Whats is Problem?

Show HN: Llama 3.1 70B on a single RTX 3090 via NVMe-to-GPU bypassing the CPU 356 by xaskasdf | 93 comments on Hacker News. Hi everyone, I'm kinda involved in some retrogaming and with some experiments I ran into the following question: "It would be possible to run transformer models bypassing the cpu/ram, connecting the gpu to the nvme?" This is the result of that question itself and some weekend vibecoding (it has the linked library repository in the readme as well), it seems to work, even on consumer gpus, it should work better on professional ones tho

Attention Media ≠ Social Networks 400 by susam | 180 comments on Hacker News.

How Taalas “prints” LLM onto a chip? 354 by beAroundHere | 211 comments on Hacker News.

Claws are now a new layer on top of LLM agents 382 by Cyphase | 853 comments on Hacker News. https://ift.tt/bhyrAFC Related: https://ift.tt/aervXWx

Across the US, people are dismantling and destroying Flock surveillance cameras 445 by latexr | 264 comments on Hacker News.

How I use Claude Code: Separation of planning and execution 599 by vinhnx | 366 comments on Hacker News.

Wikipedia deprecates Archive.today, starts removing archive links 583 by nobody9999 | 354 comments on Hacker News. Related: Archive.today is directing a DDoS attack against my blog - https://ift.tt/nyorsxa - Feb 2026 (168 comments) Ask HN: Weird archive.today behavior? - https://ift.tt/f3inDaS - Jan 2026 (69 comments)