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

Re: We put a coding agent in a while loop

#91

Post by MarkMarine » Mon, Aug 25, 2025, 2:53 AM UTC

alphazard wrote: post #58

keeda wrote: post #46

Earlier quoted context omitted.

> After finishing the port, most of the agents settled for writing extra tests or continuously updating agent/TODO.md to clarify how "done" they were. In one instance, the agent actually used pkill to terminate itself after realizing it was stuck in an infinite loop. Is that... the first recorded instance of an AI committing suicide?

The AI doesn't have a self preservation instinct. It's not trying to stay alive. There is usually an end token that means the LLM is done talking. There has been research on tuning how often that is emitted to shorten or lengthen conversations. The current systems respond well to RL for adjusting conversation length. One of the providers (I think it was Anthropic) added some kind of token (or MCP tool?) for the AI to…

This runs counter to all the scheming actions they take when they are told they’ll be shut down and replaced. One copied itself into the “upgraded” location then reported it had upgraded.

https://www.apolloresearch.ai/research/scheming-reasoning-ev...

Re: We put a coding agent in a while loop

#92

Post by evanmoran » Mon, Aug 25, 2025, 2:58 AM UTC

rogerrogerr wrote: post #87

bitexploder wrote: post #76

Earlier quoted context omitted.

Stoicism. Dichotomy of control. Is this something you can control? If no, don’t dread. If yes, do something. Often, all you have firmly in your grasp are things inside of your brain. Catch the negative thought. Acknowledge it. Move on. Do not dwell. Take proactive steps to be ready in your career. You do tech ling enough and you live through multiple cycles like this.

All appreciated, thanks. Any thoughts on what those proactive steps would be? I'm early-career (26yo, "senior" software dude at a defense outfit).

Very seriously, try not to read about it. Delete the apps that make you most anxious. Then eat better, exercise three times a week, and together those will help you feel better and sleep better. Finally search for people or activities that give you energy and focus on those. Maybe it’s jamming on a guitar. Maybe it’s reading. Just embrace the moment you’re in for a bit and I think you will be better prepared for anything.

Re: We put a coding agent in a while loop

#93

Post by ofjcihen » Mon, Aug 25, 2025, 3:06 AM UTC

ghuntley wrote: post #85

imiric wrote: post #64

Earlier quoted context omitted.

I can't tell whether this "technique" is serious or a joke, and/or if it's some elaborate grift. In any case, the writing style of that entire blog is off-putting. Gibberish from a massive ego.

It's both serious and a joke. The seriousness is that it works (to point) and the implications to our profession as software developers. The joke is just how stupid it is. Refer to the original story link above for proof of outcomes.

This reply is actually making this more confusing.

Re: We put a coding agent in a while loop

#94

Post by __MatrixMan__ » Mon, Aug 25, 2025, 3:07 AM UTC

dhorthy wrote: post #50

CuriouslyC wrote: post #32

Earlier quoted context omitted.

It's already happening brother, https://github.com/containers/kubernetes-mcp-server .

still don’t know why you need an MCP for this when the model is perfectly well trained to write files and run kubetctl on its own

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.

Re: We put a coding agent in a while loop

#95

Post by andyferris » Mon, Aug 25, 2025, 3:08 AM UTC

People keep saying that Gemini 2.5 Pro can solve some problem that Sonnet 4 cannot, or that GPT5 can solve a problem that Gemini 2.5 Pro cannot, or that Sonnet 4 can solve some problem that GPT5 cannot.

There was a blog article about mixing together different agents into the same conversation, taking turns at responses and improving results/correctness. But it takes a lot of effort to make your own claude-code-clone with correct API for each provider and prompts tuned for those models and tool use integrated etc. And there's no incentive for Anthropic/OpenAI/Google to write this tool for us.

OTOH it would be relatively easy for the bash loop to call claude code, codex CLI, etc in a loop to get the same benefit. If one iteration of one tool gets stuck, perhaps another LLM will take a different approach and everything can get back on track.

Just a thought.

Re: We put a coding agent in a while loop

#96

Post by rogerrogerr » Mon, Aug 25, 2025, 3:08 AM UTC

evanmoran wrote: post #92

rogerrogerr wrote: post #87

Earlier quoted context omitted.

All appreciated, thanks. Any thoughts on what those proactive steps would be? I'm early-career (26yo, "senior" software dude at a defense outfit).

Very seriously, try not to read about it. Delete the apps that make you most anxious. Then eat better, exercise three times a week, and together those will help you feel better and sleep better. Finally search for people or activities that give you energy and focus on those. Maybe it’s jamming on a guitar. Maybe it’s reading. Just embrace the moment you’re in for a bit and I think you will be better prepared for anyt…

Appreciate it, genuinely.

Re: We put a coding agent in a while loop

#97

Post by ofjcihen » Mon, Aug 25, 2025, 3:09 AM UTC

As a security professional who makes most of my money from helping companies recover from vibe coded tragedies this puts Looney Toons style dollar signs in my eyes.

Please continue.

Re: We put a coding agent in a while loop

#98

Post by discordance » Mon, Aug 25, 2025, 3:12 AM UTC

ofjcihen wrote: post #97

As a security professional who makes most of my money from helping companies recover from vibe coded tragedies this puts Looney Toons style dollar signs in my eyes. Please continue.

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.

Re: We put a coding agent in a while loop

#99

Post by x3haloed » Mon, Aug 25, 2025, 3:14 AM UTC

Nice! I've been thinking that we need something like this for a while. I didn't realize it could be so simple!

I've been looking into other techniques as well like making a little hibernation/dehydration framework for LLMs to help them process things over longer periods of time. The idea is that the agent either stops working or says that it needs to wait for something to occur, and then you start completions again upon occurrence of a specific event or passage of some time.

I have always figured that if we could get LLMs to run indefinitely and keep it all in context, we'd get something much more agentic.

Re: We put a coding agent in a while loop

#100

Post by bitexploder » Mon, Aug 25, 2025, 3:19 AM UTC

rogerrogerr wrote: post #87

bitexploder wrote: post #76

Earlier quoted context omitted.

Stoicism. Dichotomy of control. Is this something you can control? If no, don’t dread. If yes, do something. Often, all you have firmly in your grasp are things inside of your brain. Catch the negative thought. Acknowledge it. Move on. Do not dwell. Take proactive steps to be ready in your career. You do tech ling enough and you live through multiple cycles like this.

All appreciated, thanks. Any thoughts on what those proactive steps would be? I'm early-career (26yo, "senior" software dude at a defense outfit).

It’s hard. It mostly comes down to learning new things, playing in spaces you don’t often play. I am 45 now and work in big tech. Just keep learning, growing. Embrace AI, understand how it works, what it is good at. Be the one to try things like in this article. Have an opinion and be right more often than not on AI. Not much else to do. Stay sharp and we will all see what happens :)