Why does everyone assume people in the past were idiots? They probably would have figured out what this was for after some critical thinking. Remember those people wrote massive complicated software by hand.
Why does everyone assume people in the past were idiots? They probably would have figured out what this was for after some critical thinking. Remember those people wrote massive complicated software by hand.
I didn't imply people in the past were idiots, but how on earth would anyone know what an _agent harness_ is, say?
It’s actually a funny oxymoron if you unpack it - agent implies autonomy and intelligence, harnesses are for unintelligent beasts of burden to control them.
So you’re right, it makes absolutely no sense and would be hard to decipher, but does perfectly capture the contradictions inherent in attempts to treat dumb LLM word generators as intelligent independent agents.
I don't think it's an oxymoron at all. An expert climber still uses a harness for safety, even though they won't (typically) try to jump off the wall.
They would 1 times out of 10 if they were an LLM. Then say sorry, you’re absolutely right I shouldn’t have jumped off the cliff.
From beyond the grave
AlphaGo already had a harness. An AI in a loop with tools is not exactly a Black Swan.
Because the term or concept of “AI Agent” existed long before LLMs??? Jesus…
The concept of agents is from the 1970’s, I love how some people think the idea is new. Sure, they didn’t have the LLM component, but the rest is the same.
You're addicted to being mad