I can also find no working model. I expect this may be disregarded for now.
vintagedave 2 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.
nayroclade 2 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.
asdf88990 20 minutes 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.
chrisjj 2 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 the meaning of "next" and "word" as well as "next word" has become more complicated, otherwise it still holds true as a general mechanism.
kangalioo 3 hours ago [-]
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 2 hours ago [-]
This is what you get when you employ a stochastic parrot to deliver a 507.
glimshe 2 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.
zefir 2 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.
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 1 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.
MrOrelliOReilly 2 hours ago [-]
Chicanery! As others have stated, this is total AI slop. How do these things get upvoted?
bvan 2 hours ago [-]
I want to believe… but..
4 hours ago [-]
anentropic 2 hours ago [-]
Ironically it seems to have been made by LLM ...?
cubefox 2 hours ago [-]
This might have been written by someone suffering from AI psychosis.
suddenlybananas 3 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 3 hours ago [-]
And using AI's favourite phrase, a deep dive, is also offputting.
(I mean, is he grading the dive?)
jpnc 2 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.
Rendered at 13:14:30 GMT+0000 (UTC) with Wasmer Edge.
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.
> 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
I can also find no working model. I expect this may be disregarded for now.
I thought both these statements were no longer held to be broadly true? At least in big lab or frontier models.
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.
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.
Only if you call 90% small.
No-one is claiming <50%.
"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."
Although that's arguably way superior to AI-style reasoning.
2. Obtain an OpenAI API Key
(I mean, is he grading the dive?)