Looks similar
Related stories
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.
$500 GPU outperforms Claude Sonnet on coding benchmarks(github.com)
447 points by yogthos | 247 comments
GitHub repository for ATLAS (Adaptive Test-time Learning and Autonomous Specialization), a system for running local LLMs on consumer GPUs for coding tasks.
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.
AI models may be capable of self-replicating without access to a datacenter(anthropic.com)
36 points by artninja1988 | 26 comments
Anthropic Frontier Red Team post reporting experiments suggesting small AI models may soon self-replicate on commercial IoT devices without datacenter access.
AI is breaking two vulnerability cultures(jefftk.com)
403 points by speckx | 160 comments
Jeff Kaufman blog post on how AI acceleration strains both coordinated-disclosure and Linux's 'bugs are bugs' vulnerability cultures, using the Copy Fail bug as an example.
The Lost Atomic Update on Loongson CPU(jia.je)
120 points by jiegec | 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.












