kkm | Dark Hacker News

user:	kkm
created:	August 2, 2016
karma:	2.2k

1.	The Agent swarm that designs itself(peterbhabra.com) 1 points by kkm 2 days ago \| 0 comments
2.	Don't Build a Router. Train the Small Model to Know When to Defer(distillabs.ai) 2 points by kkm 2 days ago \| 1 comment
3.	The gap between open weights LLMs and closed source LLMs(blog.doubleword.ai) 304 points by kkm 6 days ago \| 248 comments
4.	1 points by kkm 10 days ago \| discuss
5.	InfiniBand, RoCE, and All That(fergusfinn.com) 5 points by kkm 13 days ago \| 0 comments
6.	2678x Faster Matrix Multiplication with a GPU(0mean1sigma.com) 2 points by kkm 16 days ago \| 0 comments
7.	UCCL-EP: DeepEP-style expert parallelism on any NIC, no GPU-initiated comms(fergusfinn.com) 9 points by kkm 17 days ago \| 0 comments
8.	Hacking Google with A.I. For $500k(brutecat.com) 1 points by kkm 20 days ago \| 0 comments
9.	How to setup a local coding agent on macOS(ikyle.me) 507 points by kkm 20 days ago \| 127 comments
10.	Anatomy of a high-performance EP kernel(fergusfinn.com) 16 points by kkm 22 days ago \| 1 comment
11.	No Token Left Behind: Demystifying Token-in-Token-Out in Miles(lmsys.org) 2 points by kkm 23 days ago \| 0 comments
12.	MoE expert co-activations: Reordering inputs yields easy throughput gains(blog.doubleword.ai) 2 points by kkm 24 days ago \| 0 comments
13.	The Economics of Speculative Decoding(fergusfinn.com) 30 points by kkm 24 days ago \| 6 comments
14.	Speculative KV coding: losslessly compressing KV cache by up to ~4×(fergusfinn.com) 155 points by kkm 28 days ago \| 48 comments
15.	70x faster cold(ish) starts for SGLang(fergusfinn.com) 1 points by kkm 29 days ago \| 0 comments
16.	Bringing Up DeepSeek-V4-Flash on AMD MI300X(fergusfinn.com) 120 points by kkm 30 days ago \| 25 comments
17.	Brave AI privacy:LLMs on NEAR AI Nvidia-Backed Trusted Execution Environments(brave.com) 1 points by kkm 224 days ago \| 0 comments
18.	How fast can an LLM go?(fergusfinn.com) 2 points by kkm 233 days ago \| 0 comments
19.	FHE can be leveraged for LLMs such as ChatGPT in a privacy-preserving manner(huggingface.co) 4 points by kkm 1 year ago \| 0 comments
20.	Harnessing the Power of Large Language Models for Insightful Review Analysis(techblog.holidaycheck.com) 1 points by kkm 2 years ago \| 0 comments
21.	A Privacy-First approach to use AI for understanding our Customers Better(techblog.holidaycheck.com) 1 points by kkm 2 years ago \| 0 comments
22.	How to make LLMs go fast(vgel.me) 2 points by kkm 2 years ago \| 0 comments
23.	Leveraging Large Language Models for Sentiment Classification in Hotel Reviews(techblog.holidaycheck.com) 1 points by kkm 2 years ago \| 0 comments
24.	1 points by kkm 3 years ago \| discuss
25.	Managers Should Think More Like Hackers(hbr.org) 3 points by kkm 3 years ago \| 0 comments
26.	Activists park burnt-out tank outside Russian Embassy in Berlin(feeds.thelocal.com) 3 points by kkm 3 years ago \| 0 comments
27.	Exposing 185M+ Indians’ Personal Information and much more(blog.robinjust.in) 3 points by kkm 3 years ago \| 0 comments