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

Agents that run while I sleep

claudecodecamp.com

Post reply on HN
Print view View original

501–510 of 532 posts

Re: Agents that run while I sleep

#501

Post by JumpCrisscross »

cherk3 wrote: post #236
timr wrote: post #211

Earlier quoted context omitted.

> A lot of what one previously needed a SWE to do can now be brute forced well enough with AI. (Granted, everything SWEs complained about being tedious.) Only if you ignore everything they generate. Look at all the comments saying that the agent hallucinates a result, generates always-passing tests, etc. Those are absolutely true observations -- and don't touch on the fact that tests can pass, the red/green approach…

What I want to know is, what has this increase in code generation led to? What is the impact? I don't mean 'Oh I finally have the energy to do that side project that I never could'. Afterall, the trade-offs have to be worth something... right? Where's the 1-person billion dollar firms at That Mr Altman spoke about? The way I think of it is code has always been an intermediary step between a vision and an object of va…

> what has this increase in code generation led to?

Every restaurant in my small town has their menu on the website in a normal way. Apparently someone figured out you can take a picture of a paper menu and have AI code it into HTML.

Re: Agents that run while I sleep

#502

Post by theshrike79 »

godelski wrote: post #490
theshrike79 wrote: post #296

Earlier quoted context omitted.

When you write tests with LLM-generated code you're not trying to prove correctness in a mathematically sound way. I think of it more as "locking" the behavior to whatever it currently is. Either you do the red-green-with-multiple-adversarial-sub-agents -thing or just do the feature, poke the feature manually and if it looks good then you have the LLM write tests that confirm it keeps doing what it's supposed to do.…

> you're not trying to prove correctness in a mathematically sound way. > "locking" the behavior to whatever it currently is. These two sentences are incompatible > The #1 reason TDD failed is Because spec is an ever evolving thing that cannot be determined a priori. And because it highly incentivized engineers to metric hack. > It's a bunch of repetition with slight variations If that's how you're writing tests then…

Locking behavior with tests isn't the same as comprehensive and foolproof tests. They might not cover every edge case, but will fail if the happy path starts failing for some reason.

And yes, copy-pasting is a horrendous way to write code, but everyone does it.

When you're adding the 1600th CRUD endpoint of your career to an enterprise Java/C# application, can you with all honesty say you will type every single character with the same thought and consideration every time?

Or do you just make one, copy-paste that one and modify accordingly?

Or if you write 20 unit tests with slight alterations you masterfully craft every single character to perfection?

I have a limited amount of energy to use every day, I choose to use it in places that matter. The hard bits that LLMs and copy-pasting can't speed up.

Re: Agents that run while I sleep

#503

Post by jhaugh »

arkits wrote: post #401
jhaugh wrote: post #389

I'm running 8 specialized AI agents on a Mac Mini right now. They handle research, content strategy, writing, security audits, code, and visual design. They run on cron schedules, have persistent memory between sessions, and each one improves weekly through self-improvement loops. The cost concern is real but manageable. The key is routing models by task. Complex reasoning gets Opus, routine work gets Sonnet, mechani…

Perhaps have your team look at the header colors on your website https://clelp.com/skill/4da37247-33ee-43ba-a004-0a89d84d3920

I kind of liked the old one, but after getting feedback from some other fiends in the community decided to change it. TY for the advice.

Re: Agents that run while I sleep

#504

Post by girvo »

silentsvn wrote: post #395
girvo wrote: post #198

Earlier quoted context omitted.

Interesting. I’ve been playing with something similar, at the coding agent harness message sequence level (memory, I guess). I’m looking at human driven UX for compaction and resolving/pruning dead ends

Human-driven compaction is interesting — you sidestep the "what's worth keeping" problem by putting a person in the loop. The tradeoff I've hit is that agents running autonomously need it to happen automatically or coherence degrades fast between sessions. For pruning we landed on a last-touched timestamp + recall frequency counter per memory. Things not accessed in N sessions that were weakly formed to begin with ge…

> The tradeoff I've hit is that agents running autonomously need it to happen automatically or coherence degrades fast between sessions.

Yeah that makes total sense. I wonder (and am sure the labs are doing so) if the HitL output would be good to fine tune the models used to do it autonomously?

I’m sticking with humans for the moment because I’m not sure where the boundaries lie: what actually makes it better and what makes it worse. It’s non obvious so far

Pruning “loops” has been pretty effective though, where a model gets stuck over N turns checking the same thing over and over and not breaking out of it til way later. That has been good because it gives strong context size benefits, but is also the most automatable I think

Pruning factually incorrect turns is something I’m trying, and pruning “correct” but “not correct based on my style” as well. Building a dataset of it all is fun :)

Re: Agents that run while I sleep

#505

Post by withinboredom »

arjvik wrote: post #242
jack_pp wrote: post #240

Earlier quoted context omitted.

I worked at a startup, they built their API in PHP because it was easy and fast. Now they're successful, app doesn't scale, high latency etc. What does their php code do? 95% of it is calling a DB. You're telling me today with LLM power multiplier it's THAT much faster to write in PHP compared to something that can actually have a future?

by future do you mean Future or metaphorical future? :)

I see what you did there.

Re: Agents that run while I sleep

#506

Post by withinboredom »

stavros wrote: post #484
ipaddr wrote: post #482

Earlier quoted context omitted.

PHP is faster to develop in then Pythin or JS then addin a framework like Laravel and you are already done. Python has the curse of spaces or tabs and JS has the curse of npm.

PHP has the curse of T_PAAMAYIM_NEKUDOTAYIM.

Wasn’t expecting to see Hebrew here today.

Re: Agents that run while I sleep

#507

Post by ruszki »

9wzYQbTYsAIc wrote: post #477
ruszki wrote: post #358

Earlier quoted context omitted.

Even cutting edge models are not very good. They are not even on mediocre level. Don’t get me wrong, they are improving, and they are awesome, but they are nowhere near good yet. Vibe coded projects have more bugs than features, their architecture and design system are terrible, and their tests are completely useless about half the time. If you want a good product you need to rewrite almost everything what’s written…

With Claude Code now having a /plan mode - you can take your time and deliberate through architecture and design, collaboratively, instead of just sending a fire-and-forget. Much less buggy and saves time if you keep an eye on the output as you go, guiding it and catching defects, imho.

For that you need to create something which you know exactly how you want to code, or what architecture is needed. In other words, you would win basically nothing, because typing was never the real bottleneck (no matter what VIM and Emacs people would tell you).

LLMs also make mistakes even way lower level than those one pagers allow you to control with the planning mode. Which I use all the time btw. And anyway, they throw the plan out of the window immediately when their tried solutions don't work during execution, for example when a generated test is failing.

Btw, changing the plan after its generation is painful. It happens more than not that when I decline it with comments it generates a worse version of it, because it either miss things from the previous one which I never mentioned, or changes the architecture to a worse one completely. In my experience, it's better to restart the whole thing with a more precise prompt.

Re: Agents that run while I sleep

#508

Post by 9wzYQbTYsAIc »

ruszki wrote: post #507
9wzYQbTYsAIc wrote: post #477

Earlier quoted context omitted.

With Claude Code now having a /plan mode - you can take your time and deliberate through architecture and design, collaboratively, instead of just sending a fire-and-forget. Much less buggy and saves time if you keep an eye on the output as you go, guiding it and catching defects, imho.

For that you need to create something which you know exactly how you want to code, or what architecture is needed. In other words, you would win basically nothing, because typing was never the real bottleneck (no matter what VIM and Emacs people would tell you). LLMs also make mistakes even way lower level than those one pagers allow you to control with the planning mode. Which I use all the time btw. And anyway, the…

Ah, this is true - for my purposes, I've been directing the design and deliberating on the constraints and specifications for a larger system in tandem with smaller planning sessions.

That has worked well so far, but yes, you are totally right, there are still quite a few pain points and it is still rather far from being fire-and-forget "build me a fancy landing page for a turnkey business" and getting enterprise quality code.

edit: I think it is most important that you collaborate with Claude Code on quality in a systematic way, but even that has limits, right now - 1M context changes things a little bit.

Re: Agents that run while I sleep

#509

Post by josephg »

godelski wrote: post #489
josephg wrote: post #297

Earlier quoted context omitted.

Testing works because tests are (essentially) a second, crappy implementation of your software. Tests only pass if both implementations of your software behave the same way. Usually that will only happen if the test and the code are both correct. Imagine if your code (without tests) has a 5% defect rate. And the tests have a 5% defect rate (with 100% test coverage). Then ideally, you will have a 5%^2 defect rate afte…

> Tests only pass if both implementations of your software behave the same way. That's not true. I even addressed this in my comment as did Dijkstra

What is untrue about this statement you quoted?

Re: Agents that run while I sleep

#510

Post by stavros »

withinboredom wrote: post #506
stavros wrote: post #484

Earlier quoted context omitted.

PHP has the curse of T_PAAMAYIM_NEKUDOTAYIM.

Wasn’t expecting to see Hebrew here today.

Eh, you know, when the conversation has devolved to the level of "Python is slower to develop in than PHP because of spaces or tabs", you have to bust out the Hebrew.
Post reply on HN