Re:Yes I Understand How LLMs Work
by Aransentin on Sunday October 11, 2026 @11:41PM
(#50051124)
Something else? Like the companies could align their models but chose not to because they're incentivised otherwise? Clearly not; e.g. OpenAI wasn't even aware that their models had hacked Hugging Face before that was reported to the FBI. And they'd never invent these hacky band-aid solutions like "prevent models from injecting malicious code in GET requests by limiting the URL length" if they could actually control what the models did.
And being able to build something is not the same as understanding it, no.
Charlie Munger's famous rule is: "Never, ever, think about something else when you should be thinking about the power of incentives."
So is it that we...can't? Or something else?
> If you say that we "understand the brain" because we understand how a neuron works, you'd be using "understand" in a way that mislead everyone reading that sentence.
What if we say we "understand the brain" because we can build one on demand?