Elektrine lite

← Feed

@antoinechambertloir@mathstodon.xyz

2026-09-10 18:55 UTC

#Math #AI 12/n This software, Claude Fable 5, is a fairly sophisticated program that belongs to the class of “large language models” (LLM). Basically, this means that it generates text (language) according to probabilistic rules that are sufficiently well crafted that the outcome looks very well written, but still, at the heart, this is a randomly generated text. Of course, there is no hope that a purely random text would be of any use for anybody, so the heart of the work of the LLM engineers was first to make these probabilistic rules particularly well chosen. On can already see this as a remarkable achievement of that kind of technology, but it is important to make two additional observations: - The crafting of these probabilistic rules is obtained by a recent technique in machine learning (reinforcement learning and transformers), that requires, to work properly, an extremly large number of data. To that aim, the AI companies basically scanned every possible literature, and used human workers (in particular from the Global south) to “train” the software. It is for this reason that researchers in artificial intelligence and linguistics coined the term “stochastic parrots”: this software randomly repeats what it has read. - This random text generation does not entail any notion of truth, and even any relation to the actual world. To reach the possibility of doing math, this software now combines text generation with proof verification in the sense discussed earlier. The reason that makes it workable in mathematics is precisely that the mathematical language is well specified, and we have means to assert the validity of a mathematical argument, combined with the performance of proof assistants.

Replies (2)

  • #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.

    Open ##5153662

  • @0xdefec7edcafe@piaille.fr 2026-09-10 21:24

    @antoinechambertloir@mathstodon.xyz I'm sorry to put some salt in this thread; I want to correct one point. Describing LLMs as operating according to "probabilistic rules" and producing "randomly generated text" is misleading. The internal workings of an LLM do not look like a set of logical or probabilistic rules. Given an input, the model _deterministically_ computes scores (called logits) for the possible next tokens (e.g. words, punctuation). These scores are then converted into a probability distribution. A separate decoding step selects the next token, either deterministically or by sampling: that is, by drawing a token according to that probability distribution.

    Open ##5153714