[losvedir]

I recognize your username so I know you've been around for awhile (and are you a xoogler who for a time banged the drum on the benefits of iframes, or am I confusing you with a similar username?), and so I'm kind of surprised at your lukewarm take on LLMs.

I agree they hallucinate and write bad code and whatever, but the fact that they work at all is just magical to me. GPT-4 is just an incredibly good, infinitely flexible, natural language interface. I feel like it's so good people don't even realize what it's doing. Like, it never makes a grammatical mistake! You can have totally natural conversations with it. It doesn't use hardcoded algorithms or English grammar references, it just speaks at a native level.

I don't think it needs to be concretely useful yet to be incredible. For anyone who's used Eliza, or talked to NPCs, or programmed a spellchecker or grammar checker, I think it should be obviously incredible already.

I'm not sold on it being a queryable knowledge store of all human information yet, but certainly it's laying the inevitable future of interacting with technology through natural language, as a translation layer.

[packetlost]

> GPT-4 is just an incredibly good, infinitely flexible, natural language interface.

An interface that's incredibly difficult to produce consistent output. As far as I know, we have not found a way to even make it do basic tasks parsed from natural language without a prohibitive-to-most-use-cases error rate. It's amazing that it can produce pretty believable looking text, but it's abundantly clear that there's no reasoning behind that text at all.