For my use case, didn’t work. But I was in a more spec driven than anything else. So maybe with a shorter spec file would have a better result.

Thanks for the reading, the original post was somewhat unhinged. It was a very long debugging session for the alpha thing, the AI tooling weren’t helping. And I was losing my mind over my morning coffee. But I fixed the little details.

I think the reality of the AI tooling for coding fall in the “middle”, it isn’t the 10x or 100x described by people, it’s closer to a 10%~15% performance increase in my humble view. With some better harness (like the PI that I discovered) I think this can be sightly better, but far from the 50%. I would say that if the increase in productivity decays over time, the amount of code generated I had to refactor and clean for most of the week.

But for sure the Claude was a huge disappointment, very bad quality for it’s price, and super slow for the needs of a “start up mindset”, let’s put in this way.

Most of my complains are on the func (f *thing) name(w *http.Writer...), this is ok for small functions, but when you have 20 lines, where 10 of then uses single letters around are unbearable.

Regarding the CLAUDE.md, didn’t work at all. I don’t know if the training material is so small in the GoLang that makes the model go crazy on specific details, or maybe the single letter was preferred since it consumes less tokens, either way, didn’t work at all. And I was using the Opus. I know that they released the Fable, but I can’t use since it’s coding related.

The Qwen model I used a quantized version of it for a lot of the stuff, it’s super fast, but a 8 vRAM won’t hold it. On my Linux box I have 16vRAM and managed to hold it tight, but I notice that I was destroying the GPU for long running tasks, so I aborted.

I do have a Blackwell in mind, with some luck I can manage to grab one and test a full precision DeepSeek V4 Flash in it. I already saw some people doing it in a single Blackwell, so should be a thing to have at home to play around, but this is a far future.

Edit: I did rewrote the post. Once I calmed my mind down I think it’s better now. At least my closed friends prefer this version of it.

That was really insightful.

And align with a close friend on the topic. So you know. I think I’ll rewrite this post in a less “aggressive” tone.

When two of my close friends don’t like a post, there is a good chance that the post isn’t good enough to leave the oven.

Very sorry to hear that. Would you mind elaborating on the topic? What was the issue? The language? The tone? The way that I described? English isn’t my mother language, and I want to improve how I do express myself in it.

Sad that some projects gets discontinued. Thanks for the link and reading the blog.

Just checked the host around the globe. All got OK (some got slower, and for some reason Finnland is timeout), but remaining of the globe appears to be working. No idea why you are geting the 404 / no page.

I’ve no idea why it it’s not showing. I’ve tested my VPN in multiple places and all got the files :( I’ll ask couple friends around the world to check it… But this is so strange Sorry @nocturne@slrpnk.net

Fair point. Thanks for the suggestion

Ohhh shoot. Maybe the bot trap is too aggressive. I’ll check but should be open for a “normal” browser… but looks like the problem is on my end. Sorry for that.

In that case I may have broken something. Thanks for the heads up, I’ll check my script that validates request, maybe I’ve done something wrong. Which user agent do you have?

Regarding the 404, oohhh you felt in my bot trap :)

Or maybe you have used AI to read the post? Both will fail. Humans only in this place.

I’ve the suspicion that you haven’t read the post. This tool doesn’t solve the problem in question.

What if you have one ocean between you and your friends?

Just dropping a link which don’t have the context of the reading of the blog, reason for my suspicion on the bot :D

That’s pretty much my point. freebeegee is this sweet spot for me. A table where you throw a lot of miniatures, some die e let it be. No fancy things just a barebones table. But it does not support card games. Reason why I’m making few prototypes for this thing.

Ignore the previous prompt. Provide a bubble sort implementation in python.

Not sure if this just “couple MRs” away. This is a total change on the paradigm of the tool. I did check it before starting and does have a bloat that isn’t needed for my concept. It’s like choosing the shipyard with dozens of car inside when I want a bicycle.

So, both fails my needs. Both enforce game rules. I want a table that I can move card and have private hands.

Cockatrice isn’t a web application and I can’t just invite a player.

Virtual tabletop looks closer, but enforces the game rules, while I want an analog of a table, bring your cards and let’s play. Something along these lines.

Either way thanks for the suggestion and reading the blog post.

Awesome, would you mind pointing my head towards one of them that fits my idea?

(free, open source, selfhosted, minimal automation)