Fetching from the wire…
01
02
03
04
05
06
07
08
Research2026-06-19 · source-backed
Chang and colleagues (arXiv:2606.20482) show implicit signals, mouse movement and eye-gaze, leak user preferences strongly enough to align LLMs without collecting explicit feedback or training a separate reward model. Agent interfaces could learn from natural interaction telemetry instead of thumbs-up/down prompts. The privacy flip side is obvious and uncomfortable: the same signals that improve alignment reveal preferences users never chose to share. If you build this, the consent conversation is not optional.
Each link below shares sources, entities, or timing with this story.
Shared entities / Same source domain / What happened next
Both cover Agent, LLMs; reported by the same outlet (arxiv.org); picks up the Agent thread on 2026-07-19.
Shared entity: LLMs / Same source domain / Shared topic / What happened next
Both cover LLMs; reported by the same outlet (arxiv.org); overlapping topics (explicit, llms).
Shared entity: LLMs / Same source domain / Shared topic / Earlier coverage
Both cover LLMs; reported by the same outlet (arxiv.org); overlapping topics (agent, llms).
Shared entity: Agent / Same source domain / Shared topic / Earlier coverage
Both cover Agent; reported by the same outlet (arxiv.org); overlapping topics (agent, chang).
Shared entity: LLMs / Same source domain / Shared topic / Earlier coverage
Both cover LLMs; reported by the same outlet (arxiv.org); overlapping topics (agent, llms).
Both cover LLMs; reported by the same outlet (arxiv.org); overlapping topics (agent, llms).
Shared entity: Agent / Same source domain / What happened next / Downstream implication
Both cover Agent; reported by the same outlet (arxiv.org); picks up the Agent thread on 2026-08-19.
Shared entity: Agent / Shared topic / What happened next / Tension
Both cover Agent; overlapping topics (agent, chang); picks up the Agent thread on 2026-08-17.