News for hackers. Stuff that matters.
Re:Alice in Wonderland: Simple Tasks Showing Complete Reason... by mjburgess on Wednesday June 05, 2024 @11:00AM (#40585677)
Sure, but even these people... the failures are so common, and often very obvious. Consider a CEO who puts a press briefing in and asks some questions about it, it's not uncommon for those answers to be obviously wrong on any sort of critical reflection.

We arent dealing with a technology that is 99.9% right in our most common use cases, so that we need to engineer some incredibly complex problem to expose the flaw. Rather, in most cases there is some obvious flaw. It's a system that requires typically significant "prompt engineering" to provide the reasoning the system otherwise lacks.

I guess that offers an explanation: people aren't aware that via their own prompt engineering they are repairing the deficiencies of the process by manipulating its inputs to include the structured reasoning it lacks. So there's a sort of hot-reading effect at work.

Re:Alice in Wonderland: Simple Tasks Showing Complete Reason... by throw46365 on Wednesday June 05, 2024 @02:03PM (#40588243)
> We arent dealing with a technology that is 99.9% right in our most common use cases, so that we need to engineer some incredibly complex problem to expose the flaw. Rather, in most cases there is some obvious flaw. It's a system that requires typically significant "prompt engineering" to provide the reasoning the system otherwise lacks.

Right -- we are a long way from "this is a very nuanced error" being the dominant failure.