Posts tagged “model-safety”

• OpenAI Astra Puts the Research Cluster Inside the Safety Boundary

  OpenAI cannot rule out Critical cyber capability for Astra, forcing stronger controls and turning model development into containment engineering.

• OpenAI GPT-Red Turns Prompt Injection Into a Safety Training Flywheel

  OpenAI's internal GPT-Red turns prompt-injection attacks into training data. Here is what the results prove, what remains private, and why it matters.

← Back to blog