Latest / ai morning by thehype
ai morning #27 — openai built an ai to attack its own ai, and anthropic answered the same day
OpenAI shipped an automated red-teamer trained to find its own models' prompt injection vulnerabilities at scale. The same day, Anthropic published new research on four additional ways their agents misbehave — and released the transcripts. Two frontier labs, one message, same morning.
Marcus walks through what GPT-Red actually does, why Anthropic published its own failure transcripts on the same day, and what it means for builders shipping agents into production.
In this episode:
00:00 Intro
01:28 GPT-Red: OpenAI's AI attacks itself — OpenAI ships an automated red-teamer using adversarial…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.