[bena]

I think the biggest pushback this article will get here is the date.

Although all he's saying is basically, "It's a tool, not a silver bullet". But the article is 3 years old and people will note that the models have been updated since then.

[simonh]

Sure, but they're still LLMs and still do the same things largely the same way they did 3 years ago. There are some architectural changes, and maybe these will merit a re-assessment over time, but fundamentally it's still the same basic technological approach refined and scaled up.

[bena]

And I don't disagree, but the posting of the article feels more like bait of a sort.

But I've noticed that if you mention anything that could be seen as slightly critical of LLMs, you'll get people out of the woodwork suggesting that the state of the art has made your criticism invalid.

[Diogenesian]

The models have updated but the biggest change is providers leaning in to them being "stochastic parrots," aka probabilistic computing, and if p(good response) > 0.5 then running the algorithm over and over again improves accuracy.

Of course it's gussied up as "mixture of agents" "reasoning traces" "agentic dispatching" but high-level it's Randomized Algorithms 101.

[Kim_Bruning]

Oh, that's an interesting angle! Do you know of texts or concepts I can look up? It might improve my coding by quite a bit.

[Diogenesian]

I think this is still the classic reference (it's what I used in graduate school): https://www.cambridge.org/core/books/randomized-algorithms/6...