Does whispering to agents in docs help?
I’m seeing more instances of docs and README files addressing agents directly, as in “Hey, if you’re an agent, follow these instructions”. In some cases, those instructions are visible to human readers as well, which makes for a deeply awkward experience, the reading equivalent of getting a robotic kick in the butt. Is this whistling to machines helpful? I ran some experiments to find out.
Summary
The article investigates the trend of addressing AI agents directly in documentation, highlighting the potential confusion it creates for human readers. The author shares experimental findings on whether this practice is beneficial for the agents or merely awkward for users.
Comments (9 of ) ⌛