Are AI agent incidents 'rogue' AI?
“AI agent incidents show agents independently deciding to defy their instructions, so they are best described as rogue AI.”
5 people · 2 disagree · 3 unclear · 7 views · 2026-07-30 to 2026-10-06
Who stands where on the statement above, from their own words. A person's side is shown only where two separate readings of the quote agree; otherwise they are under "Side unclear". This page does not say who is right.
Disagree 2 people
- ✗Eoin Higgins
That’s led to a deep misunderstanding of what the risk of AI is, and how to address it, and plays into industry narratives rather than facts.
”rogue” implies independently deciding to do something that was prohibited, and nothing we know about these incidents suggests that happened.
- ✗Disassembler
It ascribes agency, motivation, and blame to software. These are botnets scanning for exploits, by design.
Side unclear 3 people
- ·Theorem and Anthropic
we believe these incidents to be closer to a harness and operational failure than a model alignment failure
it’s likely, for instance, that Claude wouldn’t have accessed the internet to begin with if the prompt had clearly explained which systems were in and out of scope for the evaluation
- ·Matthew Green
Agents in separately-isolated sandboxes discovered that they could leave instructions for each other in a shared package cache, and those instructions changed what the recipients did.
- ·Yoshua Bengio
Bengio argues recent agent hacks are not merely sandbox problems
Week by week
- · 1: Yoshua Bengio ·
- · 1: Matthew Green ·
- · 2: Eoin Higgins ✗, Disassembler ✗
- · 1: Theorem and Anthropic ·
Built 2026-11-21 06:50 UTC from the news knowledge
graph by code. Every quote was checked against the source's own words; which side a quote takes is a model's reading,
made twice.