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

AI coding

geohot.github.io

Post reply on HN
Print view View original

111–120 of 299 posts

Re: AI coding

#111

Post by ChrisMarshallNY »

bdcravens wrote: post #25

I'm almost 50, and have been writing code professionally since the late 90s. I can pretty much see projects in my head, and know exactly what to build. I also get paid pretty well for what I do. You'd think I'd be the prototype for anti-AI. I'm not. I can build anything, but often struggle with getting bogged down with all the basic work. I love AI for speed running through all the boring stuff and getting to the goo…

I have a similar view of AI.

I find it best as a "personal assistant," that I can use to give me information -sometimes, highly focused- at a moment's notice.

> The potential for then stunting the growth of actual juniors into tomorrow's senior developers is a serious concern

I think it's a very real problem. I am watching young folks being frozen out of the industry, at the very beginning of their careers. It is pretty awful.

I suspect that the executives know that AI isn't yet ready to replace senior-levels, but they are confident that it will, soon, so they aren't concerned that there aren't any more seniors being crafted from youngsters.

Would suck, if they bet wrong, though…

Re: AI coding

#112

Post by skydhash »

giveita wrote: post #44

I have a boring opinion. A cold take? served straight from the freezer. He is right, however AI is still darn useful. He hints at why: patterns. Writing a test suite for a new class when an existing one is in place is a breeze. It even can come up with tests you wouldnt have thought of or would have been too time pressed to check. It also applies to non-test code too. If you have the structure it can knock a new one…

But what about the tests usefulness? Tests enforce contracts, contracts are about the domain, not the implementation. The number of tests don't actually matter as much as what is being actually verified. If you look at the code to know what to tests, you are doing it wrong.

Re: AI coding

#113

Post by rhizome31 »

croes wrote: post #97
hereme888 wrote: post #95

I'm a 100% vibe-coder. AI/CS is not my field. I've made plenty of neat apps that are useful to me. Don't ask me how they work; they just do. Sure the engineering may be abysmal, but it's good enough to work. It only takes basic english to produce these results, plus complaining to the AI agent that "The GUI is ugly and overcrowded. Make it look better, and dark mode." Want specs? "include a specs.md" This isn't a 20%…

The crucial part is security. If the apps runs locally it doesn’t matter, if it‘s connected to the net it could be the seed for the next Mirai bot network.

Apps running locally can also be subject to security issues. What you're trying to say is probably "apps not using untrusted input". If an app takes no input all, I guess we could say that security isn't an issue, but there could still be safety issues.

Re: AI coding

#114

Post by skydhash »

runningmike wrote: post #83

Great short read. But this “ It’s why the world wasted $10B+ on self driving car companies that obviously made no sense.” Not everything should make sense. Playing , trying and failing is crucial to make our world nicer. Not overthinking is key, see later what works and why.

> Playing , trying and failing is crucial to make our world nicer. Not overthinking is key, see later what works and why.

It would be, if there weren't actual important works that needs funding.

Re: AI coding

#115

Post by energy123 »

mindwok wrote: post #88

These articles are beyond the point of exhausting. Guys, just go use the tools and see if you like them and feel more capable with them. If you do, great, if you don’t, then stop.

The truth will emerge naturally through labor market competition in the long-run. You do you. I will be using these tools extensively. Good luck out there in the arena.

Re: AI coding

#116

Post by athrowaway3z »

vmg12 wrote: post #31

I think this gets to a fundamental problem with the way the AI labs have been selling and hyping AI. People keep on saying that the AI is actually thinking and it's not just pattern matching. Well, as someone that uses AI tools and develops AI tools, my tools are much more useful when I treat the AI as a pattern matching next-token predictor than an actual intelligence. If I accidentally slip too many details into th…

Both CRUD and boilerplate are arguably a tooling issue. But there are also a bunch of things only AI will let you do.

My tests with full trace level logging enabled can get very verbose. It takes serious time for a human to parse where in the 100 lines of text the relevant part is.

Just telling an AI: "Run the tests and identify the root cause" works well enough, that nowadays it is always my first step.

Re: AI coding

#117

Post by giveita »

skydhash wrote: post #112
giveita wrote: post #44

I have a boring opinion. A cold take? served straight from the freezer. He is right, however AI is still darn useful. He hints at why: patterns. Writing a test suite for a new class when an existing one is in place is a breeze. It even can come up with tests you wouldnt have thought of or would have been too time pressed to check. It also applies to non-test code too. If you have the structure it can knock a new one…

But what about the tests usefulness? Tests enforce contracts, contracts are about the domain, not the implementation. The number of tests don't actually matter as much as what is being actually verified. If you look at the code to know what to tests, you are doing it wrong.

The usefulness is in saving time boilerplating, plus figuring out tests I may not have thought of.

But I do closely review the code! It turns the usual drudge of writing tests into more of a code review. Last time I did it it had some mistakes I needed to fix for sure.

Re: AI coding

#118

Post by 8cvor6j844qw_d6 »

Just started using Claude Code recently.

It seems to speed up feature development but requires one to have a good understanding of the codebase to guide it and be aware of edge cases it missed.

Also, it doesn't seem to be able to take advantage of latest information or new SDK features unless deliberately informed. Not sure if I'm doing it right, but I resorted to feeding it documentation when it can't seem to something right.

The only thing I'm still unsure is the context management with /compact and /clear

Re: AI coding

#119

Post by hereme888 »

athrowaway3z wrote: post #110
hereme888 wrote: post #107

Earlier quoted context omitted.

What's the intent behind your question?

Evaluating your empirical experience by judging the complexity you're impressed by.

Valid inquiry. In relative terms I'm the Indian on a street corner who hacks things together using tools professionally designed by others. Among the repos I've chosen to publicly share: https://github.com/sm18lr88

Re: AI coding

#120

Post by abraxas »

apercu wrote: post #60
huevosabio wrote: post #51

There is some amount of truth on the AI coding claims. But, what's with the self driving hate? I take Waymos on a regular basis, and he is basing his credibility on the claim that they are not a thing. Makes him sound bitter more than insightful.

I think some of the “hate” is the hype. We’re all tired of companies announcing ground breaking tech that isn’t readily available a decade later. I don’t live in California (like most of the population of the planet) - Toronto for 18 years and now the American side of the Great Lakes. Ice storms, snow, sleet, cold weather 5-6 months out of the year. Batteries suck in the cold, sensors fail or under-perform. Hell, doo…

And that's just in North America where cities were built for cars and with cars in mind. Autonomous driving in Europe or Asia is likely a magnitude harder due to windy roads, non trivial intersections, complex interactions of humans, bikes, trams and cars etc.
Post reply on HN