FAQ: Five Myths About a TTY the Agent Does Not Have

Description and use

<p>Ever watch an agent freeze on a yes-no prompt? The model keeps talking like nothing blocked it. The process on the box waits for stdin.</p> <p>I keep seeing the same five claims in chat logs. People treat a headless agent box like a laptop. Then they blame the model when apt sits there.</p> <p>This FAQ is about TTY myths. It is not about model quality. It is not about git identity either.</p> <h2> Why these myths spread </h2> <p>A chat UI looks interactive, right? You type. It types back. That feeling lies.</p> <p>The free model writes a shell command. A free server may run that command. Th

Problem

<p>Ever watch an agent freeze on a yes-no prompt? The model keeps talking like nothing blocked it. The process on the box waits for stdin.</p> <p>I keep seeing the same five claims in chat logs. People treat a headless agent box like a laptop. Then they blame the model when apt sits there.</p> <p>This FAQ is about TTY myths. It is not about model quality. It is not about git identity either.</p> <h2> Why these myths spread </h2> <p>A chat UI looks interactive, right? You type. It types back. That feeling lies.</p> <p>The free model writes a shell command. A free server may run that command. Th

Outcome

<p>Ever watch an agent freeze on a yes-no prompt? The model keeps talking like nothing blocked it. The process on the box waits for stdin.</p> <p>I keep seeing the same five claims in chat logs. People treat a headless agent box like a laptop. Then they blame the model when apt sits there.</p> <p>This FAQ is about TTY myths. It is not about model quality. It is not about git identity either.</p> <h2> Why these myths spread </h2> <p>A chat UI looks interactive, right? You type. It types back. That feeling lies.</p> <p>The free model writes a shell command. A free server may run that command. Th

Evidence

FAQ: Five Myths About a TTY the Agent Does Not Have

Source