Hacker News Reader

Comment by FeepingCreature | Hacker News Reader

> Are you telling me that today’s model gets this table 85% right and the next version will get it 85.5 or 91% correct? That doesn’t help me. If there are mistakes in the table, it doesn’t matter how many there are - I can’t trust it. If, on the other hand, you think that these models will go to being 100% right, that would change everything, but that would also be a binary change in the nature of these systems, not a percentage change, and we don’t know if that’s even possible.

Of course, humans also make mistakes. There is a percentage, usually depending on the task but always below 100%, where the work is good enough to use, because that's how human labor works.

View on HN

If I'm paying a human, even a student working part-time or something, I expect "concrete facts extracted from the literature" to be correct at least 99.99% of the time.

There is a huge gap from 85% to 99.99%.

Sure but there's no step change.

You can expect that from a human, but if you don't know their reputation, you'd be lucky with the 85 percent. How do you even know if they understood the question correctly, used trusted sources, correct statistical models etc?

This does not at all resonate with my experience with human researchers, even highly paid ones. You still have to do a lot of work to verify their claims.

humans often don't trust (certain) other humans too.

but replacing that with a random number(/token) generator is more reliable to someone, then more power to them.

there is value to be had in the output of this tool. but personally i would not trust it without going through the sources and verifying the result.

A human WILL NOT make up non-existent facts, URLs, libraries and all other things. Unless they deliberately want to deceive.

They can make mistake in understanding something and will be able to explain those mistakes in most cases.

LLM and Human mistakes ARE NOT same.

> A human WILL NOT make up non-existent facts

Categorically not true and there’s so many examples of this in every day practice that I can’t help but feel you’re saying this to disprove your own statement.

It's absolutely true. Humans misremember details but I'll ask an LLM what function I use to do something and it'll literally tell me a function exists named DoExactlyWhatIWant and humans never do that unless they're liars. And I don't go to liars for information -- same reason I don't trust LLMs.

Tell me, does an LLM know when it lies?

I don't see a functional difference between misremembering details and lying. Sure one is innocent and one malicious, but functionally a compiler doesn't care if the source of your error is evil or not.

An LLM doesn't know when it lies, but a human also doesn't know when they are (innocently) wrong.

The crucial difference is between misremembering occasionally VS consistently.

You won't give any job to that kind of person.

Non-liar humans do in fact make mistakes.

True, but if they start producing non-existent facts consistently LIKE LLMS. You will be concerned about their mental health.

I insist that human hallucinations are NOT SAME as LLMs.

Reply on news.ycombinator.com