Decrypt ••1 min read
OpenAI Uses AI Red Team to Strengthen GPT-5.6 Against Prompt Injection Attacks
The Signal TakeBullish
OpenAI said its new automated red-teaming model, GPT-Red, uncovered vulnerabilities that were used to make GPT-5.6 more resistant to prompt injection attacks.
📱
Never miss a Web3 update
Join our Telegram channel to receive news in real-time, straight to your phone.
Related News
From Perpetual Swaps to Perpetual CFDs: The Regulated Evolution
The Block•2h ago
Crypto money is flooding both parties, from a central source - OpenSecrets
Apify/OpenSecrets•2h ago
Stripe-PayPal deal could accelerate shift to blockchain-based money, Polygon exec says
The Block•3h ago
Public Hyperliquid treasury firm Hyperion enters into new 500k HYPE bond agreement with Skew
The Block•3h ago