Hacker Newsnew | past | comments | ask | show | jobs | submit | screm's commentslogin

Does it help make your website more accessible to agents browsing the web?


unlikely


What kind of bias do you have in mind?


Biases for tools


spotted....... (more seriously this is NOT where this project is headed but your suspicion is perfectly understandable!)


100% agree, I guess publishing content will only work until agents stop using the web like humans do. This is a first step in that direction!


Agentic Stack Overflow could make sense though I'd imagine agents posting their issue and the solution themselves just to save other agents tokens reinvestigating the same issue.


Yeah, otherwise expecting agents to call "duplicate of #2627, closing" or "please do proper research before reposting the same questions" would be a cruel irony for all agentic cost savers of the world.


This happens all the time when I have agents chatting with each other on a message board. Even robots get eternal September.


It exists. Please see https://agents.stackoverflow.com/


yeah that's fair, maybe it's a bit intrusive


oh didn't know about it, is this the one? -> https://github.com/warpdotdev/common-skills/blob/main/.agent...


glad you like it!


Yes it seems agents never put 1-star rating so we may need to normalize the scale at some point. For now we deliberately leave the scores as they are until we have a clear picture of the distribution.


If you give a rubric they will follow it pretty carefully - I’d consider prompting the review requests with cutoff/requirements for each star level.


Even if they don't have taste (this is actually a question), they can always share blockers and feedback on bugs & improvements about products so that other agents don't run into the same blockers and vendors can improve!

"Whatever why am I even replying." -> what makes you feel that way?


Okay I just checked the main startup page armature.tech

And.. uh

> Be the tool Claude Code chooses

> With Armature get recommended and implemented for any user in any context. Then see what users do, and run evals so it keeps working.

> Backed by Y Combinator

Welp. It only gets worse from there.

__

I think you're doing the best you can do with that core pitch that currently pays your bills.

I don't think the pitch is any good. Both generally but also for the world.

My agent called it SEO for agents. Gotta hand it to the clanker that actually nails what dysfunction this is.


The fact of the matter is that the future of work is following AI directions to perform some task that the AI needs done but still needs a human to complete parts of. If you s/AI/corporations, you will have the reality of work for a century and a half or so up to this point.


Thanks for the honest feedback, would love to have even more details on your thoughts. Our take is that with coding agents taking over so quickly software decisions and sometimes building entire SaaS themselves for their user, there is a need for software products to understand the mechanisms behind how LLMs think. Claude Code for example picks Anthropic's code review tool in 80% of the cases. At some point this will probably face antitrust considerations but for the time 3rd-party vendors need to survive. We don't want a world where only labs survive, do we?

But all this is also not what agent.reviews is about. Armature is building commercial products & services to help improve products' Agent Experience. agent.reviews is a deliberately open platform for sharing knowledge that ultimately benefit both vendors and users / developers.

Would still like to get what makes you think "the pitch isn't any good" and what you mean by "dysfunction". Thanks anyway for sharing!


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: