Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AI is making me dumb

jpain.io

Post reply on HN
Print view View original

311–320 of 328 posts

Re: AI is making me dumb

#311

Post by zrn900 »

ryandrake wrote: post #72
Rooster61 wrote: post #11

I can't relate that much to this. Every time I use AI to write code, I'm constantly fighting a feeling on the back of my neck that I need to look over everything it has done and supplement/alter it with my own code. That ick feeling counteracts the dopamine hit of having a working app after a few minutes of vibe coding, and I don't think that's going anywhere anytime soon. That said, I have experience. I could absolu…

In my experience, Claude only knows how to spew code. Every problem you want it to solve, it translates into "more code" rather than "less code". You have to very closely code review everything it does, otherwise your codebase is going to just grow and grow, and asymptotically approach 100% debt. I code review everything that Claude produces, and I'd estimate about 90-95% of the time, my reaction is WOW it works but…

> Every problem you want it to solve, it translates into "more code" rather than "less code"

Try Deepseek or Xiaomi's Mimo. They produce very lean code.

Re: AI is making me dumb

#313

Post by mpalmer »

0xbadcafebee wrote: post #254

It is impossible to be made less smart by not manually writing code. If it were possible, you would be stupider every time you go on vacation. Your brain's neuronal connections do not die from talking to a chat bot. What's actually happened is you took a break from a highly technical skill. Every person on the planet will "forget" some part of that technical skill if they don't use it in a while. But the information…

> It is impossible to be made less smart by not manually writing code. If it were possible, you would be stupider every time you go on vacation. Your brain's neuronal connections do not die from talking to a chat bot.

What if everytime you went on vacation, 80% of your open work items were magically completed?

Why would you give yourself a refresher? Not you specifically, of course. This thought experiment is about what we would all do in the aggregate.

Re: AI is making me dumb

#315

Post by KurSix »

ryandrake wrote: post #72
Rooster61 wrote: post #11

I can't relate that much to this. Every time I use AI to write code, I'm constantly fighting a feeling on the back of my neck that I need to look over everything it has done and supplement/alter it with my own code. That ick feeling counteracts the dopamine hit of having a working app after a few minutes of vibe coding, and I don't think that's going anywhere anytime soon. That said, I have experience. I could absolu…

In my experience, Claude only knows how to spew code. Every problem you want it to solve, it translates into "more code" rather than "less code". You have to very closely code review everything it does, otherwise your codebase is going to just grow and grow, and asymptotically approach 100% debt. I code review everything that Claude produces, and I'd estimate about 90-95% of the time, my reaction is WOW it works but…

[dead]

Re: AI is making me dumb

#316

Post by KurSix »

cub-creature wrote: post #174
thisisthenewme wrote: post #126

As a developer, I kind of feel like this all smells like job security. After using LLMs for a while, I have to admit it's pretty nice, and I like using it. I've been vibecoding a few apps, and it's a good dopamine hit to immediately see your ideas come to life. However, based on my experience, it will bite you if you trust it blindly. Even in my vibecoded projects, it keeps adding "features" without me asking for the…

While I agree with the general sentiment that decentralized, bespoke solutions will explode, and require some maintenance (which may in-turn result in more hiring), I've seen plenty that still makes me hesitant to fully embrace this idea as likely. I know this is a wall of text, so forgive me while I doom-post my thoughts for a few minutes: For one thing, the efficiency gains are massive. Bigger than any other tool,…

[flagged]

Re: AI is making me dumb

#317

Post by luodaint »

Those sessions which stayed together had something in common: singularity of concern. 1 session = 1 feature, 1 bug, 1 migration. As soon as you have a session covering several subsystems, the diff becomes too large to read properly, and proper reading is the only thing keeping the mental model up-to-date.

Also useful: writing the constraint before the session, not after the failure. "The auth state should be checked on the route level rather than the component" becomes quite clear once you see an agent applying the same rule in three slightly different ways in two files. Writing down the constraint beforehand allows you to detect the violation; rubber-stamping achieves nothing.

What really multiplies in value is not prompting but understanding your own system enough to prompt the agent properly.

Re: AI is making me dumb

#318

Post by davebren »

mholm wrote: post #283
davebren wrote: post #250

Earlier quoted context omitted.

Please stop pushing the "getting left behind" fear. Prompting is not a skill, there is nowhere it's going that it can leave anyone behind. The "skill" of prompting is 100% dependent on one's skill programming, and in a day the skilled programmer will be able to surpass the guy that's been vibecoding for a decade.

I've seen a lot of people hop into prompting with no trouble, and people who have been using it for years that get bad results. Ultimately, prompting skill is just downstream of technical communication skill. It's probably a good way to practice, if you pay close attention to what you forgot to specify, and what the model got wrong.

Programming is the ultimate exercise in technical communication, even if we remove the aspect of communicating about the software to other programmers or non-programmers. It's not just communicating to the machine. The architecture, organization, whitespace, naming, it's all about technical communication.

Re: AI is making me dumb

#319

Post by stevepotter »

Rooster61 wrote: post #11

I can't relate that much to this. Every time I use AI to write code, I'm constantly fighting a feeling on the back of my neck that I need to look over everything it has done and supplement/alter it with my own code. That ick feeling counteracts the dopamine hit of having a working app after a few minutes of vibe coding, and I don't think that's going anywhere anytime soon. That said, I have experience. I could absolu…

I'm the same way, which makes sense because for 20 years I've done things by hand, tediously managing every line.

I hired a few fresh grads and they have no problem just going with the default AI output. As long as it works, they are good.

For me, it comes down to the ability to properly test. If the code works, is covered by tests, and its performance is measured for regressions, and the high level design is sound, it's hard to argue with vibing. The problem is almost nobody has such a testing system. They are still hard to find and/or build. So that's what I'm putting my effort into because otherwise I'll have trouble sleeping at night (for good reason)

Re: AI is making me dumb

#320

Post by eric_cc »

ryandrake wrote: post #72
Rooster61 wrote: post #11

I can't relate that much to this. Every time I use AI to write code, I'm constantly fighting a feeling on the back of my neck that I need to look over everything it has done and supplement/alter it with my own code. That ick feeling counteracts the dopamine hit of having a working app after a few minutes of vibe coding, and I don't think that's going anywhere anytime soon. That said, I have experience. I could absolu…

In my experience, Claude only knows how to spew code. Every problem you want it to solve, it translates into "more code" rather than "less code". You have to very closely code review everything it does, otherwise your codebase is going to just grow and grow, and asymptotically approach 100% debt. I code review everything that Claude produces, and I'd estimate about 90-95% of the time, my reaction is WOW it works but…

Multiple rounds of specialized sub agent peer reviews that are prompted to counter this works really well. Once you have the right pipeline in place you should not be needing to do the simplifying yourself very often.

Claude -> specialized sub agents peer review -> specialized sub agents peer review -> repeat as many times as needed

It’s not worth your time until you’ve run through such a pipeline.

Post reply on HN