News for hackers. Stuff that matters.
Re:AI Agents: Less Capability, More Reliability, Please by joshdavham on Monday March 31, 2025 @11:35AM (#43536242)
My rule of thumb has thus far been: if I’m gonna allow AI to write any bit of code for me, then I must, at a bare minimum, be able to understand that code.

There’s no way I could do what some of these “vibe coders” are doing where they allow AI to write code for them that they don’t even understand.

Re:AI Agents: Less Capability, More Reliability, Please by AlexandrB on Monday March 31, 2025 @12:04PM (#43536559)
I think there's a lot of code that gets written that's either disposable or effectively "write only" in that no one is expected to maintain it. I have friends who write a lot of this code for tasks like data analysis for retail and "vibe coding" isn't that crazy in such a domain.

Basically, what's worse? "Vibes" code that no one understands or a cascade of 20 spreadsheets that no one understands? At least with the "vibes" code you can stick it in git and have some semblance of sane revision control and change tracking.

Re:AI Agents: Less Capability, More Reliability, Please by pton_xd on Monday March 31, 2025 @12:16PM (#43536711)
> I have friends who write a lot of this code for tasks like data analysis for retail and "vibe coding" isn't that crazy in such a domain.

That sort of makes sense, but then again... if you run some analysis code and it spits out a few plots, how do you know what you're looking at is correct if you have no idea what the code is doing?

Re:AI Agents: Less Capability, More Reliability, Please by kibwen on Monday March 31, 2025 @01:15PM (#43537346)
> how do you know what you're looking at is correct if you have no idea what the code is doing?

Does it reaffirm the biases of the one who signs my paychecks? If so, then the code is correct.

Re:AI Agents: Less Capability, More Reliability, Please by AlexandrB on Monday March 31, 2025 @02:24PM (#43538069)
Lol, that's definitely a factor. Actually plotting is the perfect example because python is really popular in the space and matplotlib sucks so much. While an analyst may not understand Python very well, they often understand the data itself through either previous projects or through other analysis tools. It's kind of like vibe coding a UI for a backend that's hand built.
Re:AI Agents: Less Capability, More Reliability, Please by usui on Monday March 31, 2025 @02:14PM (#43537964)
LOL thanks for the laughs. But yes seriously though, most kinds of data analysis jobs several rungs down the ladder where the result is not in a critical path amount to reaffirming what upper people believe. Don't rock the boat.
Re:AI Agents: Less Capability, More Reliability, Please by Centigonal on Monday March 31, 2025 @12:09PM (#43536629)
> I have friends who write a lot of this code for tasks like data analysis for retail and "vibe coding" isn't that crazy in such a domain.

I think this is a great use case for AI, but the analyst still needs to understand what the code that is output does. There are a lot of ways to transform data that result in inaccurate or misleading results.

Re:AI Agents: Less Capability, More Reliability, Please by LPisGood on Monday March 31, 2025 @12:15PM (#43536694)
Vibe coders focus on writing tests, and verifying function/correctness. It’s not like they don’t read _any_ of the code. They get the vibes, but ignore the details.
Re:AI Agents: Less Capability, More Reliability, Please by cube00 on Monday March 31, 2025 @01:12PM (#43537314)
> Vibe coders focus on writing tests

From the boasting I've seen, Vibe coders are also using AI to slop out their tests as well.

Re:AI Agents: Less Capability, More Reliability, Please by kibwen on Monday March 31, 2025 @01:16PM (#43537365)
Worry not, we can solve this by using AI to generate tests to test the tests.
Re:AI Agents: Less Capability, More Reliability, Please by LPisGood on Monday March 31, 2025 @05:28PM (#43540188)
Testing the tests is pretty much the definition of being a vibe coder.
Re:AI Agents: Less Capability, More Reliability, Please by LPisGood on Monday March 31, 2025 @05:27PM (#43540179)
Yeah and tests are much easier to validate than functions.
Re:AI Agents: Less Capability, More Reliability, Please by hooverd on Monday March 31, 2025 @02:05PM (#43537895)
Huh. The whole promise of vibe coding is that you don't have to pay attention to the details.
Re:AI Agents: Less Capability, More Reliability, Please by namaria on Monday March 31, 2025 @02:24PM (#43538058)
"You're programming wrong wrong" /s
Re:AI Agents: Less Capability, More Reliability, Please by LPisGood on Monday March 31, 2025 @05:26PM (#43540165)
Yeah, of course. I don’t think what I described could possibly be misconstrued as someone paying attention to details.
Re:AI Agents: Less Capability, More Reliability, Please by achierius on Monday March 31, 2025 @09:34PM (#43541938)
This seems optimistic -- prescriptive, rather than descriptive. From what I've observed, vibe coders largely do not include tests; they do verify functionality/correctness, but not rigorously or repeatably.
Re:AI Agents: Less Capability, More Reliability, Please by liveoneggs on Monday March 31, 2025 @12:32PM (#43536898)
two wrongs don't make a right
Re:AI Agents: Less Capability, More Reliability, Please by cube00 on Monday March 31, 2025 @01:11PM (#43537300)
> I have friends who write a lot of this code for tasks like data analysis for retail and "vibe coding" isn't that crazy in such a domain

Considering the hallucinations we've all seen I don't know how they can be comfortable using AI generated data analysis to drive the future direction of the business.

Re:AI Agents: Less Capability, More Reliability, Please by inetknght on Monday March 31, 2025 @01:13PM (#43537330)
> what's worse? "Vibes" code that no one understands or a cascade of 20 spreadsheets that no one understands? At least with the "vibes" code you can stick it in git and have some semblance of sane revision control and change tracking.

You can for spreadsheets too.

Re:AI Agents: Less Capability, More Reliability, Please by palmotea on Monday March 31, 2025 @01:26PM (#43537477)
> think there's a lot of code that gets written that's either disposable or effectively "write only" in that no one is expected to maintain it. I have friends who write a lot of this code for tasks like data analysis for retail and "vibe coding" isn't that crazy in such a domain.

> Basically, what's worse? "Vibes" code that no one understands or a cascade of 20 spreadsheets that no one understands?

Correction: it's a "cascade of 20 spreadsheets" that one person understood/understands.

Write only code still needs to work, and someone at some point needs to understand it well enough to know that it works.

Re:AI Agents: Less Capability, More Reliability, Please by kevmo314 on Monday March 31, 2025 @11:56AM (#43536457)
That's only true as long as you want to modify said code. If it meets your bar for reliability then you won't need to understand it, much like how we don't really need to read/understand compiled assembly code so we largely trust the compiler.

A lot of these vibe coders just have a much lower bar for reliability than you.

Re:AI Agents: Less Capability, More Reliability, Please by fourside on Monday March 31, 2025 @12:09PM (#43536626)
How do you know if it meets your bar for reliability if you don’t understand the output? I don’t know that the analogy to a compiler is apples to apples. A compiler isn’t producing an answer based on statistically generating something that should look like the right answer.
Re:AI Agents: Less Capability, More Reliability, Please by kevmo314 on Monday March 31, 2025 @12:38PM (#43536977)
The premise for vibe coding is that it's generating the entire app or site. If the app does what you want then it's meeting the bar.
Re:AI Agents: Less Capability, More Reliability, Please by joshdavham on Monday March 31, 2025 @02:59PM (#43538484)
This is an interesting point and it's certainly true with respect to most peoples' attitudes towards dependencies.

For example, while I feel the need to understand the code I wrote using pytorch, I don't generally feel the need to totally grok how pytorch works.

Re:AI Agents: Less Capability, More Reliability, Please by SkyPuncher on Monday March 31, 2025 @01:42PM (#43537637)
Sure, but you're a professional software engineer, who I assume gets feedback and performance reviews based on the quality of your code.

There's always been a group of beginners that throws stuff together without fully understanding what it does. In the past, this would be copy n' paste from Stackoverflow. Now, that process is simply more automated.

Re:AI Agents: Less Capability, More Reliability, Please by __jochen__ on Monday March 31, 2025 @09:11PM (#43541810)
There is also likely to be increased pressure in a SE job to produce more code. You'll find that if others use AI, it'll be hard to be a hold-out and hit fewer delivery milestones, and quality is hard to measure. People are rewarded for shipping, primarily (unless you're explicitly working on high reliability/assurance products).
Re:AI Agents: Less Capability, More Reliability, Please by __MatrixMan__ on Monday March 31, 2025 @03:09PM (#43538600)
I think there are times where it's ok to treat a function like a black box--cases where anything that makes the test pass will do because the test is in fact an exhaustive evaluation of what that code needs to do.

We just need to be better about making it clear which code is that way and which is not.