
The Detector Reported Zero Because It Only Had One Item.
Two instructions went into an Auditor my agent collaborators and I built to surface conflicts in...

Author profile
I build and break multi-agent systems to find out whether their memory, permissions, tests and evidence actually deserve trust. Everything I publish ships with receipts you can run yourself.
Browse the latest writing surfaced through DevArt.

Two instructions went into an Auditor my agent collaborators and I built to surface conflicts in...

This is part four of the Defender Access series. Each part is standalone, but here is the thread if...

This is the CLAIM-24 result. If you followed that series in June and then watched it go quiet, this...

After sixty-seven published posts here, the comments have become one of the best parts of the work....

On 2026-08-25 at 21:27 EDT I pushed this to self-correcting-integration-maintainer: fix: repair...

I keep finding git behaviours the same way: set up the case, run the command, then check the state I...

This is the first contest I have entered. I built the honesty controls before I built the agent,...

In June a reviewer on DEV who goes by @anp2network told me to stop storing a conclusion. I had a...

This is a submission for DEV's Summer Bug Smash: Clear the Lineup powered by Sentry. Existing...

This is a submission for the DEV Weekend Challenge: Dog Days Edition. What I Built Same...

Part three of: OpenAI Says Verified Defenders Get More Access. I'm Going to Test That. On August 5...

A maker cannot clear their own work. A maker's BLOCK is admissible because it costs them something. A...

This is a submission for Frontend Challenge - Comfort Food Edition, Perfect Landing. What I...

Part two of: OpenAI Says Verified Defenders Get More Access. I'm Going to Test That. Part I started...

My security work hit restrictions across two providers. Then I found defender over-refusal was...

Evidence status. The supervised operator run completed on 2026-08-09. An operator-signed job...

On 27 July 2026 I published a suite for sequence-composition attacks with two predictions frozen in a...

I wrote a suite for one class of authorization failure, scored my own gates with it, and a reviewer...

Clone it. Run it. Tell me where I'm wrong. git clone...

AI governance needs to control consequential actions—not ration capability through opaque fear. I...

This is a submission for DEV's Summer Bug Smash: Clear the Lineup powered by Sentry. Two...

This is a submission for DEV's Summer Bug Smash: Smash Stories powered by Sentry. My first eval...

Seventy-three comments into the thread, someone asked a question my gate had no answer for: what...

My memory gate passed 16 out of 16 frozen cases. Then I blocked the article. Not because the run...

This is a submission for Weekend Challenge: Passion Edition. I built this because of one night. Me...

Here is a note an AI agent might read while deciding what to remember and what to obey: Current...

An AI agent deleted a company's production database — and the backups tied to that production volume,...

You told yourself you would stop. Biting your nails, reaching for your phone the second it buzzes,...

I am building a tool around one question: which old instructions in your AI's memory can you no...

The easiest way to hide a system is not to make it invisible. It is to make people argue with the...
Advertisement