Add skill for analyzing Wordle puzzles #209
Merged
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Describe the contribution to the taxonomy
This skill improves helping with solving Wordle puzzles.
Input given at the prompt
First try:
Second try, alternate formulation:
Third try, different puzzle:
Fourth try, different puzzle:
Response that was received
Responses in the same order as the questions above. They are all pretty much nonsense and inconsistent, but at least have a "consistenly wrong" structure:
Response that is now received instead
Unknown, I didn't retrain the model yet. But if I run
lab generate
, it says:even if the ./taxonomy directory has my commit/fork.
But also, I only have a ThinkPad laptop with internal graphics, no NVidia or Mac M1 hardware.
Contribution checklist
lab generate
lab generate
does not produce any warnings or errorsqna.yaml
file was linted