"they emphasised that a human could also give erroneous advice."

I dunno, seems like humans don't do this as often or as impactfully. And when they do there are consequences. When will LLMs receive their pink slips?

https://www.theguardian.com/technology/2026/mar/20/meta-ai-agents-instruction-causes-large-sensitive-data-leak-to-employees

Meta AI agent’s instruction causes large sensitive data leak to employees

Artificial intelligence agent instructed engineer to take actions that exposed user and company data internally

The Guardian

@ennenine "A human knows the “context” of a task – the implicit knowledge that one should not, for example, set the sofa on fire in order to heat the room, or delete a little-used but crucial file, or take an action that would expose user data downstream."

If nothing else, gen pop is thinking really hard now about what being human is and why that's really cool.