Hacker News Reader

Language models happen to share human flaws, but like humans they can amplify their abilities and reliability by building and using reliable tools.

I actually prefer a system that's correct half of the time at thousands of times the cost & speed.

The real answer is it's completely domain-specific. If you're trying to search for something that you'll instantly know when you see it, then something that can instantly give you 5 wrong answers and 1 right answer is a godsend and barely worse than something that is right 100% of the time. If the task is to be an authoritative designer of a new aeroplane, it's a different story.

Because we can still do things computers can't and that's interesting