I've used CC with TypeScript, JavaScript and Python. Imo TypeScript gives best results. Many times CC will be alerted and act based on the TypeScript compile process, another useful layer in it's context.
I decided to really learn what is going on, started with: https://karpathy.ai/zero-to-hero.html
That give a useful background into understanding what the tool can do, what context is, and how models are post trained. Context management is an important concept.
Then I gave a shot to several tools, including copilot and gemini, but followed the general advice to use Claude Code. It's way better that the rest at the moment.
And then I dive deep into Claude Code documentation and different youtube videos, there is plenty of good content out there. There are some ways to customize and increase the determinism of the process by using the tools properly.
Overall my process is, define a broad spec, including architecture. Heavy usage of standard libraries and frameworks is very helpful, also typed languages. Create skills according to your needs, and use MCP to give CC a feedback mechanism, playwright is a must for web development.
After the environment and initial seed is in place in the form of a clear spec, it's process of iteration via conversation. My session tend to go "Lets implement X, plan it", CC offers a few route, I pick what makes most sense, or on occasions I need to explain the route I want to take. After the feature is implemented we go into a cleanup phase, we check if anything might be going out of hand, recheck security stuff, and create testing. Repeat. Pick small battles, instead of huge features. I'm doing quite a lot of hand handling at the moment, saying a lots of "no", but the process is on another level with what I was doing before, and the speed I can get features out is insane.
I have been through Karpathy's work - however, I don't find that it helps with large scale development.
Your tactics work successfully for me at smalle scale (at around 10klocs, etc) and starts to break down - especially when refactorings are involved.
Refactoring happens when I see that the LLM is stumbling over it's own decisions _and_ when I get a new idea. So the ability to refactor is a hard requirement.
Alternatively refactoring could be achieved by starting over? But I do have a hard time accepting that idea for projects > 100klocs.
It is until it's not. That's the problem. The AI gets tripped up at some point, starts frigging tests instead of actually fixing bugs, starts looping then after several hours says it's not possible. If you're lucky.
Then on average your velocity is little better than if you just did it all by hand.
The AI gets tripped phenomenon is something I've experienced, and I think it's again related to context usage. Using more agents and skills will reduce the pollution on the main context, and delay the moment where things go weird. /clear after each small mission.
As said above, CC needs heavy guidance, but even with these issues, I'm way faster.
Some MCP's do give the models superpowers. Adding playwright MCP changed my CC from mediocre frontend skills, to really really good. Also, it gives CC a way to check what it's done, and many times correct obvious errors before coming back at you. Big leap.
I suggest you to never try a real cigarette if you haven't already. Given that you are already addicted to nicotine the kick of the real deal could be too much to handle. And you don't want that habit, talking by experience. It's good that you found a drug that helps you, just don't inhale it.
I'd never suggest anyone to try a cigarette, but from my experience being addicted to nicotine is not easily translated to being addicted to cigarettes.
It takes a really different state of mind to start a cigarette habit especially due to awful taste and effect of ingesting a strong concentration of chemicals on your body that has nothing to do with dosed concentration of 'mostly just' nicotine.
It may be anecdotal and subjective reasoning, but I battled vape addiction differently than cigarette addiction. I'd classify tobacco addiction more of an emotional addiction, while vaping was more based on nicotine addiction which was more mechanical and predictable than the former.
I just gave it a short description of a small game I had an idea for. It was 7 sentences. It pretty much nailed a working prototype, using React, clean css, Typescript and state management. It event implemented a Gemini query using the API for strategic analysis given a game state. I'm more than impressed, I'm terrified. Seriously thinking of a career change.
I find it funny to find this almost exact same post in every new model release thread. Yet here we are - spending the same amount of time, if not more, finishing the rest of the owl.
I just spent 12 hours a day vibe coding for a month and a half with Claude (which has equal swe benchmarks at gemini 3). I started out terrified but eventually I realized that these are just remarkably far away from actually replacing a real software engineer. For prototypes they're amazing, but when you're just straight vibe coding you get stuck in a hell where you don't want to or can't efficiently really check what's going on under the hood but it's not really doing the thing you want.
Basically these tools can you you to a 100k LOC project without much effort, but it's not going to be a serious product. A serious product requires understanding still.
The initial prompt was, in case people doesn't want to log in:
Make a turn based chess like game. Instead of normal chess board use an hexagonal grid. Make the board diagonal shaped. Instead of traditional chess pieces we are going to use spaceship designs. Each spaceship has unique abilities that influence the board or their own skill. For 2 players, turn based. Show me what you got.
So I was looking for ImageMagick node options, when I see a notice of the top of Magickwand.js by the creator explaining it's been homeless since October last year. Decided to investigate a bit and there was quite a rabbit hole. Hope he is ok.
>Advertising companies are pushing DoH to remove control from you and give them the control, so be aware of that
True. My first naive attempt at content filtering for my kids was to use a family friendly DNS for the whole network. That's when I learned about chrome's secure DNS option, witch effectively bypasses my intended settings. I guess endpoint control is the only effective option. A mandatory http proxy could be used to filter by hostname too. None of them easy, and I'm supposed to be an expert. Normal people has little chance of implementing technical parental controls.
You can think of the ssh://server/folder as a normal /folder. ssh provides auth and encryption to a remote hosted folder but you can forget about it for the purpose of understanding the nature of git model.
reply