All while complaining about the OLED price.

Just like Alta Vista and Netscape put there first mover advantage to use?

That's essentially the point. There is a non-zero risk that any given AI company ends up like those examples. That's why they are racing to IPO, raise more, get ahead of each other, and reach escape velocity of that risk.

Even the smallest margin or error in the demand forecast will put them at a huge loss, I can't imagine sleeping well at night if I was on that management team.

Opened the RTL, looked at the floating point math, learned that apparently you don't need correct floating point operations for LLMs, closed the page.

Well, you don't. That's why 1.58-bit (ternary) quants are often used. But if that's what they're going for, no need to dress it up in a floating-point facade.

Indeed there are some bugs/"non standard behavior" regarding very small or very big floating point values. All of those where proven harmless for LLM inference. Thanks for pointing out the bug. If you caught something outside of that, please point that out so I can fix it ;)

> All of those where proven harmless for LLM inference.

Could you share link(s) to those proof(s)?

Yup, the tests already compare to a CPU hugginsface implementation, but I'm working on making running and verifying the results of those tests easier and more available. Also, working on fixing those bugs and make the code more reliable now that the underling hardware has been saturated (memory bound)

Finally, thanks for stating the obvious! I was starting to wonder if I was not going insane.

A team of senior elite chip designers builds something they already know how to build and everyone goes "wow AI be so powerful".

Open source FPGA silicon in the wild, and it works.

> slighly crazy

What a lovely euphemism.

Signed: someone slightly crazy.

I wonder if they will be inviting him to the next RISC-V design committee meeting.

For a friendly meeting, like Julius Caesar had on March 15, 44 BC.

"This time its different".

Spot on, while reading this post I couldn't help be wonder "but what about the prototypes"?

No AI was used either for the project itself or for the post. I encourage you to look at the code and the git history.