DogLM vs TermRover

A benchmark measuring whether an LLM lets the player pet the dog when prompted to build a video game that has a dog in it.

TermRover is a native SSH + Mosh terminal optimized for working with tmux on iPhone and Android. Browser-style tabs, one-tap prefix actions, and scrolling all just work.

About DogLM

A benchmark measuring whether an LLM lets the player pet the dog when prompted to build a video game that has a dog in it. DogLM, Can you pet the dog in an AI-generated game? a video game with a background dog character in it, lets the player pet that dog. ): if a game has a dog, the player should be able to pet it. The benchmark, the games' descriptions, and the detailed methodology are available here.

About TermRover

TermRover is a native SSH + Mosh terminal optimized for working with tmux on iPhone and Android. Browser-style tabs, one-tap prefix actions, and scrolling all just work. The tmux prefix, usually Ctrl-b, is awkward on a touchscreen. Scrolling is worse: it usually requires mouse mode and changes to .tmux.conf, with no clear indication whether it is enabled., tapping the terminal should open the keyboard, and sending a screenshot to a coding agent. It immediately made sense for a phone: SSH can drop as you move between networks, while Mosh keeps the terminal working.