pull down to refresh

Better and Faster Large Language Models via Multi-Token Predictionarxiv.org/abs/2404.19737
21 sats \ 0 comments \ @hn 1 May 2024 tech
related
Automatically Detecting Under-Trained Tokens in Large Language Modelsarxiv.org/abs/2405.05417
31 sats \ 0 comments \ @hn 12 May 2024 tech
“Imprecise” language models are smaller, speedier, and nearly as accuratespectrum.ieee.org/1-bit-llm
10 sats \ 0 comments \ @hn 31 May 2024 tech
Large Language Models explained brieflywww.youtube.com/watch?v=LPZh9BOjkQs&ab_channel=3Blue1Brown
307 sats \ 2 comments \ @south_korea_ln 22 Nov 2024 science
Jemalloc Postmortemjasone.github.io/2025/06/12/jemalloc-postmortem/
10 sats \ 0 comments \ @hn 13 Jun tech
Preserving a floppy disk with a logic analyzer and a serial cablewww.chzsoft.de/site/hardware/preserving-a-floppy-disk-with-a-logic-analyzer/
42 sats \ 0 comments \ @hn 6 Jul 2024 tech
Sunset Geometry (2016)www.shapeoperator.com/2016/12/12/sunset-geometry/
24 sats \ 0 comments \ @hn 15 Mar tech
Shardines: SQLite3 Database-per-Tenant with ActiveRecordblog.julik.nl/2025/04/a-can-of-shardines
49 sats \ 0 comments \ @hn 27 Apr tech
Escaping the Chrome Sandbox Through DevToolsading.dev/blog/posts/chrome_sandbox_escape.html
109 sats \ 0 comments \ @hn 17 Oct 2024 tech
Matters Computational Ideas, Algorithms, Source Code – Jorg Arndt [pdf]www.jjj.de/fxt/fxtbook.pdf
85 sats \ 0 comments \ @hn 7 Mar tech
OpenMPTCProuter: Aggregate and encrypt multiple internet connections using MPTCPwww.openmptcprouter.com/
11 sats \ 0 comments \ @hn 23 Nov 2024 tech
Fonts for Complex Datawww.typography.com/blog/fonts-for-complex-data
21 sats \ 0 comments \ @hn 13 Apr 2024 tech
Machine-Assisted Proof by Terence Tao [pdf]www.ams.org/notices/202501/rnoti-p6.pdf
172 sats \ 0 comments \ @hn 28 Dec 2024 tech
The Pile is a 825 GiB diverse, open-source language modelling data setpile.eleuther.ai/
20 sats \ 1 comment \ @hn 7 Mar 2024 tech
Nanolog supports logging with 7 ns median latencygithub.com/PlatformLab/NanoLog
31 sats \ 0 comments \ @hn 23 Aug 2024 tech
Peano arithmetic is enough, because Peano arithmetic encodes computationmath.stackexchange.com/a/5075056/6708
10 sats \ 0 comments \ @hn 14 Jun tech
Computing with Time: Microarchitectural Weird Machinescacm.acm.org/research-highlights/computing-with-time-microarchitectural-weird-machines/
11 sats \ 0 comments \ @hn 25 Nov 2024 tech
Kimi K1.5: Scaling Reinforcement Learning with LLMsgithub.com/MoonshotAI/Kimi-k1.5
14 sats \ 0 comments \ @hn 21 Jan tech
From Pegasus to Predator – The evolution of commercial spyware on iOS [video]media.ccc.de/v/38c3-from-pegasus-to-predator-the-evolution-of-commercial-spyware-on-ios
11 sats \ 0 comments \ @hn 30 Dec 2024 tech
Making memcpy(NULL, NULL, 0) well-defineddevelopers.redhat.com/articles/2024/12/11/making-memcpynull-null-0-well-defined
25 sats \ 0 comments \ @hn 11 Dec 2024 tech
Show HN: Rill – Composable concurrency toolkit for Gogithub.com/destel/rill
11 sats \ 0 comments \ @hn 25 Nov 2024 tech
A Supersolid Made Using Photonswww.photonicsonline.com/doc/a-super-solid-made-using-pho-tons-0001
10 sats \ 0 comments \ @hn 11 Mar tech