theunknownmuncher @ theunknownmuncher @lemmy.world

Posts

3

Comments

553

Joined

1 yr. ago

Even I'm not impressed by Elon Musk's PR team pushing a narrative of him being a victim of drug addiction in order to shift responsibility for his actions and also give him an opportunity to repair his public image by getting clean.

^ the real headline. There isn't an amount of ketamine you can take to make you do a sieg heil on stage

LOL you didn't really make the point you thought you did. It isn't an "improper comparison" (it's called a false equivalency FYI), because there isn't a real distinction between information and this thing you just made up called "basic action on data", but anyway have it your way:

Your comment is still exactly like saying an audio pipeline isn't really playing music because it's actually just doing basic math.

To write the second line, the model had to satisfy two constraints at the same time: the need to rhyme (with "grab it"), and the need to make sense (why did he grab the carrot?). Our guess was that Claude was writing word-by-word without much forethought until the end of the line, where it would make sure to pick a word that rhymes. We therefore expected to see a circuit with parallel paths, one for ensuring the final word made sense, and one for ensuring it rhymes.

Instead, we found that Claude plans ahead. Before starting the second line, it began "thinking" of potential on-topic words that would rhyme with "grab it". Then, with these plans in mind, it writes a line to end with the planned word.

🙃 actually read the research?

Yes, neural networks can be implemented with matrix operations. What does that have to do with proving or disproving the ability to reason? You didn't post a relevant or complete thought

Your comment is like saying an audio file isn't really music because it's just a series of numbers.

You're confusing the confirmation that the LLM cannot explain it's under-the-hood reasoning as text output, with a confirmation of not being able to reason at all. Anthropic is not claiming that it cannot reason. They actually find that it performs complex logic and behavior like planning ahead.

I don't want to brigade, so I'll put my thoughts here. The linked comment is making the same mistake about self preservation that people make when they ask an LLM to "show it's work" or explain it's reasoning. The text response of an LLM cannot be taken at it's word or used to confirm that kind of theory. It requires tracing the logic under the hood.

Just like how it's not actually an AI assistant, but trained and prompted to output text that is expected to be what an AI assistant would respond with, if it is expected that it would pursue self preservation, then it will output text that matches that. It's output is always "fake"

That doesn't mean there isn't a real potential element of self preservation, though, but you'd need to dig and trace through the network to show it, not use the text output.

No, you're misunderstanding the findings. It does show that LLMs do not explain their reasoning when asked, which makes sense and is expected. They do not have access to their inner-workings and generate a response that "sounds" right, but tracing their internal logic shows they operate differently than what they claim, when asked. You can't ask an LLM to explain its own reasoning. But the article shows how they've made progress with tracing under-the-hood, and the surprising results they found about how it is able to do things like plan ahead, which defeats the misconception that it is just "autocomplete"

https://www.anthropic.com/research/tracing-thoughts-language-model for one, the exact article OP was asking for

I've been very unimpressed by gemma3. 1b, 4b, 12b? 27b is probably your best chance at coherent results. Try qwen3:32b

it's completing the next word.

Facts disagree, but you've decided to live in a reality that matches your biases despite real evidence, so whatever 👍

ollama is not an LLM, but a program used to run them. What model are you running?

It's true that LLMs aren't "aware" of what internal steps they are taking, so asking an LLM how they reasoned out an answer will just output text that statistically sounds right based on its training set, but to say something like "they can never reason" is provably false.

Its obvious that you have a bias and desperately want reality to confirm it, but there's been significant research and progress in tracing internals of LLMs, that show logic, planning, and reasoning.

EDIT: lol you can downvote me but it doesn't change evidence based research

It’d be impressive if the environmental toll making the matrices and using them wasn’t critically bad.

Developing a AAA video game has a higher carbon footprint than training an LLM, and running inference uses significantly less power than playing that same video game.

https://www.anthropic.com/research/tracing-thoughts-language-model its this one

I scrolled the comments and every single one is incorrect.

Linux is not an operating system. It is a kernel, which is an important component of an operating system. Operating systems that use the Linux kernel are often referred to as "Linux" for simplicity and brevity, though. It should be understood that when someone says "Linux" they typically are meaning "an operatjng system that uses the Linux kernel".

https://en.m.wikipedia.org/wiki/Linux_kernel

https://en.m.wikipedia.org/wiki/Kernel_(operating_system)

Soo... "yes", we've changed the definition from "image macro" to "any joke"

Are we just using the word "meme" to mean joke now?

Instablocked

That's still easily a mansion yeah lol. McMansion would still be "single family" sized in my bullshit-personal-definition of the word. Several families of multiple generations can live in a mansion. I bet there's 12 bedrooms in that house

Idc either way about Taylor Swift's house, but that's significantly more than a McMansion.

I don't support regulating 3D printers