Achieving AI-style reasoning without an LLM

44 points by edwardchalk 6 hours ago on hackernews | 29 comments

Never seen that one before:

"Insufficient Storage

The method could not be performed on the resource because the server is unable to store the representation needed to successfully complete the request. There is insufficient free space left in your storage allocation.

Additionally, a 507 Insufficient Storage error was encountered while trying to use an ErrorDocument to handle the request."

: chrisjj | 3 hours ago
This is what you get when you employ a stochastic parrot to deliver a 507.

jstanley | 4 hours ago

I can't see where you can try this out, so at the moment it's a lot of claims and no real evidence. Also the text feels like it was written by an LLM.

If it's really such a small model why not provide a web interface where we can test it for ourselves?

This feels like high risk of being crackpottery.

SOLAR_FIELDS | 3 hours ago

It was definitely written by an LLM, the entire article is full of “it’s not X, it’s Y” overconfident truisms

: prmph | 3 hours ago
Yep:
> The relation between them always has to be supplied, and supplying it is what the system’s logic is.
100% sure this is Claude's recent writing style at work

srdjanr | 3 hours ago

And all illustrations have the AI look (they're not AI images, but AI-generated SVG or Powerpoint or something)

suddenlybananas | 4 hours ago

It's really a nitpick but putting a big, obvious AI generated slop photo at the top of your post is a signal for bad quality content. I would recommend to avoid doing it.

: tarkin2 | 4 hours ago
And using AI's favourite phrase, a deep dive, is also offputting.
(I mean, is he grading the dive?)
: jpnc | 3 hours ago
I wouldn't even mind it if it weren't so blatantly lazy (lazier). It's always that off-putting overly busy default look. Like, you couldn't even be bothered to ask for some refinement.

iterance | 4 hours ago

The associated paper is (I will say generously) not forthcoming: https://zenodo.org/records/23526702

I can also find no working model. I expect this may be disregarded for now.

8474_s | 4 hours ago

> without a LLM https://github.com/pcoz/decisionator

2. Obtain an OpenAI API Key

    Sign up at OpenAI
    Create an API key

jstanley | 4 hours ago

I'm pretty sure that's a different project

8474_s | 4 hours ago

Its the only repo by the author(Edward Chalk) that focuses on decision making models? Its his github account linked from the front page.

: jstanley | 3 hours ago
I'm pretty sure it's a different project. It's not that inconceivable that the same author has done more than one project in a related area, especially if the one you found on github is obviously different to the one described here.

vintagedave | 4 hours ago

> A large language model is trained to predict the next word of a piece of text. … simply asking a model to “think step by step” makes its answers better.

I thought both these statements were no longer held to be broadly true? At least in big lab or frontier models.

asdfsa32 | 4 hours ago

Only the meaning of "next" and "word" as well as "next word" has become more complicated, otherwise it still holds true as a general mechanism.

nayroclade | 4 hours ago

Next token prediction is still how pre-training works, but that's a relatively small part of the whole training run nowadays. Most of the time is spent in post-training reinforcement learning scenarios, where models are scored based on an evaluation of their ability to complete a task, not whether any specific token correctly predicts a known next token.

Generally, anyone talking about next token prediction being some limiting factor of LLM capability is a good reason to ignore them, as they haven't updated their understanding of LLMs since 2023 or so.

chrisjj | 3 hours ago

> Next token prediction is still how pre-training works, but that's a relatively small part of the whole training run nowadays

Only if you call 90% small.

No-one is claiming <50%.

cubefox | 2 hours ago

It's only about 10% of total compute capacity. https://x.com/EugeneNg/status/2099315982959616369

: didroe | an hour ago
I think there's a question of semantics here. RL is way more expensive in terms of compute, as you have to generate a significant amount of output before you can judge whether it's good or bad. So compute is one angle, but another is how much impact RL has on the weights vs pre-training
: chrisjj | 59 minutes ago
I cannot see how cost is relevent. What we're discussing is impact.

asdf88990 | 2 hours ago

All that happens in reinforcement learning and everything from pre-training to generation, including the last token, at the end is about adjusting the probability of the next token given the sequence.

Anyone who thinks reinforcement learning changes how the generation works hasn’t worked on inference engines and you can dismiss them as inexperienced and misguided.

didroe | an hour ago

I think you're conflating prediction and training. The models are auto-regressive so they always predict the next token.

cubefox | 4 hours ago

This might have been written by someone suffering from AI psychosis.

glimshe | 3 hours ago

When I read the title, I thought this was a joke and the article would just say: "Think by yourself".

Although that's arguably way superior to AI-style reasoning.

bvan | 3 hours ago

I want to believe… but..

MrOrelliOReilly | 3 hours ago

Chicanery! As others have stated, this is total AI slop. How do these things get upvoted?

anentropic | 3 hours ago

Ironically it seems to have been made by LLM ...?

zefir | 3 hours ago

As a Prolog enthusiast and someone who had followed Newell & Simon's SOAR work etc., this was intriguing. There are some respositories that seem related: https://github.com/pcoz/operational-representation-of-system... But, it is disappointing that the summary does seem to be AI-generated slop and I can't find code reproducing the claims as described.