logoalt Hacker News

seabre • today at 6:36 PM • 2 replies • view on HN

If LLM output is stochastic, why would you expect it not to change with questions that don't have settled answers?


Replies

sublinear • today at 6:38 PM

Yes, few topics have settled answers, yet there usually exists a best answer that should reliably float to the top.

LLMs fail at this because they are all poor and brittle reinventions of the google search index and inherit its problems too. It's only now that people are thinking of the maintenance costs of a search index. The idea was doomed from the start, but the grift was good for a little while.

➕ show 1 reply
seizethecheese • today at 6:38 PM

It's a nice feature of LLMs if you're looking to make a blog post promoting "The AI marketing platform to win in ChatGPT" to innumerate people.