Viewing profile — readitalready

[flagged]

[flagged]

[flagged]

How do you think the tests were generated? You don't actually think I look at the code, do you?

I don't micromanage it. I let my projects custom linter micromanage it. Every project should have a custom linter for their tech stack. It would check for not just syntax errors, b…

I let agents break things 30 changes down the line. If something breaks, I add a check to my project validator and start over, with the validator providing instructions on what was…

This flow is really for LLM consumption, since Markdown spec documents are for LLMs anyways. And you can always write a JSON-to-markdown converter for human use (actually, LLMs rem…

I moved from Markdown to JSON for all spec writing about 9 months ago. Although not HTML, it still has the same benefits. Claude and the other models are just so much more reliable…

Not for me. 2 Claude Max 20x accounts here both at high usage on weekly allotments.

This probably started because of Andrej Karpathy's complaint about deployment being more painful than coding itself.

The point isn't to save money. The point is to make money. And all those companies that are failing because of their fabs, they MADE money because of the fabs. Intel is now on its …

Your custom linters don't check architectural design? linters statically check code and provide deterministic recommendations. LLMs are used to make judgement. I specifically write…

No fixing the mess definitely does not take longer than writing it oneself. Your linter should identify all issues - including architectural and stylistic choices - and the AI agen…

Come on Apple at least start the process of building your own fabs. License some of the processes if you must. Otherwise you will always be at the mercy of fabs that are more focus…

I think companies are charged API prices vs individual prices. That alone is 10x for Anthropic. Not sure though.

No, you CAN'T raise prices because no one will buy them, destroying your brand and your business. And you won't have supply anyways. There is no scenario where not having a fab is …

OMM 0910 is the AI Jesus. We've literally seen this movie before.

Apple doesn't own TSMC. TSMC is putting Apple in the back burner in favor of Nvidia and other high margin companies. They are literally being limited by TSMC (as well as the DRAM m…

You can easily end up like AMD or Intel spending years with your own fab that’s uncompetitive. You could. Or you could have no fab and no supply of chips for your business.

They really need to build their own fabs at this point. AI is going to kill their ASIC and DRAM supply chain if they don't. "Real men have fabs." - Jerry Sanders, first CEO of AMD.…

Took getting their asses handed to them in a war to realize this.

lol no. LLMs are infinitely more capable than programmers. People really do think too highly of themselves.

That's like saying "the programmers are so terrible you have to think ahead of them so they don't make mistakes".

All the CAD and modelings tools have their own scripting languages that LLMs can write to, so you can just use that directly without any built-in LLM support. There will probably b…

It's because LLMs will soon start building real-world objects via CAD. This is the first step. Look at things like the Adam plugin for Onshape. Works great with Opus. It built a to…