5gruel
I mean, your suggestive question at least helps me understand your mindset a bit better. If I would see the situation the way you characterize it, I would probably sound the same.
I can only encourage you to try to see tbrough the business bullshit that is undoubtedly there and recognize that there is an actual underlying technological breakthrough with the chance of redefining how we interact with machines.
I’m running a local LLM that I use daily at work to help me brainstorm and the fact that I can run perfect speech to text in real time on my laptop was simply not possible a few years ago.
Weird responses here so far. I’ll try to actually answer the question.
I’m using copilot for 9 months at work now and it’s crazy how it accelerates wiring code. I am writing class c code in C++ and rust, and it has become a staple tool like auto formatting. That being said, it cannot really do more abstract stuff like this architecture decisions.
Just try it for some time and see if it fits your use case. I’m hoping the local code models will catch up soon so I can get away from Microsoft, but until then, copilot it is.
I’m not convinced about the “a human can say ‘that’s a little outside my area of expertise’, but an LLM cannot.” I’m sure there are a lot of examples in the training data set that contains qualification of answers and expression of uncertainty, so why would the model not be able to generate that output? I don’t see why it would require an “understanding” for that specifically. I would suspect that better human reinforcement would make such answers possible.