https://twitter.com/fablesimulation/status/16813529041528504... These guys seem to be on the leading edge there - making self-referential character-driven narratives where agents talk to each other and build the collective world understanding, all through a South Park Westworld lol
Like the current top HN post suggests (https://eugeneyan.com/writing/llm-patterns/), we’re still discovering patterns that work well with LLMs.
That said, anecdotally - they already excel at being logic engines. Capable of filling in the gaps between instructions. Using their worldly knowledge or “common sense” to do so.
But ever so often, they’ll miss an important bit. And I have to be quite involved to catch that. Kinda defeats the purpose. Here, I think we can benefit from supervisor LLMs. A second layer, whose sole job is to ensure the output quality. A QA bot - essentially.
Coincidentally, that appears to be how GPT4 was made - apparently it's actually about 8 personas with designated roles running GPT3.5 trained together ("Panel of experts"? there's an AI name for the technique). Makes you wonder how far that one trick scales.
(P.S. great link. Gah - another long read on the todo list)
So I absolutely agree with this. And yet this meme persists. I wonder what's creating the feeling that it's "dumber" in so many? Perhaps they're just noticing the limits that always existed previously? I'm not sure, and am interested in others thoughts on it.
In comparison, Bard and Claude are getting better with time.
If you ask GPT to give you the same thing now, it wont , no matter how hard you try.
That's like hard evidence for me that they've dumbed it down.
And yes, LLaMA 2 is awesome. Progress is being made. But it’s slowed down. The novelty’s worn off. Now we’re lacking some fundamental plumbing to reach a useful AGI.
If anyone cares, Bard is proving to be way more useful these days. Especially for research work. And Claude is bar none for document analysis.