This is a submission for the Kaggle Benchmarking Challenge GPT-5.4 mini got a perfect 1.00 on my...
My benchmark scored GPT-5.4 mini 1.00 by silently skipping the 3 questions it failed
Related
A Word List Tied the Model
I tried to find out which of my comments mattered. The answer was not the one I built for. A few...
Prompt injection by email: we attacked our local AI inbox assistant. It reads everything and can send nothing
An AI assistant for your inbox is an obvious idea: read every message, sort what needs you, find the...
Guardrails for AI Agent Tool Calls That Write to Your ERP, in Python
One of our clients, an industrial equipment distributor with about $85 million in revenue, kept its...