I think I'm using it wrong.

I'm using Zed as my editor, and maybe 18 months ago I upgraded my system. I didn't miss the AI autocomplete at the time, so I didn't bother to set it up again. However, around two weeks ago I figured I'd give it another go.

I set up GitHub Copilot in Zed and... it's horrible. It seems like most of its suggestions are completely misguided and incorrect, usually just duplicating the code immediately above or below the cursor location while updating the name of a single identifier to match some perceived pattern. Not remotely close to what I'd consider useful; I'm definitely a faster & better programmer without it.

I also tried setting up some local models on ollama: I kept getting random tokens inserted that seemed to be markup from the model output that Zed didn't know how to parse. (On mobile rn, will post sample output when I am back at work if I remember to.)

Is paying Anthropic an arm and a leg for the privilege of granting them first-party access to train on my user data really the competitive move as a modern developer?

P.S. I know Zed has their own AI (and it seems like it should be really good!), but when they first introduced it, I tried it out and it immediately consumed the entire free tier's worth of credits in just a few minutes of normal coding: suggestions are proactively generated and count against your account credit even if not accepted, so I didn't really feel like I'd gotten a good sense of the tool by the time the trial ran out. Even if it's really good, it burns through credits extremely fast.

I've used the 200 bucks Claude Code account, and while that's pretty great, it's definitely not "fire and forget". It often requires a completely different skill set. You basically need to develop a feeling for what the agent can do automatically and what needs extra prompting.

If you want a perfect investment imho, get Supermaven. It's autocomplete is 99% perfect.

For autocompletion I suggest giving Zed's own offering another try. It's guesses somewhat correctly at least half the time and is very convenient when it get's what you're trying to do durin a refactor and suggest valid multiline changes. It's still rather annoying when it replaces regular autocompletion for import paths with it's plausible sounding guesses. Before that I was using Cody, but I don't think that they have free tier any more.

> immediately consumed the entire free tier's worth of credits in just a few minutes of normal coding

Happened to me too when I've tried to do a single edit with connected gemini pro. It somehow ran out of free quota even before finishing it.

I don’t think you should look at the Copilot autocomplete as anything other than autocomplete, as far as I know they use worse but faster models for that.

I’m not big on AI but I get occasional use out of Copilot with the chat / agent mode and Claude Sonnet 4.

> suggestions are proactively generated and count against your account credit even if not accepted

This is no longer the case. They only count if you accept them.

Ime their model is not great, but better than copilot (ime copilot is just too slow and disruptive).

Also the options you have for tab-complete, afaik, are zed/zeta, guthub copilot, supermaven, and local models. I dont think there are other providers right now, glad if I am wrong in that.