alt Hacker NewsYou're missing the biggest suggestion from the GP's post: that the key to LLM success is verifiability.
Software has high verifiability through compilers, linters, static analysis, leak/memory corruption detection tools, or the very least, running the program to see if it crashes.
Math (as has been making the headlines recently) has high verifiability through automated theorem provers. Notably some of the non-mechanized math results from LLMs have been demonstrated to be wrong (and presumably many more are being checked; these aren't exactly easy to understand proofs).
Game playing (chess, go, Star Craft, etc.) is similarly verifiable: you get your score and you always know how you did in the end (even if not in the moment).
Making assumptions about LLMs in non-veriable domains is making a claim about LLMs that doesn't match their current capabilities. Maybe they'll get there and maybe they won't; I can speculate as well as you can but we're both guessing, so I'm not sure how much value the speculation has.
Replies
This is the same highly verifiable domain that has delivered reliable, bug-free software to date?
And LLMs won't take the easy way out (like so many people) and suppress errors, change tests etc, tweak code until warnings go away?
I think we'll naturally develop intuition and infrastructure for fault-tolerant ways to implement LLMs in non-verifiable domains, i.e. requiring multiple, independent agents agree on a direction from multiple angles before taking an action.
But we're definitely very early on this trend.