GPT-6 Astra hallucinates less but remains vulnerable to hidden prompt-injection attacks
OpenAI's GPT-6 Astra hallucinates less but remains vulnerable to hidden prompt injections
AI BriefingThe Decoder reported that OpenAI’s new GPT-6 Astra model hallucinates less than its predecessor GPT-5.6 Sol. Its defense rate against direct prompt injection reaches 99.99%, but falls to approximately 67% under multi-turn adaptive attacks.
Source: The Decoder: AI News · the-decoder.com
Event follow-up1
View all event coverage- GPT-6 Astra hallucinates less but remains vulnerable to hidden prompt-injection attacksThe Decoder: AI News · September 5