HN
login
Thinking fast and slow in AI: The role of metacognition (2021)arxiv.org
177 points•teleforce•3 days ago•78 comments•
#ai#thinking#role#metacognition#thinking fast

78 comments

gchamonlive3 days ago
There was this post a few days ago https://news.ycombinator.com/item?id=49797323

It had this to say in the linked post:

  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.

sourdecor2 days ago
I don't know how this is related, but it reminds me of how I have always believed compression to be the ultimate sign of intelligence. If you can reduce something while keeping comprehension, you are finding more abstract symbols to represent the information of the original source.
acuozzo2 days ago
> I don't know how this is related

https://en.wikipedia.org/wiki/Hutter_Prize

Obscurity43403 days ago
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

mpalmer3 days ago

    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.

nkmnz3 days ago
You analyze the frequency of combinations of bytes, then replace those with high frequency with pointers to a single instance.
doctoboggan2 days ago
Other than what the others mentioned about finding more efficient representations, you can also compress by pre-agreeing on some common terminology.

In many ways, we are communicating using a compressed channel (words) since we both have pre-agreed on the meaning of these words.

fizzbuzzbarbazz2 days ago
comments would be omitted.

``` th #1 - numbers are just comments ng #2, this has a space at the end information #3 compress #4 letter #5 this has a space at the start and #6 this has a space at the start and end sentence #7 this has a space at the start

How can 1ings be 4ed without losi23 or structure?

Like for text, what would 1at involve? How do you 4 a stri2or multi-line stri2wi1out losi236hopefully structure (paragraphs, would it be like replaci2periods61e followi2space wi1 just sticki21e starti2capitalized5 of 1e followi2word to 1e previous7's last56when it de4es 1eres some kind of note 1at converts 1at back into 1e. First5of the next7 ```

I'm on a phone, so I may have mistakes here, but I'm pretty sure that's shorter than your original text, in bytes, by about (9+18+20+21+12+12+16=108), minus the dictionary size of 51 -- so, 57 bytes shorter, but still containing your full text. With predistributed compressor binaries and a lot of analysis, you can even predistribute a global dictionary for common sequences, and simply specify "xyz0", x, y, and z being 24-bit numbers, or whatever bit size can index into your full reference dictionary, and 0 meaning end-of-file-dictonary. then, assuming the byte sequences in your text above are common enough to be in the 24-bit indexed dictionary, that initial dictionary could be just 22 bytes (21 and a terminator) -- so, 86 bytes shorter than the original, but still containing your original message unaltered. ..assuming i didn't make mistakes in my hand-compression.

red75prime3 days ago
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.

bananaflag3 days ago
You mean "Artificial Intelligence meets Natural Stupidity" by Drew McDermott

https://dl.acm.org/doi/pdf/10.1145/1045339.1045340

arethuza3 days ago
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...)
Phemist3 days ago
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.
creativeSlumber3 days ago
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.

Shorel3 days ago
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.
virgilp3 days ago
> 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 :)

glial2 days ago
'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...

creativeSlumber2 days ago
Wouldn't you need a classifier to even decide if it is system 1 or 2? How capable does this classier need to be?
Retric3 days ago
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.

usernametaken293 days ago
> 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

schainks2 days ago
Not quite. The better analogy for you is the "thinking" setting on your model.
theptip2 days ago
Very relevant. Modern models use CoT to do “slow thinking” and this enables them to achieve much greater performance. You can also turn off thinking and answer directly which is quite similar to “fast thinking”, good at approximate maths, not capable of algorithms, etc.

Of course the shapes of what an AI can do in fast vs slow are quite different.

jhrmnn3 days ago
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.
hoppp3 days ago
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.

arbirk3 days ago
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
hoppp3 days ago
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.

Read the full thread on Hacker News →

Related stories