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.

I’m not an expert in Game Dev, but I can see “good” code and “bad” code.

And yet, I can’t see the meaningful benefit, I can see the cracks, it’s never “fully” there, it’s always a couple details that aren’t correct in the planing, it’s always something that bothers, or some misleading thing that looks “ok”, but when you think little bit more it’s not trully correct.

I know that on the empirical knowledge and testing I’m not seeing this benefit and speed.

But for some reason people are claiming that. And it feels like I’m left behind.

Even if the real number is a 10% speed boost, I want to know where and how to apply this to benefit from this tools. It’s the same as the LSP, people can complain about it, and be like DHH that says that LSP aren’t worth it. But on my own usage it’s a good tool to add on my set of tooling.

That’s a very valida argument that I completed missed in the discussion. Fair point.

I didn’t hat the opportunity to write on this comment yesterday, so I’ll do it today. Freaking awesome idea. Right now when I need to make some more “complex” logic for the AI, I’m using the singleton for the CombatManager to keep it with its data. But having a resource for the combat_context would solve and make it able to have more isolated, and for sure create even a replicable combat (since each turn is “predictable”)… Love it. Thanks for the comment.