Blog

Writing on enterprise AI, SaaS, and technology adoption.

Cerca per titolo, riepilogo o tag.

Filtri attivi: Tag: prompt injection ✕

1 articolo trovato

Inherited robustness: you cannot run the lab's test, and the evidence expires (GPT-Red). Model choice as a security control. News-pegged.

17 Jul 2026

Inherited robustness: you cannot run the lab's test, and the evidence expires (GPT-Red). Model choice as a security control. News-pegged.

Most organisations believe they have a rough sense of how exposed their AI systems are. Something OpenAI published this week shows how much of that judgement rests on evidence they cannot reproduce. It has built GPT-Red, an internal automated attacker trained specifically to break AI systems. By the

Read more →