Apple & LLM reasoning
2024-10-12 16:46:36.108054+02 by Dan Lyke 0 comments
Furthermore, we investigate the fragility of mathematical reasoning in these models and show that their performance significantly deteriorates as the number of clauses in a question increases. We hypothesize that this decline is because current LLMs cannot perform genuine logical reasoning; they replicate reasoning steps from their training data. Adding a single clause that seems relevant to the question causes significant performance drops (up to 65%) across all state-of-the-art models, even though the clause doesn't contribute to the reasoning chain needed for the final answer.
Via Charlie Stross @cstross@wandering.shop
Here in one paper is the probable reason why Apple abruptly pulled out of OpenAI's current funding round a week ago, after previously being expected to buy at least a billion bucks of equity.
(AI is peripheral to Apple's business model and not tarnishing their brand in the long term is more important than jumping on a passing fad.)
https://appdot.net/@jgordon/113294630427550275
Marcus on AI: LLMs don’t do formal reasoning - and that is a HUGE problem