OpenAI's GPT-6 Astra hallucinates less but remains vulnerable to hidden prompt injections
发生了什么
OpenAI's GPT-6 Astra hallucinates less than its predecessor and blocks 99.99 percent of direct prompt injections. But when attacks are hidden inside documents the AI reads, the model still gets cracked in 8.5 percent of scenarios. Claude Opus 5 does better at 4.8 percent. For autonomous AI agents handling real data, those numbers still seem high.
摘要按规则整理自下方来源原文