Yet another Hacker News

Achieving AI-style reasoning without an LLM

39 points edwardchalk 2 hours ago 20 comments

kangalioo 1 hour ago | parent

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 11 minutes ago | parent

[delayed]

jstanley 1 hour ago | parent

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 2 minutes ago | parent

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

suddenlybananas 1 hour ago | parent

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 35 minutes ago | parent

And using AI's favourite phrase, a deep dive, is also offputting.

(I mean, is he grading the dive?)

jpnc 11 minutes ago | parent

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 50 minutes ago | parent

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 40 minutes ago | parent

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

2. Obtain an OpenAI API Key

    Sign up at OpenAI
    Create an API key

jstanley 37 minutes ago | parent

I'm pretty sure that's a different project

8474_s 33 minutes ago | parent

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

vintagedave 31 minutes ago | parent

> 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 29 minutes ago | parent

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 25 minutes ago | parent

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 12 minutes ago | parent

> 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 29 minutes ago | parent

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

glimshe 16 minutes ago | parent

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 15 minutes ago | parent

I want to believe… but..

MrOrelliOReilly 15 minutes ago | parent

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

anentropic 12 minutes ago | parent

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