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.
What a cold thing to say about humans.
What is an anti tank machine gun?
Yes and probably yes. But that answers why they are there.
Or you know, like, deterrence.
deleted by creator
I love that for reference you got spelling and meaning wrong.
Spoken like a true keyboard warrior
I don’t know. My washing machine beeps three times in increasing intervals, so it isn’t that intrusive. The display shows me unique error codes that I can look up when someone happens. And I can set the machine to finish in a set amount of hours, so it will start just in time to be done when I’m back. All without WiFi
TL;DR?
So obscure opinions are made visible and we can talk about them?
As it should be. Just don’t give it more attention that it deserves.
Who the hell cares? Don’t feed into the artificial rage.
Always a great sign if posts asking for evidence are getting downvoted.
Stupid sexy Stewart
Sorry I don’t understand what you mean. What about the anti Muslims?
And yes, we should punish those who commit crimes rather than the ones who aren’t.
Everybody is talking about German guilt standing in the way of recognizing faults with Israel and I don’t think that’s what’s happening here. It’s rather that now all the actual anti semites are coming out of their holes and mix with people rightfully opposed to Israel’s actions, amplifying the hate against Jews in general.
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.