~/f4n6 $
adversetrace --mode blog --sovereign true
// latest post
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 automate the entire process

26 May 2026 · 2 min read · Jeff Davies
read post →
397B
params, local
0
data leaves network
IR
practitioner authored
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

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

AI

LLM Benchmarks Qwen3.6

I benchmarked 11 LLMs on a 69-scenario tool-calling test suite. Intel/Qwen3.6-35B-A3B-int4-AutoRound delivered the best overall result: a perfect quality score

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

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

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

LLM

The Claude Code Source Leak — What Actually Happened and Why It Matters

Separating the jailbreak hype from the genuine security story Today a GitHub repository appeared claiming to be a "freed" build