Sovereign - f4n6

AI

EvilTokens

Original inspiration for this from https://abnormal.ai/blog/eviltokens-oauth-device-codes-bec-operations EvilTokens Is Still Live: Three Months On, the PhaaS Platform Has

25 Jun 2026 · 19 min read read →

AI

I don't believe in threat intel, so I built a threat intel platform

Let me get the bias out of the way first, because it shapes everything that follows. I don't hold much weight in threat intel.

08 Jun 2026 · 6 min read read →

LLM

Finding Evil: When Full Automation Falls Short

So I started down the path of building an automated DFIR pipeline. As mentioned previously, SANS announced an AI Hackathon, and my original idea was to

26 May 2026 · 2 min read read →

AI

TP=4 Qwen3.5-397B on DGX Spark: From Silent Zeros to 41.5 tok/s

Or: how I spent twelve hours building a workaround for a flag that already existed I run a four-node DGX Spark cluster for local DFIR

08 May 2026 · 8 min read read →

AI

Building a deterministic-ish DFIR pipeline for the SANS AI hackathon

SANS recently announced their first hackathon for autonomous incident response — open to the community, build something that uses AI to figure out what the bad guys

30 Apr 2026 · 1 min read read →

LLM

Three companies, one OAuth token, and the case for sovereign AI

On 19 April 2026, Vercel disclosed a security incident. Within 48 hours, the public attack chain had resolved into something more interesting than the initial "

20 Apr 2026 · 7 min read read →

LLM

DORA gap analysis in 2 hours — no data left the building

DORA came into force in January 2025. Financial entities across the EU are supposed to be compliant. Most aren't — at least not fully — and

10 Apr 2026 · 2 min read read →

AI

GLM-4.7-Flash on Nvidia GB10

So I have gotten into running my own local llm for privacy reasons, and like to use it to assist with incident response tasks and collecting

31 Mar 2026 · 9 min read read →