Breaking news, curated around the clock
Home /Tech

OpenAI Uses AI Red Team to Strengthen GPT-5.6 Against Prompt Injection Attacks

Tech | 2026-07-15 at 20:50 UTC | Source: decrypt.co
OpenAI Uses AI Red Team to Strengthen GPT-5.6 Against Prompt Injection Attacks
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.
Read Full Article →
← More Tech news
Related Articles
2026-11-03 · 14:14
Just a little AI resistance, as a treat
A customer complained to Ocado about malformed calendar invites and received a response that appeared to be…
2026-11-03 · 14:53
OpenAI seems to be silently re-enabling model training on Codex chats
OpenAI users report that the "Improve the model for everyone" data-sharing setting was silently re-enabled in…
2026-11-03 · 01:12
Ukraine’s new pocket-sized gadget turns Russian drones’ cameras against them
A Kyiv startup’s pocket-sized, 10-ounce receiver lets Ukrainian troops watch the video feeds of Russian…
2026-11-03 · 17:40
Qwen 3.8 27B on my laptop can interpret model weights, too
Researchers discovered that large language models, including smaller models like Qwen 3.8 27B running locally,…
2026-11-03 · 07:20
Apple Watch’s AI features for rewinding and recapping conversations begin beta testing
Now in beta: Apple's new Audio Intelligence features can help you remember what someone said or take notes on…