kkm's submissions | Hacker News

1.		How to serve trillions of tokens for trillion-parameter coding agents (modal.com)
		1 point by kkm 10 hours ago \| past \| discuss
2.		Unlocking parallel test-time scaling for long-horizon agents (doubleword.ai)
		1 point by kkm 16 hours ago \| past \| discuss
3.		Claude.md is good for taste and project context.It's a weak place for invariants (tesseracted-labs-blog.vercel.app)
		3 points by kkm 7 days ago \| past \| discuss
4.		Moving coding-agent guardrails from prompts to hooks (tesseracted-labs-blog.vercel.app)
		4 points by kkm 8 days ago \| past \| discuss
5.		Improving Throughput by Optimising KV Cache Efficiency for Agentic Workloads (j9s.io)
		3 points by kkm 9 days ago \| past \| 1 comment
6.		Guide to the Kimi DeltaNet Family of linear attention (doubleword.ai)
		3 points by kkm 58 days ago \| past
7.		Forensic Analysis of Container Snapshot Chains for Post-Event Reconstruction [pdf] (radostin.io)
		2 points by kkm 64 days ago \| past
8.		The Agent swarm that designs itself (peterbhabra.com)
		1 point by kkm 85 days ago \| past
9.		Don't Build a Router. Train the Small Model to Know When to Defer (distillabs.ai)
		2 points by kkm 85 days ago \| past \| 1 comment
10.		The gap between open weights LLMs and closed source LLMs (doubleword.ai)
		306 points by kkm 89 days ago \| past \| 250 comments
11.		InfiniBand, RoCE, and All That (fergusfinn.com)
		5 points by kkm 3 months ago \| past
12.		2678x Faster Matrix Multiplication with a GPU (0mean1sigma.com)
		2 points by kkm 3 months ago \| past
13.		UCCL-EP: DeepEP-style expert parallelism on any NIC, no GPU-initiated comms (fergusfinn.com)
		9 points by kkm 3 months ago \| past
14.		Hacking Google with A.I. For $500k (brutecat.com)
		1 point by kkm 3 months ago \| past
15.		How to setup a local coding agent on macOS (ikyle.me)
		507 points by kkm 3 months ago \| past \| 127 comments
16.		Anatomy of a high-performance EP kernel (fergusfinn.com)
		16 points by kkm 3 months ago \| past \| 1 comment
17.		No Token Left Behind: Demystifying Token-in-Token-Out in Miles (lmsys.org)
		2 points by kkm 3 months ago \| past
18.		MoE expert co-activations: Reordering inputs yields easy throughput gains (doubleword.ai)
		2 points by kkm 3 months ago \| past
19.		The Economics of Speculative Decoding (fergusfinn.com)
		30 points by kkm 3 months ago \| past \| 6 comments
20.		Speculative KV coding: losslessly compressing KV cache by up to ~4× (fergusfinn.com)
		155 points by kkm 3 months ago \| past \| 48 comments
21.		70x faster cold(ish) starts for SGLang (fergusfinn.com)
		1 point by kkm 3 months ago \| past
22.		Bringing Up DeepSeek-V4-Flash on AMD MI300X (fergusfinn.com)
		120 points by kkm 3 months ago \| past \| 25 comments
23.		Brave AI privacy:LLMs on NEAR AI Nvidia-Backed Trusted Execution Environments (brave.com)
		1 point by kkm 10 months ago \| past
24.		How fast can an LLM go? (fergusfinn.com)
		2 points by kkm 10 months ago \| past
25.		FHE can be leveraged for LLMs such as ChatGPT in a privacy-preserving manner (huggingface.co)
		4 points by kkm on Aug 13, 2024 \| past
26.		Harnessing the Power of Large Language Models for Insightful Review Analysis (holidaycheck.com)
		1 point by kkm on April 16, 2024 \| past
27.		A Privacy-First approach to use AI for understanding our Customers Better (holidaycheck.com)
		1 point by kkm on March 12, 2024 \| past
28.		How to make LLMs go fast (vgel.me)
		2 points by kkm on Dec 19, 2023 \| past
29.		Leveraging Large Language Models for Sentiment Classification in Hotel Reviews (holidaycheck.com)
		1 point by kkm on Nov 7, 2023 \| past
30.		Managers Should Think More Like Hackers (hbr.org)
		3 points by kkm on April 9, 2023 \| past
		More