Cheaper to write definitely, no so much cheaper to read. AI generated docs tend to be so annoyingly verbose if not reined in during prompting.

But well, any documentation is good when a human would've written zero docs

Rather than that, the quality of human-written documentation is just too inconsistent. Because it's not written by a single person.

AI's verbosity is definitely a problem, but I think it's something you can just check once more. Of course, opinions vary.

It does, but it's very poorly documented and quite unstable (on purpose i think). What the other commenter said about the VSCode BYOK seems to be the more reliable way.

I tried adding a Foundry LLM as Github Copilot custom model and failed miserably. But with VSCode BYOK (and Github Copilot as the interfact) i did get it working, and i can now use Deepseek V4 Flash with Copilot.

Yeah exactly.

I'm not exactly building TUI's every day, but even i felt pain when i read that "small game engine" post

> I'm not exactly building TUI's every day, but even i felt pain when i read that "small game engine" post

The bigger issue is they where somehow thinking it was "cool" and "advanced" while it's just a kludgy rube-goldbergy monstrous hack.

Which is of course only semi-working: to me the model thinking what you see is what it outputs in the TUI is the deal-breaker for me. It's of course not working like that for they're apparently, in their "game engine", converting on the fly a headless browser to approximated characters to display in the terminal. So the model tells you he did output ASCII but people are copy/pasting (because, yes, at times you want to copy/paste) Unicode chars.

Plenty of bug reports and pissed users.

That's the bigger issue.

The biggest issue is those thinking a 10 GB VM required to run a headless Electron browser and then fuxx0ring characters conversion is somehow an achievement.

Whats the small game engine post?

Seeing Jonathan blow invoked and his response in the comments tickled me pink

Was it Casey Muratori that spoke about an AI educing allocations from 10k per frame to 200 per frame, but the manual programming work got it to 0 instead?

The stupidest thing is that according to that logic, ncurses is a game engine too.

At least game engines manage to render their frames properly. Claude Code sometimes eats entire paragraphs of text output, resulting in things such as numbered lists jumping from 2 to 4 out of nowhere.

I'd just ask Claude to repeat himself at first but it happens so often that I actually made a little tool to dig up the output inside the session history and present it properly in a separate terminal.

Truly, the future!

Very interesting! Gonna look through this for sure in the next weeks

Nice looking library! Might try it for one of my own projects.

You should definitely try mealie yes. On top of a good way to host your own recipes, the entire thing just feels...really well put together?

I'm not even using the features beyond the recipes yet, but i'm already very happy that i can migrate my recipes from google docs to over there

I don't think youre missing out necessarily. I would riot if i couldn't use Pycharm anymore, for big python projects just nothing beats it right now.

I do use VSCode too, but mostly for quick scripting or non-programming projects. and even then i installed a bunch of extensions to make it more like Pycharm.

The manual approval of commands in GHCP can be circumvented, there's an experimental setting that allows you to accept all commands automatically.

I wish you could be a bit more specific though, you can't set which commands you want to auto-accept in detail.

Pretty sure you can set a terminal whitelist and blacklist for it.

I've been using GitMCP.io + Github Copilot for this problem specifically (AI assistant + accurate docs). The downside is that you need to add a separate MCP server for each repository, but the qualitative difference in agent mode is incomparable.

I used it recently to do a major refactor and upgrade to MLFlow version 3.0. Their documentation is a horrid mess right now, but the MCP server made it a breeze because i could just query the assistant to browse their codebase. Would have taken me hours extra myself.

How does GitMCP compare to Context7

Not sure, i can't run it since i can't install Node.js on my work environment. What is your experience with Context7 like?

As for GitMCP: I think the url fetching tool of the docs it does is not great, but the code searching tool is quite good. Regardless, i remain open to alternatives, not stuck to this yet.

you should def give it a try, happy to hear what u think

When you do have that work context MS copilot performs quite well. But outside of that usecase it's easy to see their model is pretty bad.

It absolutely does not perform well with work context.