[jliptzin]

My friends and I have always wondered as we've gotten older what's going to be the new tech that the younger generation seems to know and understand innately while the older generations remain clueless and always need help navigating (like computers/internet for my parents' generation and above). I am convinced that thing is AI.

Kids growing up today are using AI for everything, whether or not that's sanctioned or if it's ultimately helpful or harmful to their intellectual growth. I think the jury is still out on that. But I do remember growing up in the 90s, spending a lot of time on the computer, older people would remark how I'll have no social skills, I won't be able to write cursive or do arithmetic in my head, won't learn any real skills, etc, turns out I did just fine and now those same people always have to call me for help when they run into the smallest issue with technology.

I think a lot of people here are going to become roadkill if they refuse to learn how to use these new tools. I just built a web app in 3 weeks with only prompts to Claude Code, I didn't write a single line of code, and it works great. It's pretty basic, but probably would have taken me 3+ months instead of 3 weeks doing it the old fashioned way. If you tried it once a year ago and have written it off, a lot has changed since then and the tools continue to improve every month. I really think that eventually no one will be checking code just like hardly anyone checks the assembly output of a compiler anymore.

You have to understand how the context window works, how to establish guardrails so you're not wasting time repeating the same things over and over again, force it to check its own work with lots of tests, etc. It's really a game changer when you can just say in one prompt "write me an admin dashboard that displays users, sessions, and orders with a table and chart going back 30 days" or "wire up my site for google analytics, my tag code is XXXXXXX" and it just works.

[queenkjuul]

The thing is, Claude Code is great for unimportant casual projects, and genuinely very bad at working in big, complex, established projects. The latter of course being the ones most people actually work on.

Well either it's bad at it, or everyone on my team is bad at prompting. Given how dedicated my boss has been to using Claude for everything for the past year and the output continuing to be garbage, though, i don't think it's a lack of effort on the team's part, i have to believe Claude just isn't good at my job.

[sodafountan]

I was going to try having an AI agent analyze a well-established open source project. I was thinking of trying something like Bitcoin Core or an open-source JavaScript library, something that has had a lot of human eyes on it. To me, that seems like a good use case, as some of those projects can get pretty complex in what they're aiming to accomplish. Just the sheer amount of complexity involved in Bitcoin, for instance, would be a good candidate for having an AI agent explain the code to you as you're reviewing it. A lot of those projects are fairly well-written as they are, with the higher-level concepts being the more difficult thing to grasp.

Not attempting to claim anything against your company, but I've worked for enterprises where code bases were a complete mess and even the product itself didn't have a clear goal. That's likely not the ideal candidate for AI systems to augment.

[pennomi]

As context size increases, AI becomes exponentially dumber. Most established software is far, FAR too large for AI. But small, greenfield projects are amazing for something like Claude Code.