Hey, absolute props for replying to my code by making a counter-code of your own!

I don’t have the time to look into this right now, but wanted to say that this is the best I could hope of posting my random projects here: Having someone else tell you what they would do instead.

And for context, this was a weekend experiment. I wanted to try building “agentic stuff,” and exploring the not-so-promising intersection of information theory, LLMs, and code quality.

Will edit later after I read yours.

So how does it connect to any LLM without using their API?

Well, the typical use would be by local Agent subscription. But in theory any LLM could work, so long as it’s made to follow the filesystem protocol that faaah expects.

There’s a video in the repo with an example of how it works, plus a diagram.

Do you think rather than AI was used for most of the code? I don’t think it was.

If what you’re saying is that “vibe-coded” applies when “some AI was used”, and that it’s a bad thing, that’s a valid opinion that I might agree with in some contexts (like an ethical one).

It’s not, but some AI was used for the code. I think vibe coding it would have produced a very different (and larger) code base. What makes you think it’s vibe coded?

Yes. The idea is that you can have any tool on one side (which expects an OpenAI-like LLM API, which is a bit of a de facto standard), and any LLM on the other side (which can be an agent subscription).

I used this, for example, to test GraphRAG locally (which is designed to make a lot of LLM API calls) by piping it to an agent subscription I already had (and not needing to buy expensive API tokens for the low volume I needed).

Thanks!

Yeah, I don’t like agents either, so I’ll take it. This just solved a real problem I had, so I went ahead and shared it

Well, the main reason why I post my projects is for people to tell me what alternatives I’m missing, so thanks for that.

I’m actually not that familiar with Kilo, but I believe it’s an agent/IDE-extension, and that you can use different providers for it, including coding agents (I think this is what you were referring to.)

So basically my use case is more niche. I just had an external tool (Graphrag) that only worked with an LLM API, and I had just an agent subscription, so i built an agnostic protocol via the filesystem to make them work together.

It’s agnostic because you can have any tool on one side (which expects an OpenAI-like LLM API), and any LLM on the other side (which can be an agent subscription).

Nothing in Kilo would have allowed me to get Graphrag working, I think.

What in particular? Maybe I can tell you.

My initial use case was testing graphrag locally, which might become relevant at work later on, so I generalized the thing I did to get it working through an agent subscription. Actually that usage is public too: https://github.com/sebastiancarlos/graphrag-faaah

Hey pmjv, thanks for dropping by! You’re an absolute legend and I couldn’t have made this (for better or worse) without your work.

Thanks for the feedback. I’m the author of the medium blog post too.

If you have any tips on where to find a better free voice, I’m all ears. I haven’t tried chatterbox yet, that one might do it.

It could also be that the “direct blog post to video” format doesn’t cut it. But I’m still experimenting with ways to generate effective multimedia out of my content.

Btw, this is my open-source pipeline, which I use to make the video and blog post out of the same source file: https://github.com/sebastiancarlos/hacker-press

Edit: Regarding “satire”, that doesn’t apply to this blog post in particular. But I did add some jokes here and there to keep the dry topic going.

That parody is a bit problematic, though

That’s a good point, yes.

Your empathy is really appreciated.

No problem! Fwiw I think a lot of us identify with a lot of that character these days.

There’s no criticism of the outside factors

The article literally starts with “In 2026, the job market is tough. AI plunged us all into economic despair” (itself exaggerated, and a play on the typical “AI doomer” clickbait articles saying what we all know more dramatically, which is another can of worms).

It shouldn’t be a sentence for poverty.

Agreed. And in the article it isn’t. He does get a job at the end.

But yeah, I can see how your reading of the article is valid. I’ll sleep on it and see if I can do something about it.

I don’t actually think I frame that as the only alternative. There’s nuance on the article. It’s a bit up to you how to interpret it. Some options are:

• He would have actually kept the job if he hadn’t slacked off the final week, and kept using AI.
• The job was not a good fit for him anyway because the vibecode-heavy workspace virtually required using AI. But that doesn’t meant that there wouldn’t be other jobs for him (he gets one at the end btw).
• He might have been able to get by without AI if he didn’t go through his gargantuan vimwiki project for 3 weeks.

I don’t imply that being able to use AI tools is a panacea to get a job. I don’t imply that the reason for many lay offs isn’t related to AI.

I don’t insinuate that being out of work is entirely the fault of the worker. I’m just making the nuanced point that some workers can sometimes do more beneficial things when looking for work, without realizing that that’s the case. This can happen despite the main barrier to getting a job being a completely external cause (as it’s indeed implied in the article).

I understand that the topic is uncomfortable. That’s why I tried to to put it in the context of humor and satire. Basically I’m asking what can we do better when trying to get a job, even if an external, uncontrollable situation would make any improvement almost pointless.

It’s implied that he actually gets fired because of refusing orders for 3 weeks, and then slacking off another week.

Well, the idea was to have a narrator who is a bit self-sabotaging in their job hunt, doesn’t notice, and blames the job market and AI. The nuance is that they are partially right on the external diagnosis, but not on the internal one, and that’s something that happens.

For the record, I think the entire spectrum of accepting/rejecting AI has valid points, and that there’s a lot of value on the rejection side. I also think it’s alright to make fun of some of them, particularly if doing it mostly to highlight some contradictions and conflicts, without making a moral judgement.

I assure you that’s way off from my intent. But for privacy reasons, I don’t want to discuss publicly my financial circumstances and how appropriate they might be in the context of writing this. In any case, I appreciate your feedback on how this could be read. I’ll keep it in mind, and I apologize.

Anything in particular that felt like punching down or strawmanning people in financial problems?

Thank you for reading it!

To me the logs are the real heart of the book, where the actual things I’m trying to say get more into focus.

I think you’re gonna like the ending if you liked everything so far, it really wraps everything up.

Yeah, I had to shout out analognowhere. I think he’s one of a handful of artists that are writing about a similar topic in a similar style. I really like their work, it inspired me.

Also, the open-source katana is a reference to OpenBlade.