News for hackers. Stuff that matters.

A comment on Hybrid Reasoning Agents: LLM agents that think in latent space, act through text. Parent comment

Re:Hybrid Reasoning Agents: LLM agents that think in latent ... by throwaway314155 on Sunday October 18, 2026 @06:37PM (#50146212)
> hey currently monitor it to prevent users from using their models in certain ways they consider unsafe or bad for their business

Can't they just monitor the text outputs as well?

[ Parent | on HN ]

There are no comments on this comment yet.