First screen, captured .
Looks similar
Intel's $475M error: the silicon behind the Pentium division bug(righto.com)
362 points by gslin | 110 comments
Ken Shirriff's blog post examining the Pentium die to show where the 1994 floating-point division bug lies in the silicon and why it occurred.
Related stories
The GPU, not the TPM, is the root of hardware DRM(mjg59.dreamwidth.org)
399 points by DvdGiessen | 408 comments
Blog post by Matthew Garrett arguing that GPUs, not TPMs, are the real root of hardware DRM; the capture shows a Dreamwidth captcha page instead.
Reverse-engineering the Intel 8087's tangent algorithm: more than CORDIC(righto.com)
98 points by pwg | 11 comments
Ken Shirriff's blog post reverse-engineering the Intel 8087 coprocessor's FPTAN tangent instruction, which combines CORDIC with polynomial approximation.
Intel's $475M error: the silicon behind the Pentium division bug(righto.com)
362 points by gslin | 110 comments
Ken Shirriff's blog post examining the Pentium die to show where the 1994 floating-point division bug lies in the silicon and why it occurred.
The Intel 8087 chip: floating-point addition and subtraction(righto.com)
102 points by pwg | 33 comments
Ken Shirriff blog post examining the Intel 8087 coprocessor's microcode and circuitry for floating-point addition and subtraction, including special cases.
GPUs Go Brrr(hazyresearch.stanford.edu)
1056 points by nmstoker | 243 comments
Stanford Hazy Research blog post on what GPU hardware wants for efficient AI kernels, introducing the ThunderKittens CUDA kernel library.
Building the heap: racking 30 petabytes of hard drives for pretraining(si.inc)
392 points by nee1r | 267 comments
Standard Intelligence blog post describing how they built a 30-petabyte hard drive storage cluster in a San Francisco colocation center for under $500k to store video pretraining data.