[chimtim]

Unfortunately, one in 10 times is far from good enough (and this is with good prompt engineering which after using large language models for a while, one starts to do).

I feel like the current generation of AI is bringing us close enough to something that works once in a while but requires constant human expertise ~50% of the time. The self-driving industry is in a similar situation of despair where millions have been spent in labelling and training but something fundamental is amiss in the ML models.

[miohtama]

You are correct. I feel this is why the service is called Copilot, not Pilot :)

[ganzuul]

I think 1/10 is incredible. If it holds up it means they may have found the right prior for a path of development that can actually lead to artificial general intelligence. With exponential improvement; humans learning to hack the AI and the AI learning better suggestions, this may in theory happen very quickly.

We live in a very small corner of the space of possible universes, which is why finding a prior in program space within it is a big deal.

[Jeff_Brown]

I keep wondering how much time it could possibly save you, given that you're obligated to read the code and make sure it makes sense. Given that, the testimonials here are very surprising to me.