Comment by unclebucknasty
12 hours ago
I've (elsewhere) written about this diminishing return effect on LLM utility in relation to increasing expertise.
The question: what's the net positive gain of turning people who know nothing in a given field into sub-novices, while weighing actual experts down with work slop and marginal returns?
And I wonder what the true cost is of arming so many novices with that level of dangerous knowledge.
The fact that some people get genuine value from LLMs when learning doesn’t contradict the fact that they’re Dunning-Krueger “expertise” generators. The fact that the person learning from them is in charge of ensuring they aren’t full of shit, which they frequently are, is an inescapable flaw in this process. I honestly think that reduces the value of these things to just above what you can find out with a search engine with most topics. Hey, great. An improvement is an improvement right? Is it an improvement worth trillions of dollars and screwing over writers and artists worldwide? Fuck no.
Sounds about right.
Tangentially, but related: I'm old enough to remember when the spirit of your comment was pervasive on HN.
It wasn’t even all that long ago. I noticed around the time ChatGPT 3.5 was released I saw a significant change in tone regarding LLMs and diffusion models. I think that’s when some serious astroturfing started.
I’m old enough that I worked my first IT summer job the same year slashdot was founded. I’ve seen a lot of tech tribalism form and dissipate, and this one didn’t feel organic. My gut says a lot of the us-vs-them tension originated in a deliberate campaign to cast AI boosters as the tech industry in-crowd, and ‘other’ the people not on-board. Who knows.
1 reply →
I think the true cost will be some catastrophic failures.
Just hoping folks don’t get hurt due to people not understanding what they’re doing with these things but believing they’re competent.
If that is the case, I seriously doubt the blame would ever touch the people that oversold this shit.