I think it actually holds truer to it working better with a _lighter grip_. LLMs tend to conclude the wrong thing if you over-control them (more context is what makes them less and less reliable over time, as in those demos), and trying to force a model to execute A+B+C=D in sequence is way harder than giving it a bunch of tools to arrive to conclusion D
They have much better jackhammer metaphors over on JackerNews
yes but i cant open that at work
Bravo!
I think it actually holds truer to it working better with a _lighter grip_. LLMs tend to conclude the wrong thing if you over-control them (more context is what makes them less and less reliable over time, as in those demos), and trying to force a model to execute A+B+C=D in sequence is way harder than giving it a bunch of tools to arrive to conclusion D