News for hackers. Stuff that matters.

A comment on DeepMind’s AlphaCode Conquers Coding, Performing as Well as Humans. Parent comment

Re:DeepMind’s AlphaCode Conquers Coding, Performing as Well ... by bradjohnson on Thursday December 15, 2022 @12:24PM (#34002767)
I threw a leetcode easy description into ChatGPT and submitted the solution without any editing. It passed all the test cases and got in the 95th percentile for efficiency of C++ submissions.

I haven't tried anything more advanced, but to go from simple requirements to solution without any clarification or even method signatures (It guessed the correct method signature down to the name and input params) was pretty dang impressive to me.

[ Parent | on HN ]
Re:DeepMind’s AlphaCode Conquers Coding, Performing as Well ... by AnonymousPlanet on Thursday December 15, 2022 @12:55PM (#34003158)
Chances are, you gave it a problem that was actually in its training set.
[ Parent | on HN ]
Re:DeepMind’s AlphaCode Conquers Coding, Performing as Well ... by bradjohnson on Thursday December 15, 2022 @01:16PM (#34003439)
It's still impressive to me even if it was in its training set. The data used for training is not stored verbatim in the OpenAI model. It would still need to parse the context anew and solve the problem given its understanding of the boundaries of what I've written.
[ Parent | on HN ]
Re:DeepMind’s AlphaCode Conquers Coding, Performing as Well ... by Dopameaner on Thursday December 15, 2022 @02:31PM (#34004445)
On contrast, I did it for projecteuler and told it needs to be extremely efficient or math. Didnt give me an appropriate result.
[ Parent | on HN ]