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

AI handles incidents, engineers lose touch with their systems

sylvainkalache.com

Post reply on HN
Print view View original

241–250 of 375 posts

Re: AI handles incidents, engineers lose touch with their systems

#241

Post by bigstrat2003 »

eudamoniac wrote: post #237
LeafItAlone wrote: post #204

Earlier quoted context omitted.

Depends on the prior state. For one codebase I work in, LLM written code is noticeably and measurably (we have literally measured it for bugs, performance, etc.) better than what existed before. So the LLM code is a welcome change.

I find this shocking though not unbelievable. Could you share how you measure this accurately? I'm interested in integrating such measurements into our services as well.

I find it unbelievable. I've seen the code LLMs write and it sucks compared to what a typical human produces. The only way an LLM is doing better than human programmers is if your human programmers were producing really terrible work.

Re: AI handles incidents, engineers lose touch with their systems

#242

Post by spicyusername »

mcmcmc wrote: post #198
spicyusername wrote: post #195

Its true we will lose the skills, but so far the LLMs are more than picking up the slack when wielded competently. They _regularly_ go above and beyond when troubleshooting and frequently in 1/2 - 1/1000th of the time. I remember spending entire days troubleshooting in the before times. Now it's like 30 minutes, tops, on literally any issue. This is what progress looks like. We used to do a thing and now we don't.

> when wielded competently. And what happens when the competency drains away?

That's what everyone's learning to do now, that is the skill that people will be improving.

Re: AI handles incidents, engineers lose touch with their systems

#243

Post by spicyusername »

2sk21 wrote: post #230
spicyusername wrote: post #195

Its true we will lose the skills, but so far the LLMs are more than picking up the slack when wielded competently. They _regularly_ go above and beyond when troubleshooting and frequently in 1/2 - 1/1000th of the time. I remember spending entire days troubleshooting in the before times. Now it's like 30 minutes, tops, on literally any issue. This is what progress looks like. We used to do a thing and now we don't.

Who is going to teach programmers to wield AI competently?

That's what everyone's learning to do now, that is the skill that people will be improving.

Re: AI handles incidents, engineers lose touch with their systems

#244

Post by LeafItAlone »

eudamoniac wrote: post #237
LeafItAlone wrote: post #204

Earlier quoted context omitted.

Depends on the prior state. For one codebase I work in, LLM written code is noticeably and measurably (we have literally measured it for bugs, performance, etc.) better than what existed before. So the LLM code is a welcome change.

I find this shocking though not unbelievable. Could you share how you measure this accurately? I'm interested in integrating such measurements into our services as well.

We’ve been tracking performance and bugs for years. Including commits those bugs were introduced in. So when LLM-generated code started working its way into our codebases, we have the before and after. And even comparing human generated code today with LLM-generated code today.

Re: AI handles incidents, engineers lose touch with their systems

#245

Post by marcosdumay »

bob1029 wrote: post #6

A natural evolution of engineers losing touch with the customers and users. I'm noticing some of the concern play out regarding AI weakening the capabilities of software people. I gave the team an exact solution on a silver platter and they still failed to identify how to go about it after 3 days slamming it into Claude. The resolution is literally 1 line of code that could be arrived at in about 30 minutes of patien…

That happens all the damn time... Some otherwise competent developer decides to use AI, and falls into the pattern where AI will pretend to solve their problem for a week, while if they would have to think about it for an entire long hour to discover how to solve it by themselves.

As a bonus, that person will spend half of the week asking their peers for crazy delusional stuff.

Re: AI handles incidents, engineers lose touch with their systems

#246

Post by mattm »

DiggyJohnson wrote: post #42
mawadev wrote: post #25

Earlier quoted context omitted.

I can share a weird story: Usually, I take my time to understand each keyword of the code I'm looking at, especially if it is new to me, like terraform. I work in a team/with one architect, who only did the DevOps/Infra stuff for the past years and I had the expectation he knows what he is doing and talking about. At around 2 weeks, I noticed how his knowledge has severe gaps and how he takes things at face value or…

You captured this phenomenon very well in this comment. Appreciate you sharing it because it’s hard to describe exactly what makes this sort of behavior so bizarre.

@backlava12 fyi your comments are all dead in this thread

Re: AI handles incidents, engineers lose touch with their systems

#247

Post by budman1 »

noir_lord wrote: post #127
adjejmxbdjdn wrote: post #35

Earlier quoted context omitted.

The funny thing is that if you never understand the codebase then you will keep thinking Claude is doing a great work delivering all this incredible software, when all it has done is created unnecessary tech debt.

Which at some point the developers who actually still do know how to program are either going to have to clean up or in terminal cases rewrite. In a way all we've done (currently) is drastically expand the amount of technical debt across the whole industry. Should be profitable for the ones who can still actually program though and haven't let their skills atrophy by letting Claude do everything . I don't deny there…

2040.

The demand for real programming skills will become infinite (again).

someone who can actually read, understand, and debug code. when the clankers get stuck.

unfortunately, there will be only be a dozen people.

Re: AI handles incidents, engineers lose touch with their systems

#248

Post by budman1 »

lmf4lol wrote: post #165
ilija139 wrote: post #91

Earlier quoted context omitted.

I have also a weird story to tell that a human did and it is as crazy as this. It happen in 2019 so no LLMs at all. A person that was hired as an expert in our startup spent more than one week full time working on implementing his solution to the problem we were having. I checked the code after one week to see the progress and was curious how they are implementing an already crazy sounding idea. I found that the whol…

Jesus Christ... and then? What happened to him? What was the conclusion? Did he get paid?

of course he got paid.

that is the deal for an employee, you put in the hours, you get a check.

today, this individual is CTO- Vibecoding at Uber.

Re: AI handles incidents, engineers lose touch with their systems

#249

Post by revetkn »

bigstrat2003 wrote: post #241
eudamoniac wrote: post #237

Earlier quoted context omitted.

I find this shocking though not unbelievable. Could you share how you measure this accurately? I'm interested in integrating such measurements into our services as well.

I find it unbelievable. I've seen the code LLMs write and it sucks compared to what a typical human produces. The only way an LLM is doing better than human programmers is if your human programmers were producing really terrible work.

What LLM/harness are you using that the results are so terrible?
Post reply on HN