41 karma · joined April 7, 2012
more info: wrd.hu
> Traditional LLMs output everything they think immediately, without stopping to consider the best possible answer. New techniques like scaffolding, on the other hand, function like a thoughtful agent who explores different possible solutions before deciding. This “thinking before speaking” approach provides over 10x performance on demanding tasks like code generation, fundamentally boosting the intelligence of AI models without additional training.
Update: oh sry, you meant the movies...
However in case you use co-mocha[1] to test your generators, istanbul won't work properly, the generators in the reports are shown as uncovered. Therefore I made a mocha fork[2] and directly applied the changes from co-mocha to the source (instead of monkey patching); it solved the problem.
[1] https://github.com/blakeembrey/co-mocha [2] https://github.com/tfitos/mocha