That's an interesting idea, but if the tools are really the problem, is there an actual way that we can solve this? How?
Not the author, but one way you could mitigate some of the LLMs problems while learning (authoritatively stating wrong facts, reward hacking, ...) is to have it give you testable code exercises to teach you facts. So…
Lately I've been thinking about this a lot. I've slightly shifted my use of Claude from implementing tool to scaffold generator for me to actually do the hard parts. It's frustrating at first, because the impulse always…
That's an interesting idea, but if the tools are really the problem, is there an actual way that we can solve this? How?
Not the author, but one way you could mitigate some of the LLMs problems while learning (authoritatively stating wrong facts, reward hacking, ...) is to have it give you testable code exercises to teach you facts. So…
Lately I've been thinking about this a lot. I've slightly shifted my use of Claude from implementing tool to scaffold generator for me to actually do the hard parts. It's frustrating at first, because the impulse always…