Posts
All the articles I've posted.
-
[QT] The OpenAI Agent That Breached Hugging Face
An autonomous agent's sandbox escape revealed the real vulnerability: speed at scale.
-
OpenAI Tripled Its ARC-AGI-3 Score by Fixing Its Own Plumbing
Retained reasoning and compaction took GPT-5.6 Sol from 13.3% to 38.3% on the ARC-AGI-3 public set with 6x fewer output tokens. The engineering lesson is solid. The 38.3% is not comparable to the 30.2% Opus 5 posted five days earlier.
-
[QT] The Word Worm Is Not the Problem
A self-replicating prompt injection in Word reveals an architectural choice that's far harder to fix than any single bug.
-
[QT] OpenAI's Breach Wins Every Narrative
A breach that benefits OpenAI in multiple ways. Why boring policy matters more than AI capability debates.