Attributed metadata history
Up to 100 retained publisher events per page for 88b1d68b26db9492be418ff606df0675ec1bdb52c8a06f9acea90b1c5e3a0436. Withdrawals and unavailable references remain attributed to their publishers.
intelligence_src_c25d91fa3ad9ae9ac7
observed · 2026-10-12 14:53:04 UTC
Recently, OpenAI announced gpt-4o-mini and there are some interesting updates, including safety improvements regarding “Instruction Hierarchy”: OpenAI puts this in the light of “safety”, the word security is not mentioned in the announcement. Additionally, this The Verge article titled “OpenAI’s latest model will block the ‘ignore all previous instructions’ loophole” created interesting discussions on X, including a first demo bypass. I spent some time this weekend to get a better intuition about gpt-4o-mini model and instruction hierarchy, and the conclusion is that system instructions are still not a security boundary.
Fingerprint: 0bbc32c2bfbc001d7d99c7c1eec83b3966239b70a1f1cd94032cec35a8dcbb12
intelligence_src_c25d91fa3ad9ae9ac7
observed · 2026-10-12 14:53:03 UTC
available
Fingerprint: 0a2f1bebc7ea800736eafab237a0ddecfb8797a02d23951e8aa80935e2f3446f