifiers and the second to reasoning models.
The analogy breaks down, since each instance of token being produced is an example of a policy execution (system 1), and reasoning is just stringing lots of these together. But there are those who argued, before LLMs, that system 2 is just "policy composition" anyway...
Wouldn't you need a classifier to even decide if it is system 1 or 2? How capable does this classier need to be?
1 reply →
No clue what’s the consensus on this but my internal mental model is absolutely that LLM AI is pure fast mode, no slow mode. The “reasoning” loops are an attempt to mimic the slow mode but ultimately it doesn’t really work. I’m curious about the recent maths advances though, they seem to possibly challenge this.
Its just hype talk. Slow mode is conscious in humans, fast is subconscious, so we need to discuss AI consciousness to talk about system 2 thinking.
So the entire debate is fubar.
You can ask a model for output directly and stop, or you can recursively ask it to keep refining the output.
That seems to fit the fast vs slow model of human thought reasonably well.
> You can ask a model for output directly and stop
That’s still several orders of magnitudes too slow to fit fast vs slow. Think of 30ms vs 3-4 seconds to get an idea of what we’re talking about here
5 replies →
Not relevant at all. Its a way to hype.
Structurally speaking we learn nothing like AI, we don't use vast amounts of information to pick up completely new skills. We also make decisions by using prior knowledge and emotions.The latter part is important, Thinking fast and slow cannot operate in a world of AIs as they stand today unless we are willing to grant them rights — because you have to teach them to make decisions based on all kinds of emotions — which is tricky at best.
> we don't use vast amounts of information to pick up completely new skills.
Except, we do.
Seems like a terrible idea in the first place to build an entire organization around a single pop-sci book, but that’s just me.
System 1/2 is the pop version, but the fast/slow distinction is prevalent in both RL and computational cognitive science, sometimes going under different names: procedural/deliberative, model-free/model-based, automatic/controlled, associative/rule-based, autonomous/algorithmic, etc.
It's indeed a terrible idea - as in, it's great. You get benefits of cross-marketing: you ride on a popularity of a well-known book, and as you also drive more sales of it, even if you don't have a deal and don't benefit from that directly, you strengthen the loop and solidify your brand.
This choice doesn't really constrain what the organization can do, either. Pop-sci books have plenty of wiggle room in interpretation, and afford a lot of "you're holding it wrong" dismissals of criticism, that with a bit of clever copywriting, the organization can do absolutely anything and still claim it's embodying the framework/theory of the book.
[dead]
[dead]
It looks like a lot like how data bases query optimizers work, with the exception that in the paper there is also a learning/memory component that conditions the evaluation of the answer provided by the first model.
Given how LLMs access compressed knowledge from their model weights, the similarities make sense
[flagged]
At least this is written before ChatGPT.
Trying to get LLMs to 'think about their thinking' is my daily struggle. This paper nails why it's so critical.
If I recall correctly, all that fast and slow business has been debunked as yet more non-replicable pop psychology.
I shouldn't be surprised that it shows up in a screed on AI
This is still a great paper, but it's missing the second axis of the quadric -- if the only two options are thinking fast or thinking about thinking, that leaves no room for thinking slow yet deliberately, AKA selfconsciousness. See https://www.gutenberg.org/cache/epub/4280/pg4280-images.html for details
I do wonder if any of these folks ever got a chance to try this at one of the big labs, tho...
Isn't system 2 by itself semantically means thinking by thinking
[flagged]
> submitted Oct 5 2021
(In case people miss that before discussion)
Updated, thanks!
[dead]
[flagged]
[dead]
[flagged]
This has already been solved by GPT 5 Adaptive reasoning. A single model that knows when to reason or not based on a thinking parameter we provide (like xhigh). What’s the relevancy to post it today?
edit: why is this downvoted?
It's being downvoted, I think, for a few reasons:
* The person who posted it likely posted it not as an out-of-date paper but as an interesting idea. Your comment ignores the idea and focuses on what you're calling its out-of-dateness.
* You say "this has been solved" without defining what "this" is.
* Your description of the solution -- different effort levels -- seems to indicate that you misunderstand the idea that the paper is proposing. If I understand their proposal, it's that the system itself decides how to reason based on the nature of the problem it faces, given the model's world model and past experience. "Effort" isn't so much the issue as types of effort using different systems, modeled specifically after Kahneman's idea of fast and slow thinking.
* The title is an allusion to a book by Daniel Kahneman. The brisk dismissal without acknowledging the idea or the history doesn't leave a good impression, even if I'm mistaken and you're right.
In short, Hacker News readers tend to reward depth and detail (the FAQ specifically encourages thoughtful contributions and explicitly discourages dismissal). Your comment doesn't provide them, and it appears to make a mistake that further undermines its value as a contribution to discussion.
> it's that the system itself decides how to reason based on the nature of the problem it faces, given the model's world model.
do you even know how adaptive reasoning works?
2 replies →
> This has already been solved by GPT 5 Adaptive reasoning. A single model that knows when to reason or not based on a thinking parameter we provide (like xhigh). What’s the relevancy to post it today?
Tell me you didn't read Daniel Khaneman's book without telling me you didn't read Daniel Khaneman's book.
Asking earnestly, I don’t know what you mean by this reply. I know what system 1 and 2 is. But this has already been solved using same model.
5 replies →
Surely that is obvious
2021. Please remember the rule of HN to add the year if it’s not actual.
Good luck linking to that rule.