Prompt Injection Crisis: OpenAI Deploys Savage AI Hunter Across Thousands of Attacks
OpenAI’s GPT-Red uses self-play red teaming to find prompt injection flaws at scale, hardening GPT-5.6 against adversarial attacks before they reach users.
Artificial intelligence through a market lens: earnings from the companies building AI, chip demand and supply, valuations, funding rounds, and the capital flowing into compute and data centres.
OpenAI’s GPT-Red uses self-play red teaming to find prompt injection flaws at scale, hardening GPT-5.6 against adversarial attacks before they reach users.