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