Shin

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.

Yet this is my problem, A tool that "waste" tokens, is slow (with some tasks taking 30~40 minutes) and generating a result, while a model running locally can do the 70% in 5min. It's a huge difference.

And don't forget, at the end of the day, I would still need to look into the code and fix some stuff myself.

And if compared with Deepseek (which had fit best on my use case), it's even faster like 1~3 minutes, to get on the 90% of the result, on a fraction of the cost. This is the points that I'm focused, and a enterprise should either understand that the market have changed, or pay the price. And looks like we will pay the price.

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.

You complain about the ai essay style, and pointed to the language tool, I told you that I self host, so doesn’t include this part of it. (The ai bulshiting)

Either way, feels like you didn’t like my “writing” in a general sense… I imagined it was some deeper thought on it. Either way thanks for the reading.

Does it matter?

When shite is going to the fan, this is the price I want :)

Self hosted, doesn’t include the AI bulshiting.

Last week I was deeply in the mind of "I don't see the real benefit" of AI for a fair lot of things. But with the current change of hearts in a lot of companies, and with the fact that this tool won't leave us soon. I'm trying to mitigate the major issues on codebases that I'll work in the future.

So yeah, this is kind of the situation, and maybe this is the point that needs to be more explored on the conversation of the AI bullshiting.

Can you help me there. This writting style is mostly me (an non-native) writting. And a fair lot of languagetool fixing my grammar mistakes.

Maybe you can point some of the issues, maybe it's how I express myself, or something else. Also thanks for reading the text.

This is a very sad contradiction that I see in the market right now. The pile of work, the endless list of "Backlog" on the board that never ended, and still firing 8k people because "AI" is doing the work. If the AI is a multiplier of 100x, the backlog could be cleaned before throwing everyone under the bus.