Is GitHub Copilot still relevant in the enterprise?
It used to be the default choice for companies a few years ago, and now I dont hear many people using it. Does anyone still use it here or have you gone over to Claude Code/Codex/devin/cursor?
I don’t use it heavily. I had to turn off the auto-suggestions, because they were almost always wrong, and the hijack the tab key, which makes writing my hand painful (having to hit escape before every tab). I tried looking for a way to change the keybinding a year ago, but it didn’t seem possible.
I will occasionally use the Ask sidebar to see if it gives me some good options or for a quick syntax lookup. That’s about it.
It got Agent mode recently, which it defaults to. When this first happened, I went to ask a question and the agent just started doing stuff and destroyed my code in a way that undo didn’t fix. I had to go back to the commit history and make some manual changes to get back to where I was. I never used the agent again.
There has been some talk about getting Claude Code, but the problem is that it takes so long to make these enterprise deals and get something rolled out, that there is something new by the time we get the last new thing deployed. The pace of evolution in this space is faster than the enterprise moves.
I can only assume that when the next model releases, people will say the current Claude Code isn’t very good… so I’m probably not missing much in real terms. It kind of reminds me of video game graphics. The bleeding edge of the current-gen is always talked about as if its photo realistic and so amazing… then looking back at the same game 10 years later, and it looks like trash compared to the new bleeding edge. So maybe it’s not worth getting so worked up.
There is actually Claude code integrated into gh copilot.
You can also access opus 4.6 and codex 5.3 in it, which work pretty well in agentic mode.
GitHub copilot agent mode is quite bad, and advanced premium models like opus4.6/codex 5.3 are making it barely usable.
Claude code and codex are night and day comparatively.
Additionally, GitHub copilot admins can enable/disable models. Each model has different ToS, so perhaps their admin has not turned it on.
I would suggest you not immediately insult people with ad hominem attacks.
What about warp, is that also just a wrapper?
When you say "Add a default $5 tip to the dialog screen titled 'Tip this waiter?'", what the harness does is supply information on where the strings are, the dialogs, and where the design style containing the PrimaryButton might be.
Cursor is excellent at this and probably pioneered the whole approach. Copilot hasn't really bothered to be more than a wrapper.
People were sold a spoon, get a spork, and end up eating with their hands.
In the recent rise of agents orchestration we're looking into moving towards more automated agentic setup. But while waiting, I decided to take max out of the copilot. Turned out, both copilot cli and VSCode one were lacking in agentic capabilities.
Fortunately OpenCode exists and it allows to officially connect to copilot account. So we were allowed to use it. OpenCode allows more granular control over what is available to the model, what specific model to use, etc. It filled missing gaps so we're now experimenting creating agentic flows.
Additionally, you can connect a local model in OpenCode. So if you have a beefy mac or pc, Qwen Coder may be interesting for you.
Some people seem to be talking about the VS(C) extension/feature, the paid llm service from GitHub, or both?
“X bone X is your PC!” vibes, anyone?
I have used Claude Code past few weeks and honestly can't tell if it is any better, or does anything different than Copilot in agent mode with same models.
for 50$ a month for 1500 requests - I use up the entire weeks worth of context for the other platforms in a couple hours with what im coding its annoying as hell and thats if they are working properly setup properly
Then ofc Cursor took off, but even then normie coders were AI-sceptical or mostly aware through ChatGPT.
Devin was only ever hype.
I still use Copilot (I've been a subscriber since first available) but in concert with ChatGPT/Codex and Cursor & Warp, so it tends to take a backseat.
I would expect most usage of it to be via VSCode until recently.
So perhaps it was always a secondary choice (despite being the pilot) to the trailblazers like Cursor and Claude Code but it has an important place in history and as a monthly subscription it's one of the best value ones so still worth looking at.