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

451–460 of 532 posts

Re: Agents that run while I sleep

#451

Post by jimmyjazz14 »

recroad wrote: post #83

Am I supposed to be impressed by this? I think people are now just using agents for the sake of it. I'm perfectly happy running two simple agents, one for writing and one for reviewing. I don't need to go be writing code at faster than light speed. Just focusing on the spec, and watching the agent as it does its work and intervening when it goes sideways is perfectly fine with me. I'm doing 5-7x productivity easily,…

agreed, honestly if I see my agent "run" for more than 5 minutes or so I get very suspicious that its doing anything of value other than burning credits because more often than not its just talking to its self or running in loops. I also find the whole multi-agent stuff to be suspect most the time, I don't know that I have seen multiple agents running in parallel do anything that a single agent with good guidance couldn't do synchronously in about the same amount of time.

Re: Agents that run while I sleep

#452

Post by lagrange77 »

taneq wrote: post #237
nurettin wrote: post #64

Earlier quoted context omitted.

They probably meant goal hacking. (I just made that up)

I refer to it as ‘wanking’. It’s doing something that’s unproductive but that’s incentivised by its architecture.

I'll use that term from now on. :D

Re: Agents that run while I sleep

#453

Post by snoman »

lugu wrote: post #338
brobdingnagians wrote: post #300

Earlier quoted context omitted.

I would encourage my competitors to use AI agents on their codebase as much as possible. Make sure every new feature has it, lots of velocity! Run those suckers day and night. Don't review it, just make sure the feature is there! Then when the music stops, the AI companies hit the economic realities, go insolvent, and they are left with no one who understands a sprawling tangled web of code that is 80% AI generated,…

Both be true at the same time: some teams spend a fortune on AI and the AI investments won't get the expected ROI (bubble collapse). What is sure is that a lot of capacity is been built and that capacity won't disappear. What I could see happening in your scenario is the company suffers from diminishing return as every task becomes more expensive (new feature, debugging session, library update, refactoring, security…

> What is sure is that a lot of capacity is been built and that capacity won't disappear.

They really are subsidizing what will be an incredibly healthy used server equipment market in a year or two. Can’t wait. My homelab is going to be due for an upgrade.

Re: Agents that run while I sleep

#454

Post by viccis »

serial_dev wrote: post #246
hi_hi wrote: post #206

This _all_ (waves hands around) sounds like alot of work and expense for something that is meant to make programming easier and cheaper. Writing _all_ (waves hands around various llm wrapper git repos) these frameworks and harnesses, built on top of ever changing models sure doesn't feel sensible. I don't know what the best way of using these things is, but from my personal experience, the defaults get me a looong wa…

> sounds like alot of work and expense for something that is meant to make programming easier and cheaper. Not if you are an AI gold rush shovel salesman. From the article: > I've run Claude Code workshops for over 100 engineers in the last six months

Reminds me of when I was looking for Obsidian note management workflows and every single person who posted about theirs used it to take notes on... note taking workflows.

Re: Agents that run while I sleep

#455

Post by aray07 »

palmotea wrote: post #446
nananana9 wrote: post #406

Earlier quoted context omitted.

Yes, but given a feature that should take say 100 lines of code, the average programmer will write in the order of 100 to 500 lines. If they're a heavy OOP user, maybe they'll write 10 classes that total 2000 lines. Regardless, worst case, it will be within ~2 orders of magnitude of a reasonable solution. It's not that they're not trying to write the biggest clusterfuck possible and maximize suffering in the world, i…

> it's just that there's a human limit on how much garbage they can type out in their allocated time. Another example where removing friction and constraints is a bad thing.

i think the friction has moved upstream - now it's working on the right thing and specifying what correct looks like. i don't think we are going back to a world where we will write code by hand again.

Re: Agents that run while I sleep

#456

Post by teejmya »

misja111 wrote: post #322
wesselbindt wrote: post #133

Does anyone know what this guy is having his agents build? Bc I looked a bit and all I see him ship is linkedin posts about Claude.

I can't imagine he's building anything serious. How can you claim otherwise that your agents were deploying code that you couldn't verify. Imagine doing that in any serious business ..

It's okay, you don't have to imagine anymore...

https://news.ycombinator.com/item?id=47324211

Re: Agents that run while I sleep

#457

Post by aray07 »

josephg wrote: post #297
godelski wrote: post #263

Earlier quoted context omitted.

I can't believe we're back to advocating for TDD. It was a failed paradigm that last few times we tried it. This time isn't any different because the fundamental flaw has always been the same: tests aren't proofs, they don't have complete coverage. Before anyone gets too confused, I love tests. They're great. They help a lot. But to believe they prove correctness is absolutely laughable. Even the most general tests a…

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…

This is great. The tests in this case are the spec. When you give the agent something concrete to fail against, it knows what done looks like.

The problem is if you skip that step and ask Claude to write the tests after.

Re: Agents that run while I sleep

#458

Post by aray07 »

alexey-pelykh wrote: post #428
p0w3n3d wrote: post #284

Earlier quoted context omitted.

Yeah, my colleague recently said "hey I've burnt through $200 in Claude in 3 days". And he was prompting. Max 8hrs/day Imagine what would happen if AI was prompting. As I like this allegory really much, AI is (or should be) like and exoskeleton, should help people do things. If you step out of your car putting it first in drive mode, and going to sleep, next day it will be farther, but the question is, is it still on…

[dead]

Agreed. The spec file is context. Writing acceptance criteria before you prompt provides the context the agent needs to not go off in the wrong direction. Human leverage just moved up and the plan/spec is the most important step.

Parallelism on top of bad context just gets you more wrong answers faster

Re: Agents that run while I sleep

#459

Post by aray07 »

seer wrote: post #228
egeozcan wrote: post #65

Earlier quoted context omitted.

The trick is, with the setup I mentioned, you change the rewards. The concept is: Red Team (Test Writers), write tests without seeing implementation. They define what the code should do based on specs/requirements only. Rewarded by test failures. A new test that passes immediately is suspicious as it means either the implementation already covers it (diminishing returns) or the test is tautological. Red's ideal outco…

This seems quite amazing really, thanks for sharing What is the scope of projects / features you’ve seen this be successful at? Do you have a step before where an agent verifies that your new feature spec is not contradictory, ambiguous etc. Maybe as reviewed with regards to all the current feature sets? Do you make this a cycle per step - by breaking down the feature to small implementable and verifiable sub-feature…

I do it per feature, not per step. Write the AC for the whole feature upfront, then the agent builds against it. I haven't added a spec-validation step before coding but that's a good idea. Catching ambiguity in the spec before the agent runs with it would save a lot of rework

Re: Agents that run while I sleep

#460

Post by aray07 »

jakevoytko wrote: post #376
voidUpdate wrote: post #327

Earlier quoted context omitted.

Its for when you want to write an spec like "make me a todo list app", then tell your agent of choice to go have fun, and return in the morning to a fully finished app, and not care about what the code is actually doing

I’ve been playing around with these kinds of prompts. My experience is that the prompts need a lot of iteration to truly one-shot something that is halfway usable. If it’s under-spec’d it’ll just return after 15-20 minutes with something that’s not even half baked. If I give it an extremely detailed spec it’ll start dropping requirements and then finish around the 60-70 minute mark, but I needed 20 minutes to write t…

The dropping requirements problem is real. What's helped us is breaking the spec into numbered ACs and having the verification run per-criterion. If AC-3 fails you know exactly what got dropped.
Post reply on HN