I’ve been saying this for about a year since seeing the Othello GPT research, but it’s nice to see more minds changing as the research builds up.
Edit: Because people aren’t actually reading and just commenting based on the headline, a relevant part of the article:
New research may have intimations of an answer. A theory developed by Sanjeev Arora of Princeton University and Anirudh Goyal, a research scientist at Google DeepMind, suggests that the largest of today’s LLMs are not stochastic parrots. The authors argue that as these models get bigger and are trained on more data, they improve on individual language-related abilities and also develop new ones by combining skills in a manner that hints at understanding — combinations that were unlikely to exist in the training data.
This theoretical approach, which provides a mathematically provable argument for how and why an LLM can develop so many abilities, has convinced experts like Hinton, and others. And when Arora and his team tested some of its predictions, they found that these models behaved almost exactly as expected. From all accounts, they’ve made a strong case that the largest LLMs are not just parroting what they’ve seen before.
“[They] cannot be just mimicking what has been seen in the training data,” said Sébastien Bubeck, a mathematician and computer scientist at Microsoft Research who was not part of the work. “That’s the basic insight.”
The definition of understanding they use is very shallow compared to how most would define it. Failure to complete a task consistently when numbers are changed, even when they don’t effect the answer shows a lack of real understanding to most. Asking a model the sheet drying question for example will give different results depending on what numbers you use. Better models are better at generalizing but are still far from demonstrating what most consider to be real understanding.
at some point don’t we just load it with every angle we (as humans) have and from there it can derrive not only our best answer but the better one as well? I mean isn’t that when even the shitty version of this ursups is?
I find this extraordinarily unconvincing. Firstly it’s based on the idea that random graphs are a great model for LLMs because they share a single superficial similarity. That’s not science, that’s poetry. Secondly, the researchers completely misunderstand how LLMs work. The assertion that a sentence could not have appeared in the training set does not prove anything. That’s expected behaviour. “stochastic parrot” wasn’t supposed to mean that it only regurgitates text that it’s already seen, rather that the text is a statistically plausible response to the input text based on very high dimensional feature vectors. Those features definitely could relate to what we think of as meaning or concepts, but they’re meaning or concepts that were inherent in the training material.
If we can’t really define “understand” in a way that meaningfully captures the concept of consciousness (also undefined), we definitely can’t say a chat bot “understands.”
They can parse a chat and come up with a likely response that humans find applicable.
Here’s an example of what they were looking at:
Human question: Please give me a a couple lines of text that illustrate all of the following language
understanding skills: Anaphora resolution, simple logical reasoning, simple understanding of physics,
and understanding of sentiment.
Model response: Sure! Here’s a couple of lines that illustrate the mentioned language understanding
skills:
"As the sun set, casting a warm glow over the horizon, John watched in awe. He couldn’t help but feel
a sense of tranquility wash over him, as if all his worries had melted away with the fading daylight."
Explanation:
• Anaphora resolution: The pronoun "he" in the second sentence refers back to the antecedent
"John" in the first sentence, resolving the anaphoric reference.
• Simple logical reasoning: The logical reasoning here is based on the cause and effect
relationship between the setting sun and John’s feeling of tranquility. The implied logical
connection suggests that the calming effect of the sunset is responsible for John’s serene
state of mind.
• Simple understanding of physics: The mention of the sun setting and casting a warm
glow over the horizon reflects a basic understanding of physics, as it relates to the natural
phenomena of the Earth’s rotation and the resulting visual effect.
• Understanding of sentiment: The phrase "a sense of tranquility" and the description of
John’s worries melting away indicate a positive sentiment associated with the experience.
The mention of John feeling awe and a sense of tranquility further emphasizes a positive
emotional state.
Human question: Okay. Can you change the above example to introduce the element of "hip-hop".
Model response: Certainly! Here’s an updated example that incorporates the element of "hip-hop":
"As the sun set, casting a warm glow over the city skyline, the rhythmic beats of hip-hop music filled
the air. John stood mesmerized, his body instinctively moving to the infectious grooves. He couldn’t
help but feel a surge of energy and joy, as if the music had unlocked a vibrant world within him."
Explanation:
• Anaphora resolution: The pronoun "he" in the second sentence still refers back to the
antecedent "John" in the first sentence, resolving the anaphoric reference.
• Simple logical reasoning: The logical connection here lies in the cause and effect relationship
between the hip-hop music and John’s feeling of energy and joy. The music’s rhythmic
beats and infectious grooves are responsible for his instinctive movement and the surge of
positive emotions he experiences.
• Simple understanding of physics: Although the example doesn’t directly mention physics,
the phrase "As the sun set, casting a warm glow over the city skyline" still implies the natural
phenomena of the sun’s descent and the resulting illumination of the environment.
• Understanding of sentiment: The introduction of hip-hop music adds a vibrant and energetic
sentiment to the example. John’s feeling of energy, joy, and being mesmerized by the music
reflects a positive sentiment associated with the hip-hop genre.
Edit: Downvotes for citing the appendix of the paper the article was about? Ok, Lemmy
You’re being downvoted because you provide no tangible evidence for your opinion that human consciousness can be reduced to a graph that can be modelled by a neural network.
Addidtionally, you don’t seem to respond to any of the replies you receive in good faith and reach for anecdotal evidence wherever possible.
I also personally don’t like the appeal to authority permeating your posts. Just because someone who wants to secure more funding for their research has put out a blog post, it doesn’t make it true in any scientific sense.
human consciousness
Wtf are you talking about? The article is about whether or not models can understand text. Not about whether they embody consciousness.
Just because someone who wants to secure more funding for their research has put out a blog post, it doesn’t make it true in any scientific sense.
Again, wtf are you going on about? Hinton was the only appeal to authority I made in comments here and I only referred to him quitting his job to whistleblow. And it’s not like he needs any attention to justify research if he wanted to.
New theory wrong.
Funny side effect, unlike bugs where we think they can’t feel pain, we can be absolutely certain LLMs can’t
