Plain writing about what's inside your AI.
Short reads from the house that reads AI models — and proves what it finds. No jargon, no hype. Pick the lane that fits the question you came with.
Posts
For buildersWe didn't just catch the hidden backdoor — we read out what it was told to do
The hardest backdoors are built so no test can ever trigger them — off-the-shelf scanners see nothing. We read the tampered model's own file and recovered the exact secret instruction, without setting it off.
For everyoneDo you actually know what's inside the AI you use?
Most companies run AI they didn't build and have never read. Here's why the label on the box isn't proof — and what to ask instead.
UpdatesWe hid a backdoor in a public model — and sealed the answer first
Seven open models, one with a secret trap, out in the open. The catch: we locked the answer before anyone could look.
For buildersThe name on the model isn't proof. The file is.
You can test what a model does, or you can read what it is. Only one of those can find a backdoor you don’t already know about.
UpdatesWe're reading the open models people actually download — in public
A living, public library of open AI models and what they really are. It grows every time we read another one.
On the rulesNew rules are coming for AI. Here's the plain version.
You'll soon need to show evidence of what your AI is and does — not just say it. That sounds like a burden. It can be a routine.