Got distracted before finishing edits. Makes me wonder whether chatgpt’s commentary here asking it to come up with its own [parable of predict-o-matic](https://www.lesswrong.com/posts/SwcyMEgLyd4C3Dern) - might have been more insightful than I realized at the time. It might actually be competitive as as a short parable of predict-o-matic, in a descriptive sense, if competing for the name.
Posting to shortform because there are many of these. While searching for posts to share as prior work, I found the parable of predict-o-matic, and found it to be a very good post about self-fulfilling prophecies (tag). I thought it would be interesting to see what ChatGPT had to say when prompted with a reference to the post. It mostly didn’t succeed. I highlighted key differences between each result. The prompt:
Describe the parable of predict-o-matic from memory.
samples (I hit retry several times):
The parable of predict-o-matic is a story about a powerful machine that can predict the future with incredible accuracy. It is a valuable tool for those who can afford it, but it has a dark side.
The machine is used by a wealthy and powerful man to gain even more wealth and power. He uses it to predict the stock market, elections, and other events, and he always comes out ahead.
However, one day, the man’s son begins to question the ethics of using the machine. He realizes that by predicting the future, the machine is taking away free will and choice from those who are not privy to its predictions.
The son eventually destroys the machine, but not before it predicts its own destruction. The parable ends with the message that although knowledge of the future may be useful, it also comes with great responsibility and the potential for harm.
Of course, there’s prior art it was pulling from, including the post on less wrong which is much longer and gets into the point more and explores all the interesting and varied ways it could go in reality at a company building such a thing, but I’ve never seen any presented in a distilled format like this. Very nicely done, IMO.
Got distracted before finishing edits. Makes me wonder whether chatgpt’s commentary here asking it to come up with its own [parable of predict-o-matic](https://www.lesswrong.com/posts/SwcyMEgLyd4C3Dern) - might have been more insightful than I realized at the time. It might actually be competitive as as a short parable of predict-o-matic, in a descriptive sense, if competing for the name.
Of course, there’s prior art it was pulling from, including the post on less wrong which is much longer and gets into the point more and explores all the interesting and varied ways it could go in reality at a company building such a thing, but I’ve never seen any presented in a distilled format like this. Very nicely done, IMO.