Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Is GitHub Copilot still relevant in the enterprise?

news.ycombinator.com

Post reply on HN
Print view View original

11–20 of 27 posts

Re: Is GitHub Copilot still relevant in the enterprise?

#11

Post by kken »

al_borland wrote: post #6

GitHub Copilot is the only AI we’re allowed to use where I work. 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 gi…

Skill issue

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.

Re: Is GitHub Copilot still relevant in the enterprise?

#12

Post by dd8601fn »

acadavid79 wrote: post #4

We still use it. Its integration in VSCode makes it very easy to use. We can select which model to use, and Claude’s are the best in my opinion.

I think I’m seeing fallout of Microsoft’s notoriously horrific branding and marketing, again?

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?

Re: Is GitHub Copilot still relevant in the enterprise?

#13

Post by idontwantthis »

dd8601fn wrote: post #12
acadavid79 wrote: post #4

We still use it. Its integration in VSCode makes it very easy to use. We can select which model to use, and Claude’s are the best in my opinion.

I think I’m seeing fallout of Microsoft’s notoriously horrific branding and marketing, again? 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?

Or are we talking about Microsoft Word?

Re: Is GitHub Copilot still relevant in the enterprise?

#14

Post by Atotalnoob »

kken wrote: post #11
al_borland wrote: post #6

GitHub Copilot is the only AI we’re allowed to use where I work. 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 gi…

Skill issue 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.

No, those are the models. They are NOT the same as Claude code/codex.

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.

Re: Is GitHub Copilot still relevant in the enterprise?

#15

Post by cedws »

We have Copilot and Claude Code. The rationale of having both is that Copilot is cheap anyway, grants access to a range of models, and some developers still haven’t moved over to CC. There’s also the smart auto completion which is actually free now but AFAIK there’s no Claude Code equivalent.

Re: Is GitHub Copilot still relevant in the enterprise?

#16

Post by zihotki »

At my work we can use only copilot. The rest of the tools is currently in pilot stage and under review. And no github cloud copilot.

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.

Re: Is GitHub Copilot still relevant in the enterprise?

#17

Post by taurath »

Atotalnoob wrote: post #14
kken wrote: post #11

Earlier quoted context omitted.

Skill issue 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.

No, those are the models. They are NOT the same as Claude code/codex. 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 i…

Wait really? I thought the models were basically the same with a wrapper.

What about warp, is that also just a wrapper?

Re: Is GitHub Copilot still relevant in the enterprise?

#18

Post by FloatArtifact »

giantg2 wrote: post #9

We started with GitHub Copilot, but it was largely replaced by Claude Code. The major benefit was that Claude could execute scripts and Copilot could not. That might have just been the way my organization configured it though.

Claude really utilizes tools or develops its own tools well. If OpenAI could get their sandbox situation ironed out... I could switch.

Re: Is GitHub Copilot still relevant in the enterprise?

#19

Post by procinct »

taurath wrote: post #17
Atotalnoob wrote: post #14

Earlier quoted context omitted.

No, those are the models. They are NOT the same as Claude code/codex. 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 i…

Wait really? I thought the models were basically the same with a wrapper. What about warp, is that also just a wrapper?

The models are the same. The agent implementation is different. I can confirm Claude Code performs much better than GH Copilot with the same Claude models.

Re: Is GitHub Copilot still relevant in the enterprise?

#20

Post by muzani »

taurath wrote: post #17
Atotalnoob wrote: post #14

Earlier quoted context omitted.

No, those are the models. They are NOT the same as Claude code/codex. 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 i…

Wait really? I thought the models were basically the same with a wrapper. What about warp, is that also just a wrapper?

There's a layer between your input and the model called an agent harness. It's the bit that guides the model how to traverse the file system, where to search, how the codebase is architected, how to navigate the monorepo.

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.

Post reply on HN