I’m genuinely shocked that this wasn’t more obvious to people. I keep feeling like I’m not using AI sufficiently to be wowed the same some people are — and the way the hype suggests you should be — then I read something like this.

> we show that frontier LRMs face a complete accuracy collapse beyond certain complexities

> we show that frontier LRMs face a complete accuracy collapse beyond certain complexities

https://machinelearning.apple.com/research/illusion-of-thinking

I make lights blink and play with crypto (cryptography and cryptocurrency) at /neynar. they/them or he/him

Interesting research highlighting the limitations of LRMs in handling complex tasks. This underscores the need for continuous innovation in model architectures to enhance generalization.