alt Hacker NewsThe issue is that many problems aren't easy to verify, and LLMs also excel at producing garbage output that appears correct on the surface. There are fields of science where verification is a long and arduous process, even for content produced by humans. Throwing LLMs at these problems can only produce more work for a human to waste time verifying.
Yes, that is true. And for those problems, those who use LLMs will not get very far.
As for those who use LLMs to impersonate humans, which is the kind of verification (verify that this solution that is purported to be built by a human actually works), I have no doubt we will rapidly evolve norms that make us more resistant to them. The cost of fraud and anti-fraud is not zero, but I suspect it will be much less than we fear.