I tried this with a more technical prompt... and what can I say? I'm stunned at the incredible command of jargon here. It's even mostly correct with the actual technical details at a glance, especially that description of how radar works! I can't wait for those research paper generators to use stuff like this to make high caliber fakes.
Prompt:
> Synthetic aperture radar imaging is an effective method for
Results:
> Synthetic aperture radar imaging is an effective method for detecting the presence and/or quantification of target objects, including: detection and tracking of moving targets, which are known to be difficult with visible imaging and/or laser radar; monitoring the occupancy of an enclosed space, such as a room, by the presence of occupants therein; and detection of moving objects, including animals and pedestrians, as well as people. A radar device is composed of an antenna, a receiver, and a transmitter. The antenna radiates a beam of energy (e.g., electromagnetic radiation in the radiofrequency range) that is received by the receiver. The transmitter then transmits an interrogating signal to the target(s). The time delay between transmission and reception at the target(s) is used to measure the range of the target(s) from the radar device. All targets in the field of view of the radar device contribute to the signal received by the receiver. The transmitter amplitude and/or phase modulates the signal transmitted to the target(s) with the information to be encoded, typically at a much higher modulation rate than that used
Another prompt:
> Fringe fields in microstrip patch antennas
Results (shortened by me for brevity):
> Fringe fields in microstrip patch antennas and their RF performance
> 1. The microstrip patch antenna is a conventional patch antenna that is created by a thin layer of insulating material placed on top of a conductive substrate. The antenna is excited by a current in the conductive layer in the vicinity of the antenna.
Now I have a question. How does this GPT-J know what a patch antenna is? It's able to give an almost correct description of this rather technical device. It made the mistake of flipping conductive material and insulating substrate, but it's very close. Does this neural network have the "knowledge" of a patch antenna in the weights? How does that even work? It seems kind of incredible.
To me this really is not that impressive. Responding to a definition request of some concrete technical object is basically just a dictionary look up task. Responding to more abstract input especially having to do with the meaningful relationship of multiple objects in space and time is more dificult. For example in a sex related prompt, I find the AI confuses gender role, i.e. he was so wet, her nipples were pulsating, and it gets confused about other object relations.
Prompt:
> Synthetic aperture radar imaging is an effective method for
Results:
> Synthetic aperture radar imaging is an effective method for detecting the presence and/or quantification of target objects, including: detection and tracking of moving targets, which are known to be difficult with visible imaging and/or laser radar; monitoring the occupancy of an enclosed space, such as a room, by the presence of occupants therein; and detection of moving objects, including animals and pedestrians, as well as people. A radar device is composed of an antenna, a receiver, and a transmitter. The antenna radiates a beam of energy (e.g., electromagnetic radiation in the radiofrequency range) that is received by the receiver. The transmitter then transmits an interrogating signal to the target(s). The time delay between transmission and reception at the target(s) is used to measure the range of the target(s) from the radar device. All targets in the field of view of the radar device contribute to the signal received by the receiver. The transmitter amplitude and/or phase modulates the signal transmitted to the target(s) with the information to be encoded, typically at a much higher modulation rate than that used
Another prompt:
> Fringe fields in microstrip patch antennas
Results (shortened by me for brevity):
> Fringe fields in microstrip patch antennas and their RF performance
> 1. The microstrip patch antenna is a conventional patch antenna that is created by a thin layer of insulating material placed on top of a conductive substrate. The antenna is excited by a current in the conductive layer in the vicinity of the antenna.
Now I have a question. How does this GPT-J know what a patch antenna is? It's able to give an almost correct description of this rather technical device. It made the mistake of flipping conductive material and insulating substrate, but it's very close. Does this neural network have the "knowledge" of a patch antenna in the weights? How does that even work? It seems kind of incredible.