Comment by browningstreet
1 day ago
Doing research work with it that outputs any kind of artifact is.. really painful. It constantly crashes, has to regenerate.. and then the output is often very difficult to carry to other Microsoft products, like Sharepoint. I end up creating PDFs that I import.
I'll go ahead and burn working hours on it because I'm getting paid, and people like the things I create.. but it's a very crippled and painful version of what you get with the frontier products and most OSS options.
It boggles my mind that Microsoft can fail to deliver even bare minimum working software so consistently, with all the engineering talent they house. What are the product teams doing?
It boggles my mind that it doesn't seem to effect their bottom line at all
I feel it is even worse than bare minimum -- it is so bad it infuriates the user. It is hard to get away from that reaction when one uses better alternatives in their personal life.
incredible right? - not to mention the complete access they have to OpenAI's IP
Vibecoding.
Oh it's so bad. So so bad.
If you prompted an AI to return answers "as though you habitually ate soap and crayons while mouth breathing" you'd still get a better response than copilot
That used to be the case, but the current Enterprise version, with the poorly-named "GPT 5.6 think deeper" option, is very decent indeed. Can't tell if it's Sol, Terra or a mixture of the two, but it's certainly not Luna.
(Stick with the default "Auto" and you probably get Phi-4 -- it's lobotomised AF.)
I use Copilot a lot now. Unlimited, free, high-quality, enterprise-protected inference is not to be sniffed at. It also writes some of the nicest code I've ever seen from an LLM, that's almost entirely free of comments.
Are you referring to GitHub Copilot? I believe this thread is referring to Windows Copilot, such as the AI feature embedded into every Office progam, which is not the same experience.
2 replies →
My previous company used copilot enterprise
My experience was great because I had premium license and only used thinking models
Most colleagues didn’t have premium and used default/auto model
People stick to their very first bad experience unfortunately
Its so bad you would probably get better answers using a 2b parameter local model