Software engineers at Microsoft are now expected to use both Claude Code and GitHub Copilot and give feedback comparing the two, I’m told. Microsoft sells GitHub Copilot as its AI coding tool of choice to its customers, but if these broad internal pilot programs are successful, then it’s possible the company could even eventually sell Claude Code directly to its cloud customers.
Guys? Are we going to have to rename Microsoft products from Copilot to Claude soon?
Microsoft Claude 365?
We got copilot reviewing our code at work
It mostly just finds typos and other things like that
Quite useless at anything else
We have ours configured pretty well at this point and it does an absolute bang-up job at code review. It will point developers towards tools and utilities that our monorepo has If they appear to be reinventing the wheel. It will catch common problems and issues that we have in our instruction file, and does a pretty good job of catching bugs and small issues like typos and what not.
Perhaps you need to tighten up your instruction file?
Yeah, LLMs are pretty great contextual search engines if you curate a good dataset for them to draw from.
They aren’t a magic bullet that’ll find what’s relevant to you from the vast ocean of shit that is the internet.
Like intelisence which has been doing it faster, more consistantly and offline since the mid 2000’s?
Intellisense can review a 1000 line PR?
Of course? Just as quick as it can candy colour the braces and highlight your references of your 1000 line pr
My girlfriend is forced to use only Copilot at her work, and its just completely useless. She frequently posts me failed tasks it couldnt do. :).
Seems to be the worst Ai by far.
For copilot in visual studio at least you can select between models it will use, depending on the org setup showing them.
I don’t see how “worst of all of them” applies when it’s an umbrella of other models.
Maybe we’re all taking about different copilots. There’s multiple products after all.
They’re all objectively shit.
Even with Opus in the backend Copilot is so bad compared to Claude code
GitHub copilot within visual studio is not bad actually, if it doesn’t find anything to but typos then congrats your team is all competent senior developers…
It does cut down review time for juniors’ work, and it’s capable of implementing full features given the correct documentation and instructions. It’s a useful tool that assists and doesn’t replace competent developers.
I don’t know, that is about all Mistral can do too.
That and python scipy is like a 50/50 for relevant code snippits.
It had never once output compilable embedded code, even when I have tried to directly lead it there.
Its only core competency is convincing idiot c-suites that they should force their org to use copilot
Which is weird because isn’t ChatGPT supposed to be one of the best (least shitty)? Isn’t CoPilot rebranded ChatGPT?
The model (sonnet, opus, gpt) is the engine, the framework (copilot, Claude, codex) is the rest of the car
If you put a V8 Hemi in a shitbox, it’s still a shitbox.
No, gpt is much better. I dont know how it works behind the scenes but I think Copilot is what Microsoft built and gpt is what open ai built.