[dsubburam]

I didn't know of that paper, and thought the title was a riff on Karpathy's Unreasonable Effectiveness of RNNs in 2015[1]. Even if my thinking is correct, as it very well might be given the connection RNNs->LLMs, Karpathy might have himself made his title a play on Wigner's (though he doesn't say so).

[1] https://karpathy.github.io/2015/05/21/rnn-effectiveness/

[throwaway314155]

Unreasonable effectiveness of [blah] has been a thing for decades if not centuries. It's not new.

[temp0826]

It's an older version of "x hates this one weird trick!"

[ayrtondesozzla]

It is not at all, it's being misused here to make it feel like that.

Wigner's essay is about how the success of mathematics in being applied to physics, sometimes years after the maths and very unexpectedly, is philosophically troubling - it is unreasonably effective. Whereas this blog post is about how LLM agents with tools are "good". So it was not just a catchy title, although yes, maybe it is now beibg reduced to that.