Closed obuzek closed 6 months ago
The existence of the quantitative skill tree suggests that we do expect math-related skills.
Please take a look at #200 - it may be an example of how a skill could improve scores on math questions without actually attempting to teach the model to "do math".
I agree, that one and #231 are fascinating examples. Added a "skill category: abstract math" label so we can consider them together.
Based on this week's experience, I think we can consider that "math" and "computation"-type skills are generally going to be rejected. Abstract math still might be a special case, but even so it's likely to be rejected until we establish a "reasoning"-related foundational skill.
People have definitely submitted some very cool things on this topic so we'll have lots to choose from when we start opening in that direction!
David brings up a great point that LLMs are well-known to be poor at math. Even if we can make them behave correctly on small number examples, it's likely to extrapolate poorly to large numbers and large texts.
Questions for the Lab inventors:
taxonomy
only solicit non-math-related skills?cc @akashgit @katesoule @xukai92 @juliadenham