Back to Featured
The Decoder:AI NewsMatthias Bastian2026-09-05 01:23September 5

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 Briefing

The 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

Finished reading the news? Let’s talk about your business.

Leave your contact details, and I’ll get in touch with you personally.

WECHAT

Add me on WeChat

Press and hold or select the WeChat ID below to copy it.