Articles by kkm
16

Speculative KV coding: losslessly compressing KV cache by up to ~4× (fergusfinn.com)

1

70x faster cold(ish) starts for SGLang (fergusfinn.com)

34

Bringing Up DeepSeek-V4-Flash on AMD MI300X (fergusfinn.com)

1

Brave AI privacy:LLMs on NEAR AI Nvidia-Backed Trusted Execution Environments (brave.com)

2

How fast can an LLM go? (fergusfinn.com)

2

FHE can be leveraged for LLMs such as ChatGPT in a privacy-preserving manner (huggingface.co)

1

Harnessing the Power of Large Language Models for Insightful Review Analysis (holidaycheck.com)

1

A Privacy-First approach to use AI for understanding our Customers Better (holidaycheck.com)

1

How to make LLMs go fast (vgel.me)

1

Leveraging Large Language Models for Sentiment Classification in Hotel Reviews (holidaycheck.com)

2

Managers Should Think More Like Hackers (hbr.org)

2

Activists park burnt-out tank outside Russian Embassy in Berlin (thelocal.com)

3

Exposing 185M+ Indians’ Personal Information and much more (blog.robinjust.in)

2

Converse with book – Built with GPT-3 (github.com/namuan)

33

ZeroSSL: XSS to session hijacking, stealing a private key (and password hash) (groups.google.com)

1

Converse with a Book [pdf] (github.com/namuan)

2

Hashgraph: The Sustainable Alternative to Blockchain (stackoverflow.blog)

13

Kraken.com: Proof of Reserves (kraken.com)

31

Climate geoengineering via stratospheric aerosol injection (deeplearning.ai)

35

User-Agent Reduction (akamai.com)

2

Geo-Locating Telegram Users with Telepathy (os2int.com)

1

What does GPT-3 “know” about me? (technologyreview.com)

2

Practically-exploitable Cryptographic Vulnerabilities in Matrix [pdf] (nebuchadnezzar-megolm.github.io)