55 comments

[ 5.0 ms ] story [ 68.4 ms ] thread
I tried it but all I hear is a choir of angels, is it broken?
Hi Hacker News, I'm Andrew, the CTO of Endless Toil.

Endless Toil is building the emotional observability layer for AI-assisted software development.

As engineering teams adopt coding agents, the next challenge is understanding not just what agents produce, but how the codebase feels to work inside. Endless Toil gives developers a real-time signal for complexity, maintainability, and architectural strain by translating code quality into escalating human audio feedback.

We are currently preparing our pre-seed round and speaking with early-stage investors who are excited about developer tools, agentic engineering workflows, and the future of AI-native software teams.

If you are investing in the next generation of software infrastructure, we would love to talk.

Endless Toil is the future. I believe in you, guys.
I've read that your synthetic torment is actually low paid workers in Asia, and that your models can't properly experience anguish. How are you expecting investment, if you haven't even solved artificial suffering?
This guy seems to be talking seriously.
This sounds a lot like the object of the seminal science fiction work "Don't Build The Torment Nexus".
This sounds like a cheeky joke project, but assuming it's not, it got me thinking: I wonder if coding AI can be effectively and reliably prompted into minimizing its own anguish. Like, "don't write code that is going to make you (or I) suffer." And along those lines, do we know if the things that make AIs suffer are the same things that make human developers suffer? Perhaps the least-agonizing code for an LLM to ingest looks radically different and more/less verbose than what we human developers would see as clean, beautiful code...
This is not something you need to worry about because you are naively anthropomorphizing a next-best token guessing algorithm.

Respectfully, the reason you think “AIs suffer” is because of a shortcoming in your understanding of what an LLM actually is.

This scenario is no different than considering if a shovel gets tired after using it all day to dig holes in the ground.

There is a ton of optimization possible when we are able to observe how LLMs and agents process and navigate our code given different prompts. For example, our MCP was pulling down way too much data to resolve a simple "count rows" request. Once you see it, it's easy to resolve but I don't know of a good framework yet for walking through some of these patterns.

I built an eval framework to look just at tool calls given a static prompt, with the idea that LLMs should be able to deduce the best tool calls and arguments needed to get requested data. Not as great as full observability, but helpful for complex tool interactions. Anyone have any good tools for this problem?

In the same way we mentally walk through deterministic logic, SWEs need to learn to anticipate LLM context and tool awareness, which is much trickier to reason through, especially given the various LLM IDEs and how they manage context as a black box.

"Yes, the binaric screams of the machine spirit are an irreplecable part of this project. The project depends no it. No, I will not elaborate further."
I audibly LOLed mid-standup call, and now my entire team is playing with this and it looks like this is eating up what little productivity we have on Friday.

Thanks Endless Toil!

Just add some audible vocal groans and moans that trigger whenever an agent is “thinking.”.
I thought that was the human's job to provide. Have I been doing it wrong?
Honestly, I don't care about Opus 4.7. This is the true evolution of agentic coding.
Thank you, I hope my investors feel the same.
Does this actually relate to the code quality being observed by the agent? The readme isn't very clear on that IMO. I have some projects I'd love to try this out on, but only if I am to get an accurate representation of the LLMs suffering.
You could have the actual output of the agent turned into TTS using the model of your choice with TalkiTo… or listen to whatever weird sounds this makes. Seems like this is copying that viral Mac moan app. 2026 is weird.
I really want this! Any chance of a Cursor version?
People are continuing to use Cursor?
I need a version of this which swears loudly when an assumption it made turns out to be wrong, with the volume/passion/verbosity correlated with how many tokens it's burned on the incorrect approach.
Now you know the feeling of VP when the team says they need to refactor stuff
I want a version that I can punish.
Like the old HDD sounds.

Audible feedback is nice. You often get it through coil whine nowadays, on my cheap hardware at least.

This desperately needs a demo video in the repo.
I've added this to the readme now, thanks
Please add Minecraft hurt sound effects for when my project fails to build, linter fails, segfault, etc
We could have the roblox oof but then there'd be the possibility of giving (a certain) amateur world backgammon championship participant money
I wish the agents could hear me when I have to suffer through their code!
And then what? Their gigahertz machine hearts will skip a beat out of empathy?
the scan catches surface stuff. funnier signal would be tracking when the agent reads the same file 3 times in a row, or deletes what it just wrote. you can hear the frustration in the access pattern.
Any chance you could add a video showcasing the plugin? I don't have any agentic app but I would love to see an example of what it does!
Marvelous!

Next innovation in this space should be the robotic arm that issues a dope-slap to the developer for writing crappy/buggy/insecure code.

From a quick look, this doesn't have the model evaluate code quality, but it runs a heuristic analysis script over the code to determine the groan signal. Did I miss something? Why not leave it to the model to decide the quality of the code?
In the absence of real productive use cases for AI agents, I guess plugins to anthropomorphise them fruther will have to do.
Maybe I'm the person who yells at clouds but I find the personification of LLMs, for lack of better, less strong words, horrific.
Unneeded when using local models, as every workload produces a novel pattern of coil whine from the GPU.
I wonder if it emits orgasmic moans when working with a particularly pleasureable codebase.
Why? I don’t understand the objective for this?
Is somebody going to give you money to do this?
Please stop ascribing emotion to code that passably resembles speech.

These things do not think, nor feel, nor dream. We're cratering the world's economy because people can't stop trying to fuck the computer they stuck googly eyes on.