zlacker

[return to "GitHub Copilot Coding Agent"]
1. Scene_+V4[view] [source] 2025-05-19 16:47:11
>>net01+(OP)
I tried doing some vibe coding on a greenfield project (using gemini 2.5 pro + cline). On one hand - super impressive, a major productivity booster (even compared to using a non-integrated LLM chat interface).

I noticed that LLMs need a very heavy hand in guiding the architecture, otherwise they'll add architectural tech debt. One easy example is that I noticed them breaking abstractions (putting things where they don't belong). Unfortunately, there's not that much self-retrospection on these aspects if you ask about the quality of the code or if there are any better ways of doing it. Of course, if you pick up that something is in the wrong spot and prompt better, they'll pick up on it immediately.

I also ended up blowing through $15 of LLM tokens in a single evening. (Previously, as a heavy LLM user including coding tasks, I was averaging maybe $20 a month.)

◧◩
2. Beetle+bc[view] [source] 2025-05-19 17:20:18
>>Scene_+V4
> I also ended up blowing through $15 of LLM tokens in a single evening.

Consider using Aider, and aggressively managing the context (via /add, /drop and /clear).

https://aider.chat/

◧◩◪
3. gen220+l51[view] [source] 2025-05-19 22:25:04
>>Beetle+bc
I, too, recommend aider whenever these discussions crop up; it converted me from the "AI tools suck" side of this discussion to the "you're using the wrong tool" side.

I'd also recommend creating little `README`'s in your codebase that are mainly written with aider as the intended audience. In it, I'll explain architecture, what code makes (non-)sense to write in this directory, and so on. Has the side-effect of being helpful for humans, too.

Nowadays when I'm editing with aider, I'll include the project README (which contains a project overview + pointers to other README's), and whatever README is most relevant to the scope of my session. It's super productive.

I'm yet to find a model that beats the cost-effectiveness of Sonnet 3.7. I've tried the latest deepseek models, and while I love the price (nearly 50x cheaper?), it's just far too error-prone compared to Sonnet 3.7. It generates solid plans / architecture discussions, but, unlike Sonnet, the code it generates often confidently off-the-mark.

◧◩◪◨
4. rcarmo+qR1[view] [source] 2025-05-20 07:00:06
>>gen220+l51
There is a better way than just READMEs: https://taoofmac.com/space/blog/2025/05/13/2230
◧◩◪◨⬒
5. gen220+083[view] [source] 2025-05-20 16:37:32
>>rcarmo+qR1
I like this a lot! My root README ends up looking a lot like your SPEC.md, and I also have a file that’s pretty similar to your TODO.md.

My experience agrees that separating the README and the TODO is super helpful for managing context.

[go to top]