Zork – 1977 text adventuredeveloped by Tim Anderson, Marc Blank, Bruce Daniels and Dave Lebling. It was originally released for the PDP-10 mainframe, and later as a commercial product for the PC. The game became a springboard for the American company Infocom, which is now producing a variety of software.
Of course it was not the first in the worlda text adventure, but its difficulty was significantly higher than anything that had been released before it. The text parser was designed to allow players to enter “natural” speech, and the game interpreted these commands and acted as a sort of narrator or dungeon master, explaining what happened and the current situation/location.
“Some fans of adventure games inGoogle wondered what would happen if you used the result of the classic text adventure game “Zork” as input to Imagen, Google's text-to-image conversion model, – writes Google Chief Engineer Matt Walsh, – To confirm the desired results, we made some additions to Zork itself, which was a fascinating journey through a mysterious language and a lost toolchain.
The game has a text description of adventuresplayer, which is used as a tooltip for the Imagen imaging tool. However, things are not that simple, and the team had to work on how the game presented information and how artificial intelligence interprets it.
However, the most surprising thing about this is thatImagen is capable of generating a wide range of art styles. The example shown in the video – it is a white house depicted in a variety of ways, from Rembrandt pastiche to mosaics and pencil drawings. The various other locations shown also vary in style, ranging from photorealistic to impressionistic.
This is a prime example of how newpay tribute to the old. No one knows where we'll end up with these AI tools, but using them to breathe some life into the interactive past certainly seems like one of the most forgiving uses.