Oops! It looks like you already are doing this. At least you say so in the instructions but it's not clear from the actual example you give . Did you generate the story from images and artifacts of Pompeii?
Because you can make tax from images as well as you can make images from text, have you tried using frescoes or mosaics, or even other visual artifacts from Pompeii, and then asking ChatGPT to reverse engineer the prompt? For some reason doing it this way provides a more detailed description of the image than when you simply ask it to caption it. This is just another way to continue the historical fiction telephone game.
Thank you for this. Yes, this is an interesting option. Two different factors to think about:
1) For the initial text prompt which starts the simulation, you can add a visual primary source and ask it to "take this as inspiration for developing a realistic historical scenario based on this image." It works ok, but for older artworks and artifacts it veers toward fantasy (I tried it with Brueghel's "Triumph of Death" and the results were interesting but not useful for teaching -- it dropped me in the late 15th Netherlands where a fountain had begun overflowing with black water). However I think this has a lot of promise when it comes to simulating time periods like the 19th or 20th centuries, using historical photographs.
2) In terms of using historical images or artifacts to help the *image* generator, this is worth experimenting with more. Perhaps next time I develop a prompt for a simulation of a given time/place, I'll also give students a set of a dozen or so images and ask them to feed those in where appropriate when generating images. Definitely has potential, but the issue is that right now it involves too many steps to really work in a classroom - would have to be automated.
This is the primary source I used for the Pompeii simulation prompt:
"PRIMARY SOURCE: From Pliny the Younger's firsthand account: On the 24th of August, about one in the afternoon, my mother desired him to observe a cloud which appeared of a very unusual size and shape. He had just taken a turn in the sun93 and, after bathing himself in cold water, and making a light luncheon, gone back to his books: he immediately arose and went out upon a rising ground from whence he might get a better sight of this very uncommon appearance. A cloud, from which mountain was uncertain, at this distance (but it was found afterwards to come from Mount Vesuvius), was ascending, the appearance of which I cannot give you a more exact description of than by likening it to that of a pine tree, for it shot up to a great height in the form of a very tall trunk, which spread itself out at the top into a sort of branches; occasioned, I imagine, either by a sudden gust of air that impelled it, the force of which decreased as it advanced upwards, or the cloud itself being pressed back again by its own weight, expanded in the manner I have mentioned; it appeared sometimes bright and sometimes dark and spotted, according as it was either more or less impregnated with earth and cinders... broad flames shone out in several places from Mount Vesuvius, which the darkness of the night contributed to render still brighter and clearer. But my uncle, in order to soothe the apprehensions of his friend, assured him it was only the burning of the villages, which the country people had abandoned to the flames: after this he retired to rest, and it is most certain he was so little disquieted as to fall into a sound sleep: for his breathing, which, on account of his corpulence, was rather heavy and sonorous, was heard by the attendants outside. The court which led to his apartment being now almost filled with stones and ashes, if he had continued there any time longer, it would have been impossible for him to have made his way out. So he was awoke and got up, and went to Pomponianus and the rest of his company, who were feeling too anxious to think of going to bed. They consulted together whether it would be most prudent to trust to the houses, which now rocked from side to side with frequent and violent concussions as though shaken from their very foundations; or fly to the open fields, where the calcined stones and cinders, though light indeed, yet fell in large showers, and threatened destruction. In this choice of dangers they resolved for the fields. "
Thank you for these posts Benjamin. I'm an Irish historian and have been tasked with giving a talk on tech and the teaching of the history of the Irish revolution - I plan on citing your example here. I'm in the early stages of a project on video games and Irish history and your posts have also helped me think through that topic.
Your initiative in using ChatGPT for interactive history lessons is incredible! Integrating images via multimodal AI enhances the immersive experience, making history more palpable and empathetic. This innovative blend of text and visuals not only engages but fosters a deeper understanding of historical contexts, reminding us of the uncertainties faced by people in the past. It’s a groundbreaking approach that redefines how we perceive and teach history, providing a unique and invaluable learning avenue. Looking forward to seeing more fascinating applications!
If only you could cross-reference these prompts with some sort of retrieval-augmented generation from a database of historical facts about Pompeii and Roman life during the period to bring in relevant primary source material on a per-turn basis in the simulation to narrow in on the relevance. If this is something of interest to you, please don't hesitate to reach out! You can find me at https://twitter.com/the_key_unlocks on Twitter.
Oops! It looks like you already are doing this. At least you say so in the instructions but it's not clear from the actual example you give . Did you generate the story from images and artifacts of Pompeii?
Because you can make tax from images as well as you can make images from text, have you tried using frescoes or mosaics, or even other visual artifacts from Pompeii, and then asking ChatGPT to reverse engineer the prompt? For some reason doing it this way provides a more detailed description of the image than when you simply ask it to caption it. This is just another way to continue the historical fiction telephone game.
Thank you for this. Yes, this is an interesting option. Two different factors to think about:
1) For the initial text prompt which starts the simulation, you can add a visual primary source and ask it to "take this as inspiration for developing a realistic historical scenario based on this image." It works ok, but for older artworks and artifacts it veers toward fantasy (I tried it with Brueghel's "Triumph of Death" and the results were interesting but not useful for teaching -- it dropped me in the late 15th Netherlands where a fountain had begun overflowing with black water). However I think this has a lot of promise when it comes to simulating time periods like the 19th or 20th centuries, using historical photographs.
2) In terms of using historical images or artifacts to help the *image* generator, this is worth experimenting with more. Perhaps next time I develop a prompt for a simulation of a given time/place, I'll also give students a set of a dozen or so images and ask them to feed those in where appropriate when generating images. Definitely has potential, but the issue is that right now it involves too many steps to really work in a classroom - would have to be automated.
This is the primary source I used for the Pompeii simulation prompt:
"PRIMARY SOURCE: From Pliny the Younger's firsthand account: On the 24th of August, about one in the afternoon, my mother desired him to observe a cloud which appeared of a very unusual size and shape. He had just taken a turn in the sun93 and, after bathing himself in cold water, and making a light luncheon, gone back to his books: he immediately arose and went out upon a rising ground from whence he might get a better sight of this very uncommon appearance. A cloud, from which mountain was uncertain, at this distance (but it was found afterwards to come from Mount Vesuvius), was ascending, the appearance of which I cannot give you a more exact description of than by likening it to that of a pine tree, for it shot up to a great height in the form of a very tall trunk, which spread itself out at the top into a sort of branches; occasioned, I imagine, either by a sudden gust of air that impelled it, the force of which decreased as it advanced upwards, or the cloud itself being pressed back again by its own weight, expanded in the manner I have mentioned; it appeared sometimes bright and sometimes dark and spotted, according as it was either more or less impregnated with earth and cinders... broad flames shone out in several places from Mount Vesuvius, which the darkness of the night contributed to render still brighter and clearer. But my uncle, in order to soothe the apprehensions of his friend, assured him it was only the burning of the villages, which the country people had abandoned to the flames: after this he retired to rest, and it is most certain he was so little disquieted as to fall into a sound sleep: for his breathing, which, on account of his corpulence, was rather heavy and sonorous, was heard by the attendants outside. The court which led to his apartment being now almost filled with stones and ashes, if he had continued there any time longer, it would have been impossible for him to have made his way out. So he was awoke and got up, and went to Pomponianus and the rest of his company, who were feeling too anxious to think of going to bed. They consulted together whether it would be most prudent to trust to the houses, which now rocked from side to side with frequent and violent concussions as though shaken from their very foundations; or fly to the open fields, where the calcined stones and cinders, though light indeed, yet fell in large showers, and threatened destruction. In this choice of dangers they resolved for the fields. "
Thank you for these posts Benjamin. I'm an Irish historian and have been tasked with giving a talk on tech and the teaching of the history of the Irish revolution - I plan on citing your example here. I'm in the early stages of a project on video games and Irish history and your posts have also helped me think through that topic.
Thank you Maurice, delighted to hear that it's helpful.
Your initiative in using ChatGPT for interactive history lessons is incredible! Integrating images via multimodal AI enhances the immersive experience, making history more palpable and empathetic. This innovative blend of text and visuals not only engages but fosters a deeper understanding of historical contexts, reminding us of the uncertainties faced by people in the past. It’s a groundbreaking approach that redefines how we perceive and teach history, providing a unique and invaluable learning avenue. Looking forward to seeing more fascinating applications!
Techtopia | Future Tech Insights
https://www.techtopia5.com/
If only you could cross-reference these prompts with some sort of retrieval-augmented generation from a database of historical facts about Pompeii and Roman life during the period to bring in relevant primary source material on a per-turn basis in the simulation to narrow in on the relevance. If this is something of interest to you, please don't hesitate to reach out! You can find me at https://twitter.com/the_key_unlocks on Twitter.