Reptar(lock.cmpxchg8b.com)

557 points by abhi9u 2 years ago | 168 comments

Tavis Ormandy's write-up of Reptar, an Intel CPU bug where redundant instruction prefixes put processors into a glitch state, covering its discovery and fix.

Why are anime catgirls blocking my access to the Linux kernel?(lock.cmpxchg8b.com)

728 points by taviso 1 year ago | 772 comments

Tavis Ormandy's essay examining Anubis, a proof-of-work anti-AI-crawler gate, covering the problem it targets, cost numbers, alternatives, and workarounds.

Linux on the Fujitsu Lifebook U729(borretti.me)

197 points by ibobev 11 months ago | 141 comments

Hiew Hex Editor(lock.cmpxchg8b.com)

171 points by taviso 2 years ago | 42 comments

Building a UMatrix Replacement(lock.cmpxchg8b.com)

45 points by taviso 5 months ago | 13 comments

Building an FPGA 3dfx Voodoo with Modern RTL Tools(noquiche.fyi)

215 points by fayalalebrun 7 months ago | 48 comments

The RCE that AMD won't fix(mrbruh.com)

343 points by MrBruh 8 months ago | 144 comments

Blog post describing a remote code execution vulnerability found by decompiling AMD's AutoUpdate software, which AMD declined to fix.

Ollama now supports AMD graphics cards(ollama.com)

578 points by tosh 2 years ago | 194 comments

Ollama blog post from March 14, 2024 announcing preview support for running models on AMD graphics cards.

The Lost Atomic Update on Loongson CPU(jia.je)

120 points by jiegec 1 month ago | 6 comments

A blog post investigating a hardware erratum on the Loongson LA664 CPU where an atomic instruction loses updates, causing an infinite loop while packaging normaliz for Debian.

AMD acquires Taalas to boost inference performance by etching models in silicon(theregister.com)

902 points by itvision 2 months ago | 681 comments

The Register reports AMD has acquired AI chip startup Taalas, which hardwires model weights into silicon for fast inference, reaching up to 17,000 tokens per second.

How we hacked McKinsey's AI platform(codewall.ai)

420 points by mycroft_4221 7 months ago | 168 comments

CodeWall blog post describing how its autonomous offensive agent found vulnerabilities in McKinsey's internal AI platform Lilli.

We were wrong about GPUs(fly.io)

834 points by mxstbr 1 year ago | 529 comments

Fly.io blog post reflecting on how the company's bet on offering GPU machines to developers did not pan out as expected.