Elektrine lite

← Feed

@antoinechambertloir@mathstodon.xyz

2026-09-10 19:05 UTC

#Math #AI 13/n This kind LLM technology is called “agentic” because it has the possibility to launch programs that can either be proof assistants that will try to check specific assertions, or other LLM agents that are instructed to counter-reason the arguments of the first one, in the hope of finding limitations of the initial plan. While I know a fair amount of mathematics from my own reading, and my own practice, I am not a specialist of these technologies, I have no idea at all of how these multi-agents are combined, and I may be slightly off here. But one of my objections that I had earlier regarding LLM technology and “intelligence” is that I see no argument for which automatic generation of arguments, possibly looking in various directions at the same time, has anything to do with the stunning phenomenon called intelligence that we, humans, are used to experiment — and that we seem to share with some other living species. My basic objection is that it is up to the builders of those tools to demonstrate by thought, not by experiment, why it should work.

Replies (2)

  • #Math #AI 14/n There is another argument against the principle for this kind of technology that I have learned from the philosopher Walter Dean. Computer science has defined precisely what an algorithm is and given means to evaluate how efficient those algorithms are. Moreover, it has delimited various classes of problems regarding efficiency of the algorithms that can solve them. Two classes are of prominent importance: - Problems for which we know fast algorithms (called P in the computer science jargon); - Problems for which we don't know fast algorithms but for which we have efficient way to check solutions (called NP in that jargon). A hard question in computer science is to prove that the class NP is really larger than the class P, this is what computer scientists believe, but can't prove. The difficulty of some problems in the NP class is at the heart of modern cryptography (hence the whole security of Internet), and if you have heard about quantum computing (or things such as “post-quantum cryptography”), this is because it would make the two classes much closer one from the other, and “breaking” those cryptographic protocols. The relation with my thread is that finding a proof of a theorem is a hard problem of the NP class, even for classes of very simple theorems. Which means that we can reasonably check proofs, as proof assistants do, but that it is very unlikely that there be efficient algorithms to find proofs.

    Open ##5153663

  • @lipsumdev@mathstodon.xyz 2026-09-11 22:21

    @antoinechambertloir@mathstodon.xyz > I see no argument for which automatic generation of arguments, possibly looking in various directions at the same time, has anything to do with the stunning phenomenon called intelligence that we, humans, are used to experiment I will not pretend to understand this stunning phenomenon myself but, you might want to have a look at a recent computational neuroscience book like this one https://neuronaldynamics.epfl.ch/ Neuroscientists have been studying individual neurons for a long time now (and the book describes these models in length). Going from an understanding of the individual neuron to an understanding of billions of them connected is a giant and difficult leap. The book describes one approach that I find rather illuminating (https://neuronaldynamics.epfl.ch/online/Ch17.S2.html), which is due to Hopfield (he got the 2024 Physics Nobel prize for that). I think these (Hopfield networks) are a good introduction to energy-based models and (biological) neural networks. In some sense, I think it gives some intuition on how things can emerge at large scale from local interactions and perceptual senses. (Regarding the relation between logic and energy-based interactions, I also tried to talk about it on my personal blog here https://lipsum.dev/2025-01-1-sat-frustration/). (Now, that is not how LLM work, but that is another topic.)

    Open ##5153712