i really want to say goodbye to copilot...

in this tutorial chris looks at how open source copilots have moved on with the advent of the continue vscode extension and the new mistral 22 billion parameter codestral model and it compares against starcoder-2 and llama-3.
he shows what the difference betweens chat and "fill in the middle" models are and why you need both today in ai coding assistants, and how they are used in continue
do powerful coding models that you can run on your local machine via ollama spell the end of the copilot era?

[@JohnMcclaned]

the blue blocking glasses with the high intensity blue lights in the background makes this video

[@chrishayuk]

I aim to please

[@SubmitToTheBiomass]

lmao

[@gauravgupta5145]

Exactly same we are implementing too.

[@flat-line]

But what is your verdict? And is something special about github copilot, if i use continue with gpt4 , will it be like github copilot?

[@chrishayuk]

i feel it's close but not quite there yet

[@flat-line]

@@chrishayuk thanks !

[@danielhenderson7050]

What machine are you running ollama on? You must have the models all loaded together do you? I can run Codestral on my 3080 10GB but definitely nothing else alongside😅

[@chrishayuk]

Yeah my machine is a little crazy it’s an MacBook Pro M3 Max with 128Gb of Unified memory

[@danielhenderson7050]

Ahh I see :) nice!

[@chrishayuk]

Yeah, it’s pretty ridiculously but to be able to do these type of videos where I’m using different models and doing fine tuning etc, I kinda need this… at least that’s the argument I made to my wife 😎

[@nikhil_jadhav]

I felt cursor was better than continue but yes continue is open source, cursor is not.

[@chrishayuk]

Yeah, open source is the key thing for me

[@explorer945]

first like :)