We put a coding agent in a while loop • Hacker News Board

Re: We put a coding agent in a while loop

#221

Post by __MatrixMan__ » Mon, Aug 25, 2025, 2:14 PM UTC

gardnr wrote: post #116

__MatrixMan__ wrote: post #94

Earlier quoted context omitted.

If it can run kubectl it can run any other command too. Unless you're running it as a different user and have put a bit of thought into limiting what that user can do, that's likely too much leeway. That's only really relevant I'd you're leaving it unattended though.

You can control it with hooks. Most people I know run in yolo mode in a docker container.

What about being in a docker container lets you `kubectl get pod` but prevents you from `kubectl delete deployment`?

Re: We put a coding agent in a while loop

#222

Post by dpoloncsak » Mon, Aug 25, 2025, 2:14 PM UTC

pelario wrote: post #191

Cthulhu_ wrote: post #148

Earlier quoted context omitted.

> and it will be harder to find someone to talk to understand what they were trying to do at the time. This will be the big counter to AI generated tools; at one point they become black boxes and the only thing people can do is to try and fix them or replace them altogether. Of course, in theory, AI tooling will only improve; today's vibe coded software that in some cases generate revenue can be fed into the models o…

> Personally, I hate it; I don't like magic or black boxes. So, no compilers for you neither ? (To be fair: I'm not loving the whole vibe coding thing. But I'm trying to approach this wave with open mind, and looking for the good arguments in both side. This is not one of them)

I think you're misunderstanding. AI is not a black-box, and neither is a compiler. We(as a species) know how they work, and what they do.

The 'black-boxes' are the theoretical systems non-technical users are building via 'vibe-coding'. When your LLM says we need to spin up an EC2 instance, users will spin one up. Is it configured? Why is it configured that way? Do you really need a VPS instead of a Pi? These are questions the users, who are building these systems, won't have answers to.

Re: We put a coding agent in a while loop

#223

Post by sdeframond » Mon, Aug 25, 2025, 2:15 PM UTC

thyristan wrote: post #196

sdeframond wrote: post #192

Earlier quoted context omitted.

> Problem is How much is it a problem, really ? I mean, what are the alternatives ?

The alternative is obviously: Do it right on the first try. How much of a problem it is can be seen with tons of products that are crap on release and only slowly get patched to a half-working state when the complaints start pouring in. But of course, this is status quo in software, so the perception of this as a problem among software people isn't universal I guess.

Sure.

How about the tons of products we don't even see? Those that tried to do it right on the first try, then never delivered anything because there were too slow and expensive. Or those that delivered something useless because they did not understand the users' need.

If "complaints start pouring in", that means the product is used. This in turns can mean two things: 1/ the product is actually useful despite its flaws, or 2/ the users have no choice, which is sad.

Re: We put a coding agent in a while loop

#224

Post by mring33621 » Mon, Aug 25, 2025, 2:18 PM UTC

ghuntley wrote: post #220

sunir wrote: post #219

I have been developing long lived self-directing agent loops. Longest with problem solving has been about 4 hours. Longest without problem solving has been nearer 8 hours until it was done. The biggest problem is simply what we think is clear is confusing to the AIs. They seem like they speak English fluently but they are aliens. You need to force them to active listen first and write out what they understand then re…

> So it’s better to work on problems that get progressively more complete towards a known objective rather than problems that require exploration. Yes. The longest I've had a self-directing agent loop running is a cumulative of three months. One goal, one purpose. Every now and then I modify the prompt in the background, and the agent picks up the updated prompt on the next loop.

very interesting!

how's it doing?

are you making progress toward your goal?

Re: We put a coding agent in a while loop

#225

Post by mring33621 » Mon, Aug 25, 2025, 2:20 PM UTC

ofjcihen wrote: post #101

discordance wrote: post #98

Earlier quoted context omitted.

Would love to hear more about your work and how you have tapped into that market if you're keen to share. Even if it's just anecdotes about vibe-in-production gone wrong, that would be really entertaining.

Absolutely. Before vibe coding became too much of a thing we had the majority of our business coming from poorly developed web applications coming from off shore shops. That’s been more or less the last decade. Once LLMs became popular we started to see more business on that front which you would expect. What we didn’t expect is that we started seeing MUCH more “deep” work wherein the threat actor will get into core…

please mention your company

if you have been doing this for some years, i'm gonna guess that you're good at it

and that there are plenty of potential customers here that could use your help

Re: We put a coding agent in a while loop

#226

Post by ofjcihen » Mon, Aug 25, 2025, 2:23 PM UTC

mring33621 wrote: post #225

ofjcihen wrote: post #101

Earlier quoted context omitted.

Absolutely. Before vibe coding became too much of a thing we had the majority of our business coming from poorly developed web applications coming from off shore shops. That’s been more or less the last decade. Once LLMs became popular we started to see more business on that front which you would expect. What we didn’t expect is that we started seeing MUCH more “deep” work wherein the threat actor will get into core…

please mention your company if you have been doing this for some years, i'm gonna guess that you're good at it and that there are plenty of potential customers here that could use your help

I’d love to but unfortunately I can be pretty inflammatory online and I’d like to continue using this account for personal opinions =]

Re: We put a coding agent in a while loop

#227

Post by _mocha » Mon, Aug 25, 2025, 2:27 PM UTC

I'm retired from the industry, and posts like these take me back to the early days of cybersecurity (where people memorized scripts). Talking with my nephews and nieces, I can already tell that many new grads struggle with fundamentals—things like choosing the right data types and containers for short-lived strings, understanding how memory allocation works, or even marginally improving a basic hashing function. I worry the next decade will bring an influx of undertrained engineers.

Re: We put a coding agent in a while loop

#228

Post by klysm » Mon, Aug 25, 2025, 2:31 PM UTC

_mocha wrote: post #227

I'm retired from the industry, and posts like these take me back to the early days of cybersecurity (where people memorized scripts). Talking with my nephews and nieces, I can already tell that many new grads struggle with fundamentals—things like choosing the right data types and containers for short-lived strings, understanding how memory allocation works, or even marginally improving a basic hashing function. I wo…

I agree understanding how memory allocation works, but not sure I would agree that understanding how to _improve_ a basic hashing function is very important.

Re: We put a coding agent in a while loop

#229

Post by jack_h » Mon, Aug 25, 2025, 2:40 PM UTC

Cthulhu_ wrote: post #148

VincentEvans wrote: post #12

There will be a a new kind of job for software engineers, sort of like a cross between working with legacy code and toxic site cleanup. Like back in the day being brought in to “just fix” a amalgam of FoxPro-, Excel-, and Access-based ERP that “mostly works” and only “occasionally corrupts all our data” that ambitious sales people put together over last 5 years. But worse - because “ambitious sales people” will no lo…

> and it will be harder to find someone to talk to understand what they were trying to do at the time. This will be the big counter to AI generated tools; at one point they become black boxes and the only thing people can do is to try and fix them or replace them altogether. Of course, in theory, AI tooling will only improve; today's vibe coded software that in some cases generate revenue can be fed into the models o…

> or replace them altogether.

Before AI companies were usually very reticent to do a rewrite or major refactoring of software because of the cost but that calculus may change with AI. A lot of physical products have ended up in this space where it's cheaper to buy a new product and throw out the old broken one rather than try and fix it. If AI lowers the cost of creating software then I'm not sure why it wouldn't go down the same path as physical goods.

Re: We put a coding agent in a while loop

#230

Post by dhorthy » Mon, Aug 25, 2025, 2:49 PM UTC

Syntaf wrote: post #188

dhorthy wrote: post #29

Earlier quoted context omitted.

When Claude starts deploying Kafka clusters I’m outro

I allowed Claude to debug an ingress rule issue on my cluster last week for a membership platform I run. Not really the same since Claude didn’t deploy anything — but I WAS surprised at how well it tracked down the ingress issue to a cron job accidentally labeled as a web pod (and attempting to service http requests). It actually prompted me to patch the cron itself but I don’t think I’m that bullish yet to let CC pa…

oh yeah we had claude diagnose a production k8s redis outage last week (figured out that we needed to launch a new instance in a new AZ to pick up the previous redis' AZ-scoped EBS PVC after a cluster upgrade).