Personnaly I didn't felt as if I was trying to recognize a place and period in history, but trying to guess what prompts were used to generate the pictures. Or at least for some of the pictures where I wasn't as sure of the event (like seeing the rose on a picture for the war of the roses).
Also I didn't listen to many of the sounds, but I got English voices for something happening in France (the Fauvisme guess).
But still I had some fun and it's nice to see a good use for AI
Yeah, it's probably a good strategy to ignore the (unfortunately mostly incorrect) details and rather try to get a general feeling of what the videos are trying to tell you. For example the "shipyard" page - I was first completely puzzled by the very American-looking workers, but then I thought about what important historic event happened in a shipyard, and together with the red-and-white flags (although the most prominent one seems to be Austrian, which is misleading) I arrived at the correct answer...
However, I also have a "complaint": the "balloon" page (trying to avoid spoiling it) has three videos in a big city and one in the countryside, yet the correct location is the countryside location, not the city (although the city is even mentioned by name in one of the prompts!). So a little more care here is probably warranted...
Aaaand the "pope" page has (according to the prompts) three scenes set at the Vatican, but the location seems to be somewhere else in Rome :)
> The videos aren’t always historically accurate to the last detail
Are they ever?
> They might incorporate elements of folklore or have details from popular beliefs about the way things looked rather than the latest academic research on how they looked
>Still more accurate most of the time than a lot of historical video games at least.
This game is much closer to Trivial Pursuit than it is Assassin's Creed. The importance of accuracy depends on the type of game and when the point of the game is specifically testing the player's knowledge, a lack of accuracy is game-breaking.
And where the creators are on the spectrum between historical accuracy vs politics vs target audience; Asscreed is one that tries to balance it, sometimes it works, their most recent example has had major criticisms. Kingdom Come focuses on historical accuracy but since they found no records of e.g. Black people in medieval Bohemia they didn't include them in the first game, which did trigger some criticism - the game director being outspoken on the issue probably didn't help.
The most recent example has had "major criticisms" because it centers a historical figure who happens to be black. (There was almost zero bellyaching about accuracy when the same figure showed up as a boss/side character in more fantastical takes on medieval Japan, including one in which he sics a ghost Atlas Bear on the PC.) There is a kernal of virtue wrt the issue of representation and appropriation, but most of the raging is driven by racism.
I do want to lend support to the idea that he series tries to balance accuracy with its gameplay/narrative foci, though. IIUC, they get a lot of details that Hollywood movies and even documentaries get wrong (by virtue of digital production). Origins and Odyssey included modes that allowed player to move through the world as if it were a living museum, reading passages about people and places as they were encountered.
Overall, it's nice when artists dealing with historical subjects understand that they're presenting imperfect models of the past, and state so, so that viewers can consider what might be accurate and what might not be.
They did "fix it" on Kingdom Come 2 and personally think they did a good job about how the reaction would be when meeting a dude with dark skin on that specific time and place.
I haven't heard of this, was mainly thinking about how Rome Total War (the original at least) misrepresented most factions and units in it, especially the Egyptians. There wasn't even an enjoyable reason for it.
The inaccuracy was disappointing to me. If the point is historical trivia it's hard when the historical trivia isn't right. I have done some fencing and I noticed it especially for weapons and armor (though that might be just because that's what I know at least a tiny bit about).
Overall it's a fun idea though. I was able to consistently get pretty close in time and location so even with the anachronisms there was enough there.
It's a really fun idea and a terrible example of applying AI to a problem. An average person with an internet connection is going to do a terrible job of getting historical details right, and the only thing AI is doing better here is generating artistic depictions of the mistakes faster than a human could.
This is an example of something that looks like an educational game but has the opposite effect. I had fun doing my round, but I won't do it again, because I think I will learn more wrong things from it than right things.
It's also a bit disappointing how much AI still deviates from what you ask of it. In one case, the prompt is (with spoilers removed):
> This star-lit scene in a [...] garden showcases [...] using a seven-foot reflecting telescope, with speculum metal mirrors, in 18th-century [...]. The [...] row house architecture, oil lantern lighting, and his period attire all pinpoint the late 1700s. The meticulously ground mirror indicates the telescope’s custom design that enabled this revolutionary astronomical finding.
The result is a picture (with some panning animation) of a guy who for some reason has a pistol in his belt, looking through a complicated-looking telescope that is however definitely not a seven-foot mirror telescope in broad daylight with an oil painting inexplicably hanging in mid air behind him. No starlight, row houses or oil lanterns to be seen.
This is awesome. I had the same feeling I had when I first played GeoGuessr. It's one of the first times I've seen what is obviously AI-generated video used in a super compelling way. I want to keep playing.
A few super nitpicky comments:
- I dropped my pin for "Seward's Folly" on Alaska. The videos were clear enough that I knew that's what it was, which made me excited. But then it said it happened in Washington, DC.
- It might be sample bias, but I've only gotten events after year 0 (and technically, it went from 1 BCE/BC to 1 CE/AD.
I'd love to play with this my seven year old, but some of the images are too violent. A "PG mode" would be awesome.
The Seward's Folly had an additional issue besides the fact that some of the locations were in DC and others were in Alaska:
The video of the signing in the White House shows Rutherford B. Hayes, not Andrew Johnson. Andrew Johnson was president in 1867, not Rutherford B. Hayes.
Your location estimate was off because you matched the 3-out-of-4 of videos showing Alaska / Russian Army / Tligits.
My time estimate was off because I matched the only video from the White House ...which was showing Rutherford B. Hayes in office.
The internal struggle of this project is that it's most likely to attract people interested in history, and these are exactly the people who are most likely to spot inconsistencies and dislike the experience.
Having said that, it's a first occurrence when I see AI-generated videos that provide something of a value.
Very polished UI/UX. I'd say this is far closer in similarity to TimeGuessr than GeoGuessr. The only difference is that in TimeGuessr you are guessing a year and a location based on a single real image whereas Time Portal is making heavy use of GenAI for image/videos. Anything I'm missing?
OP: You might also want to change the title in your HTML header for the game - it just says Eggnog which is kinda funny but not sure if that was intentional.
Interesting that the AI makes many of the outdoor structures look ancient rather than how they'd look in the time period. People walking over crumbling ancient roads whole fallen ruins loom over them isn't exactly accurate.
This is cool, but I'm not sure some of the hints are not more red herrings than anything else. Because AI sort of blends things, the prompt needs to be spot on or, for example, India starts looking like any part of the middle east. Traditional China looks like Japan, etc.
Also some of the temporal clues were very good, some were 'wtf'.
I also laughed at some of the hallucination I witnessed. Like a group of people staring in a telescope pointing straight at a white wall.
Fun though, just needs to be honed in a little.
It would help to have markers on the timeline for the different ages, at least for the first round! e.g. Bronze age.
You already sort of do, being a Gregorian timeline and marking 0 AD as Christ's birth. That's a dead giveaway when you see crosses. So I think it would be fair and useful to give a range of eras as markers on the timeline.
The map could also be continental, and the locations more precise than the country.
The map could be more exciting, and change based on the timeline selection! It's currently showing the "current" map and not the map of the era; which in some respect is relevant.
Finally, the scoring could be more explanatory, you got 5,000 / 10,000 for the following reason / calculation method. Maybe a graph of points per time correction and location. It could also be more comprehensive scoring, with a slight multiplier for streaks, a badge for being good at temporal location vs. geolocation etc.
Scoring could animate up, to gamify the experience, create a sort of level end screen that builds up excitement. The map could animate and so could the timeline in this end phase.
I like the idea, there is a lot you could do to push this further.
Thanks for the feedback and the ideas! Is your idea about showing the ages just to make it a bit easier if you don't know exactly when different ages started and ended?
My hope is that one day there is a Rainbolt for Time Portal. For someone like that to exist, the game has to be hard. That said, I agree the scoring could definitely use some improvement!
I've put the part about Pope Gregory (and St Paul Basilica) at the St Paul basilica in Vatican. Was punished by not putting it in Rome (where by "Rome" the game probably meant "whatever the meaning is in the underlying map engine").
The Alaska sale is in DC? One of the videos has the exchange of the flags on the post.
In my experience, our current AIs work best when heavily grounded with real data. Maybe try and work with actual footage, reconstructions, or existing simulations as an input to make the videos more realistic
Love the game but I second improving the scoring mechanics.
I was 40 years off and less than 5km from the place and "only" got 7829. Assuming 99% accuracy for location, and based on some back-of-the-napkin math, that means you have to be within 70.7 years of the actual event to register any points for guessing the correct time. I think If you're within 100 years of the event you should get points. I think ideally it should be a curve, but if you can't program a curve then perhaps create brackets, like -10 points for each year within 10 years, -25 points for each year between 10 and 25 years, and -50 points for each year past that. Using this method you can be +/- 115 years of an event before getting 0 points for the time portion, and the closer you are, the closer to 5000 points you achieve.
Also, the one event was credited as being in Rome, although the picture shows, and the description says, St. Peter's Basilica, which is in Vatican City.
Fair point on the scoring, seems like a lot of people feel that way. Right now, half your points come from distance in km, and half come from distance in years. So you probably got 5000 points for location, and lost points on the year. But it's probably a bit too harsh right now.
Location accuracy probably should be sinusoidal where the score is not really effected if the pointer is within ~10-20km of the event.
For dates, I think it needs to take into account how far back something occurred, with recent history being +/-5 years, early modern being +/- 50 years, and ancient history being +/-500 years. That's closer to the resolution we think of events in (decades, centuries, millennia). You could probably even update the UI to have these graduations.
What about going logarithmic with time?
The more it's in the past the more errors are forgiven.
Explained in another way use the relative time difference (diff/(now-value)) to compute the score and not the absolute time difference
I remember when the first Stable Diffusion models came out, one of their model cards, in the "safety" section, mentioned using the model to generate depictions of historical events. At that time, I thought that warning was about as useful as "do not use to dry pets" on a microwave.
Interesting concept, but the use of AI art is personally extremely off-putting.
Maybe it works for people who like having everything filtered through a modern cinematic cgi filter. In this case, sure, it is a neat tool for seeing how a hollywood studio might have imagined events of the past to look like. At least you admit upfront here that they are "fantastical imaginations" of historical events, but maybe you should clarify that on the website too.
I've always found it better to hear from actual historians, or better yet, dive into the source material when learning about events of the past. This takes some actual work and requires doing good research. It would be nice if AI could help those folks do their jobs more easily instead of being used to generate more fake looking slop.
Two small comments - if I know the precise year it is kinda hard to seek, especially at the ends of the scale. Maybe if you could hold the button to go faster?
And the text overlay on the map at the end mostly prevents me scrolling it (and seeing where the correct place was)
This is a really good game! I thought I did pretty okay, but I was surprised to find that 91% of people did better than I. I'm guessing most people know when and where King Tut's remains were found, I managed to get 4k points on that one and was still in the bottom 10% of players.
This would make for a fun party game in the style of Jackbox.
Nice game!! Well done I think.
And another nice example of how AI and generative art can help learn in an interactive way. Event though some pictures are missleading. I guessed the one was the end of rome while it was istanbul. But the pictures looked nothing like ottoman architecture and only like roman one. But overall very nice idea!!
yeah it's a cool concept, but knowing what I know about the ability of generative AI to accurately replicate specific moments of history, it falls flat.
The whole point of this kind of thing should be to reward people who can recognize "that architectural style wasn't invented until the 13th century" but that's precisely the sort of thing image models cannot do reliably.
I agree that it's not possible to have them do 13th century architectural style perfectly right now. But I believe it will be soon. The image/video models are improving, but so are the reasoning models, and they can check for and fix anachronisms.
I hope you're right. Are you aware of any image-gen models that apply chain-of-thought style reasoning (either agentic or via reinforcment learning to shape outputs?)
These are some incredible monoliths: if they were real, I feel like I would have heard about them? And if they did... that's so cool. But because it's AI generated, I have a very low confidence level that this ever existed at all. Which is sad.
Which is funny, because the monoliths in the AI video look more eroded than the real ones today.
This looked like a nice idea at first glance. At second glance, it's really bad because you have to assume that everything you see in these videos can be wrong or misleading.
No, not aware of image models that do chain-of-thought reasoning. But there are vision models that do it, so you can have them review the generated images and iterate on the prompts.
You might look into era specific LoRas if they exist, and if not consider training a few to help better capture architectural detail from that specific time frame.
This is awesome! Definitely some more obscure historical events in there. Agree that the scoring is a bit harsh, especially since the clips are, let’s say, somewhat impressionistic.
Excellent idea and can’t wait for the next version.
This reminds me of the old "Where in the USA/World is Carmen Sandiego" games...but the accuracy and of the history and kids friendliness would need to improve for me.
The super anachronistic output makes this really difficult. One of the examples was the battle in the war of the roses but all the imagery suggests over a hundred years later.
Yeah fair point. The game still has an issue with details creeping in that are not correct. I believe we can get these types of errors down quite a bit though.
Love the concept. Got annoyed with the scoring. I was off by about 200 years and got the country right and only got 2,995 out of 10,000. Felt sad i got such a low score then looked at the answer and felt proud I thought I was really close and then annoyed at how strict the scoring seemed.
But overall, I love the concept and will probably continue to play and ignore the scoring.
Neat. Feels like a solution in need of a problem though. The hints aren’t really hints, oh I was supposed to see that the rivets on that ship in the background were sovjet?! lol
Also, the "Alaska purchase" has both indoors and outdoor images. The outdoors clearly depicts Alaska but the correct location is supposed to be Washington DC.
Great concept. I'm an avid geoguessr and wikitrivia player, you're definitely onto something here.
I built a prototype version similar to this called PastPort last year, but I like your idea better.
This uses Flux then image to video? Good quality generations, it would be wonderful to see the accuracy of the images improve. I saw you want to make it interactive like moving mode in geoguessr; that would be fantastic. I can imagine a few ways to do both.
I don't believe this is open source - is there a way to contribute to this? One man operation or are you a team?
I enjoyed it :) I see a lot of complaints about the ai generation. My 2c would be the photorealistic style is throwing people off a bit. Painting/artistic renderings might do it better justice
I'm no history buff, so i found it quite fun just as a game.
the system is quite easy to cheese by simply going back and re-guessing once you have the answer, was really enjoying the scoring aspect until I figured out how simple it was to get close to 100%.
Understandable cause its still a PoC and very much a beta, but thought I'd give you the heads up.
Glad you liked it. Yeah, still no score tracking on the web game and it runs on the honor system. If you get the iOS app, you can keep track of your scores and it will just save the score the first time you play.
This is really cool work..It made me think about the original Bill & Ted movie and how you could almost generate an open ended (very pseudo-historical) time travel game now.
I was off by little both in time as in space. But when I was about to drag the map it triggered the go back on my Android phone (gestures). Maybe prevent default to avoid that?
I found the centrality of AI generated video to be quite distasteful. I had a visceral negative reaction to it, which probably speaks to how much AI slop is polluting my life in other places. I would have much preferred a game based on actual historical photographs.
I understand, it's not for everyone. The game will always be based in AI generated renditions though, because it removes the constraints on which events can be depicted.
I could imagine this to become a pastime for curious kids, and parents having nothing against them spending time on it. It still needs development and quality improvements, but that is a direction I could imagine it taking.
Thanks for playing! No immediate plans to paywall the game, but we do eventually want to make money from it in some capacity.
---
Edit: dang suggested we should add more about the link to our startup, so here's more if anyone's interested:
Originally, we were making an AI video creator tool with a focus on character consistency in long videos (https://news.ycombinator.com/item?id=39853474). A year ago, character consistency was a big problem and we developed a solution for it in AI videos. Now though, a lot of other AI video creator tools have come out, and 1) character consistency has been solved in other ways 2) the other tools just make better quality videos than ours.
So we decided to pivot from building video creator tools to building apps with AI video as the core format. When I say that we plan to sell apps like Time Portal, it's still pretty open ended. First, we just want to build an app/apps that people really like using for free and figure out the best way to monetize them later. Time Portal is not for sale right now. It's free to play on the web and there is a free app in the App Store.
Gross. History is not for LLMs to generate. I find the praise in this thread disturbing. The amount of completely anachronistic scenes would probably lead to worse historic understanding, making this an anti learning game.
Thank you! We have plans to expand it! We've been hearing from a few teachers that they like playing Time Portal with their class because it helps the kids empathize with people in the past. There are some really fun possibilities just in the learning space and more in gaming.
TIL the Nika riots took place in the Roman colosseum, and the blues and greens cheered as lone individuals from each deme were sent down for slaughter. Yeah, this is hot garbage in terms of accuracy.
@Samplank2 - this may hurt to hear, but your assertions that better models and pipeline improvements will solve this are pure cope. What you really need to do here is manually curate and tune the prompts, then cherry-pick with a fine eye for detail. There’s no substitute for actual effort and knowledge, but you seem disinterested in that part.
In the shorts, you wake up as some famous person in history: Cleopatra, Caesar ... It's a first person POV of their life and surroundings. They're AI vids.
I first tried dragging the year label -- and the second time as well, for some reason I guess I find that very intuitive, or perhaps the thing we're actually meant to drag doesn't look as much like a slider? Dunno. In case that helps polishing it
I have no idea how to use your app. It just shows 4 pictures and asks me to choose one. No. I refuse to play a challenge that is not explained wtf am i doing.
So there is a similar thing with a photo from (recent) history - and that has the edge of perfect accuracy - a picture of 1920s Alabama is a real representation.
I had real trouble with the battle of towton just now - the armour was “off” and someone was wondering around with a really cool white rose icon on their breastplate - and I could not work out if it was trying to be accurate or imaginative (accurate woukd look more like these things https://en.m.wikipedia.org/wiki/Armorial_of_the_House_of_Pla...)
I mean the fact that there were moving videos of Dutch astronomers or Ethiopian rulers is god damn amazing - it looks luscious
But it also looks … cut-scene. It’s brilliant. But it’s also a work of imagination (LLM imagings).
So it’s quite hard to do the game itself - but it’s amazing to drop people into the context and excite a historical interest.
I really liked it but felt some of the image hints were a bit ambiguous at times which annoyed me.
I had one for the US purchase of Alaska which I got from the images of Americans building log cabins in an icy landscape and another image showing an American signing a document. I assumed it would be either Washington or Alaska (Anchorage I guess), but wasn't sure which because it depends on if you weight the signing of the agreement over the building of US settlements. It could have been either given the images were of different locations.
Similarly I had picture of British dude creating telescopes and realised it was very likely Herschel. But I also knew Herschels early work was done in Bath, while his most famous telescope was built later in Slough. Again, it wasn't entirely clear which location it would have been referring to.
Maybe I'm just being stupid though. I think you could have argued that right answers in both cases were more likely to be Washington and Bath.
That said, I really really liked it and think you have something here. Personally I'd play this over Geoguessr any day and I'll show my GF it tomorrow because I think she'll also like the history aspect of it.
Also, might worth lowering the distance penalty if someone guesses the right country, but the wrong point? Events in large countries are more risky just because of their size. Eg, if an event happened in France but you click Germany you'll often get less of a distance penalty than correctly guessing an event happened in the US but clicking the wrong part of the US.
Thanks for sharing your thoughts and for the kind words! Yeah the situations you pointed out like Washington/Alaska where it's not being consistent in the depiction of a location aren't great and will be improved. I'm kind of torn about what to do on the distance scoring. On the one hand, I see your point that knowing the country should count for something, but it currently doesn't count for much if the country is big and you get the wrong side of the country. On the other hand, doing that would make the scoring system more complicated, and it's already not particularly easy to understand.
I guess you could see it that way. The is no footage from most of history, so AI gives us a new way to interact with those events in the past. But it will never be perfect, because we'll never have the ground truth to compare it to.
I have been building a kind-of geography guessing game in a similar vein. Mine has a solo mode and a party-game mode and doesn't use any AI. I'd love to hear some feedback.
To offer a non-AI alternative but a similar game concept, I highly recommend TimeGuesser: https://timeguessr.com/.
You are shown historical photos (from the past 100 years, even up to the past year) and need to guess the location on a map and the year of the image. Extremely fun and varied gameplay because of the varied events the photos capture (some mundane while others more recognizable).
Timeguessr is neat. The advantage there is that, unlike Time Portal, I don't feel pain and depression by the countless anachronisms made up by AI that people will think bear some semblance to reality (I'm a historian).
YC funded a bunch of AI video companies (4+), and AFAICT the Eggnog folks are hustling the hardest.
The path forward as a foundation video model company closed, so they worked hard on end-to-end story creation workflows and mobile.
Turns out that's hard to gain traction and distribution amongst dozens of other similarly shaped startups. So they hack on games and fun viral loops.
Keep at it! This is super clever. You're getting noticed.
Video is going to be huge, and even though power law dictates there will be only a few winners, I think there's space for teams hustling this hard if you can find distribution.
Let the foundation video model companies fight to the death. They've over-raised and are being commoditized by Tencent and Alibaba's open source foundation video models (Hunyuan and Wan). You can use their APIs on the cheap and still provide value. And value will accrue to the application layer.
Also I didn't listen to many of the sounds, but I got English voices for something happening in France (the Fauvisme guess).
But still I had some fun and it's nice to see a good use for AI
However, I also have a "complaint": the "balloon" page (trying to avoid spoiling it) has three videos in a big city and one in the countryside, yet the correct location is the countryside location, not the city (although the city is even mentioned by name in one of the prompts!). So a little more care here is probably warranted...
Aaaand the "pope" page has (according to the prompts) three scenes set at the Vatican, but the location seems to be somewhere else in Rome :)
Are they ever?
> They might incorporate elements of folklore or have details from popular beliefs about the way things looked rather than the latest academic research on how they looked
Like the one of the age of castles man loading an American civil war cannon by holding another cannon up to it: https://www.eggnog.ai/timeportal/37e02fea-bbb2-4b88-ae8c-0a3...
I must have missed that folklore.
I got a trippy one that was supposed to be about Da Vinci painting the Last Supper, but the people were moving, so I thought it was supposed to be the actual supper: https://www.eggnog.ai/timeportal/56571c14-8f13-48ba-b60f-d82...
This game is much closer to Trivial Pursuit than it is Assassin's Creed. The importance of accuracy depends on the type of game and when the point of the game is specifically testing the player's knowledge, a lack of accuracy is game-breaking.
I do want to lend support to the idea that he series tries to balance accuracy with its gameplay/narrative foci, though. IIUC, they get a lot of details that Hollywood movies and even documentaries get wrong (by virtue of digital production). Origins and Odyssey included modes that allowed player to move through the world as if it were a living museum, reading passages about people and places as they were encountered.
Overall, it's nice when artists dealing with historical subjects understand that they're presenting imperfect models of the past, and state so, so that viewers can consider what might be accurate and what might not be.
https://www.youtube.com/shorts/_OksWkD0VaY
Overall it's a fun idea though. I was able to consistently get pretty close in time and location so even with the anachronisms there was enough there.
This is an example of something that looks like an educational game but has the opposite effect. I had fun doing my round, but I won't do it again, because I think I will learn more wrong things from it than right things.
That said I too was a bit annoyed by how it rendered the byzantine empire. I thought Carthage was meant. So i was over by a thousand years.
> This star-lit scene in a [...] garden showcases [...] using a seven-foot reflecting telescope, with speculum metal mirrors, in 18th-century [...]. The [...] row house architecture, oil lantern lighting, and his period attire all pinpoint the late 1700s. The meticulously ground mirror indicates the telescope’s custom design that enabled this revolutionary astronomical finding.
The result is a picture (with some panning animation) of a guy who for some reason has a pistol in his belt, looking through a complicated-looking telescope that is however definitely not a seven-foot mirror telescope in broad daylight with an oil painting inexplicably hanging in mid air behind him. No starlight, row houses or oil lanterns to be seen.
A few super nitpicky comments:
- I dropped my pin for "Seward's Folly" on Alaska. The videos were clear enough that I knew that's what it was, which made me excited. But then it said it happened in Washington, DC.
- It might be sample bias, but I've only gotten events after year 0 (and technically, it went from 1 BCE/BC to 1 CE/AD.
I'd love to play with this my seven year old, but some of the images are too violent. A "PG mode" would be awesome.
The video of the signing in the White House shows Rutherford B. Hayes, not Andrew Johnson. Andrew Johnson was president in 1867, not Rutherford B. Hayes.
Your location estimate was off because you matched the 3-out-of-4 of videos showing Alaska / Russian Army / Tligits.
My time estimate was off because I matched the only video from the White House ...which was showing Rutherford B. Hayes in office.
Having said that, it's a first occurrence when I see AI-generated videos that provide something of a value.
https://timeguessr.com
OP: You might also want to change the title in your HTML header for the game - it just says Eggnog which is kinda funny but not sure if that was intentional.
Project "Eggnog" FTW!
Also some of the temporal clues were very good, some were 'wtf'.
I also laughed at some of the hallucination I witnessed. Like a group of people staring in a telescope pointing straight at a white wall.
Fun though, just needs to be honed in a little.
It would help to have markers on the timeline for the different ages, at least for the first round! e.g. Bronze age.
You already sort of do, being a Gregorian timeline and marking 0 AD as Christ's birth. That's a dead giveaway when you see crosses. So I think it would be fair and useful to give a range of eras as markers on the timeline.
The map could also be continental, and the locations more precise than the country.
The map could be more exciting, and change based on the timeline selection! It's currently showing the "current" map and not the map of the era; which in some respect is relevant.
Finally, the scoring could be more explanatory, you got 5,000 / 10,000 for the following reason / calculation method. Maybe a graph of points per time correction and location. It could also be more comprehensive scoring, with a slight multiplier for streaks, a badge for being good at temporal location vs. geolocation etc.
Scoring could animate up, to gamify the experience, create a sort of level end screen that builds up excitement. The map could animate and so could the timeline in this end phase.
I like the idea, there is a lot you could do to push this further.
It also dresses up the timeline so that the game gets its own identity.
The Alaska sale is in DC? One of the videos has the exchange of the flags on the post.
https://wikitrivia.tomjwatson.com/
I was only off by 600 years.
I still enjoyed it, however.
I was 40 years off and less than 5km from the place and "only" got 7829. Assuming 99% accuracy for location, and based on some back-of-the-napkin math, that means you have to be within 70.7 years of the actual event to register any points for guessing the correct time. I think If you're within 100 years of the event you should get points. I think ideally it should be a curve, but if you can't program a curve then perhaps create brackets, like -10 points for each year within 10 years, -25 points for each year between 10 and 25 years, and -50 points for each year past that. Using this method you can be +/- 115 years of an event before getting 0 points for the time portion, and the closer you are, the closer to 5000 points you achieve.
Also, the one event was credited as being in Rome, although the picture shows, and the description says, St. Peter's Basilica, which is in Vatican City.
Fair point on the scoring, seems like a lot of people feel that way. Right now, half your points come from distance in km, and half come from distance in years. So you probably got 5000 points for location, and lost points on the year. But it's probably a bit too harsh right now.
And thanks for pointing out the Vatican City nit.
For dates, I think it needs to take into account how far back something occurred, with recent history being +/-5 years, early modern being +/- 50 years, and ancient history being +/-500 years. That's closer to the resolution we think of events in (decades, centuries, millennia). You could probably even update the UI to have these graduations.
Maybe it works for people who like having everything filtered through a modern cinematic cgi filter. In this case, sure, it is a neat tool for seeing how a hollywood studio might have imagined events of the past to look like. At least you admit upfront here that they are "fantastical imaginations" of historical events, but maybe you should clarify that on the website too.
I've always found it better to hear from actual historians, or better yet, dive into the source material when learning about events of the past. This takes some actual work and requires doing good research. It would be nice if AI could help those folks do their jobs more easily instead of being used to generate more fake looking slop.
Two small comments - if I know the precise year it is kinda hard to seek, especially at the ends of the scale. Maybe if you could hold the button to go faster?
And the text overlay on the map at the end mostly prevents me scrolling it (and seeing where the correct place was)
why don't you drag to get close enough and then use the buttons?
This would make for a fun party game in the style of Jackbox.
Constantinople wasn't captured by the Ottomans until almost 1,000 years after the events depicted in the quiz
The whole point of this kind of thing should be to reward people who can recognize "that architectural style wasn't invented until the 13th century" but that's precisely the sort of thing image models cannot do reliably.
For example, consider this imagery from today's challenge: https://firebasestorage.googleapis.com/v0/b/fastab-f08e9.app...
These are some incredible monoliths: if they were real, I feel like I would have heard about them? And if they did... that's so cool. But because it's AI generated, I have a very low confidence level that this ever existed at all. Which is sad.
Which is funny, because the monoliths in the AI video look more eroded than the real ones today.
This looked like a nice idea at first glance. At second glance, it's really bad because you have to assume that everything you see in these videos can be wrong or misleading.
This is entirely possible, as the incredible accuracy[1] of non-generative picture location models (a very similar problem) shows.
[1] https://paperswithcode.com/sota/image-based-localization-on-...
Excellent idea and can’t wait for the next version.
I really enjoy time guessr! Playing it on the TV with family is fun too.
I for the chinese question, I think it was way off. It showed the great wall of china, which is the wrong place for the answer.
The rise of the mugals was also interesting, I got it right but only because I assumed it was confusing Ottoman architecture with mugal.
I guessed it was supposed to be Agincourt because of the prominence of archers.
But overall, I love the concept and will probably continue to play and ignore the scoring.
I built a prototype version similar to this called PastPort last year, but I like your idea better.
This uses Flux then image to video? Good quality generations, it would be wonderful to see the accuracy of the images improve. I saw you want to make it interactive like moving mode in geoguessr; that would be fantastic. I can imagine a few ways to do both.
I don't believe this is open source - is there a way to contribute to this? One man operation or are you a team?
This isn't open source, no. We're a team of two through our company Eggnog AI. That said, happy to talk some time if you're interested!
Boy is that overselling it. And you don't really need to, this is cool even though there's a ton of AI jank.
I think this might work better if you fed the LLM some real image and asked it to expand it than by using prompts.
On the Guess page it just has a blank screen with the 4 cinematic clips below...
---
Edit: dang suggested we should add more about the link to our startup, so here's more if anyone's interested:
Originally, we were making an AI video creator tool with a focus on character consistency in long videos (https://news.ycombinator.com/item?id=39853474). A year ago, character consistency was a big problem and we developed a solution for it in AI videos. Now though, a lot of other AI video creator tools have come out, and 1) character consistency has been solved in other ways 2) the other tools just make better quality videos than ours.
So we decided to pivot from building video creator tools to building apps with AI video as the core format. When I say that we plan to sell apps like Time Portal, it's still pretty open ended. First, we just want to build an app/apps that people really like using for free and figure out the best way to monetize them later. Time Portal is not for sale right now. It's free to play on the web and there is a free app in the App Store.
The scoring could be improved.
And I’d love to see the idea expanded further. “AI recreations of historical scenes” is an idea with tons of interesting potential.
It looks nothing like the Aztec Pyramid of Teotihuacan, which is flat on top and has no structure.
In other words, this is AI slop that makes something that looks plausible, and is utterly misleading.
As someone who has spent decades of my life on history, this makes me weep for humanity.
@Samplank2 - this may hurt to hear, but your assertions that better models and pipeline improvements will solve this are pure cope. What you really need to do here is manually curate and tune the prompts, then cherry-pick with a fine eye for detail. There’s no substitute for actual effort and knowledge, but you seem disinterested in that part.
One nit is recent events (1980+) will fall into an uncanny valley.
Seems to be tied to the videos playing — when they start, the button disappears. I’m seeing it on iOS as well.
1. The AI imagery is often misaligned with the actual answer, with some anachronistic elements.
2. The scoring seems harsh. I got a couple of answers within 50km and/or 10 years in the time scale but was still severely penalized.
Good luck with this, I will definitely watch your progress and pass it along
I had real trouble with the battle of towton just now - the armour was “off” and someone was wondering around with a really cool white rose icon on their breastplate - and I could not work out if it was trying to be accurate or imaginative (accurate woukd look more like these things https://en.m.wikipedia.org/wiki/Armorial_of_the_House_of_Pla...)
I mean the fact that there were moving videos of Dutch astronomers or Ethiopian rulers is god damn amazing - it looks luscious
But it also looks … cut-scene. It’s brilliant. But it’s also a work of imagination (LLM imagings).
So it’s quite hard to do the game itself - but it’s amazing to drop people into the context and excite a historical interest.
I had one for the US purchase of Alaska which I got from the images of Americans building log cabins in an icy landscape and another image showing an American signing a document. I assumed it would be either Washington or Alaska (Anchorage I guess), but wasn't sure which because it depends on if you weight the signing of the agreement over the building of US settlements. It could have been either given the images were of different locations.
Similarly I had picture of British dude creating telescopes and realised it was very likely Herschel. But I also knew Herschels early work was done in Bath, while his most famous telescope was built later in Slough. Again, it wasn't entirely clear which location it would have been referring to.
Maybe I'm just being stupid though. I think you could have argued that right answers in both cases were more likely to be Washington and Bath.
That said, I really really liked it and think you have something here. Personally I'd play this over Geoguessr any day and I'll show my GF it tomorrow because I think she'll also like the history aspect of it.
Also, might worth lowering the distance penalty if someone guesses the right country, but the wrong point? Events in large countries are more risky just because of their size. Eg, if an event happened in France but you click Germany you'll often get less of a distance penalty than correctly guessing an event happened in the US but clicking the wrong part of the US.
The thing that makes Geoguessr cool is that it drops you into a real place.
This is like if Geoguessr showed you the output from "Midjourney, show me China".
https://guesshole.com/
You are shown historical photos (from the past 100 years, even up to the past year) and need to guess the location on a map and the year of the image. Extremely fun and varied gameplay because of the varied events the photos capture (some mundane while others more recognizable).
It would’ve been cool to collect actual images from history. I’m sure there are 1000s of public domain images that could be used.
They literally can’t. There’s no photographs…
What’s the point? You’re just guessing at the prompt used to generate the photo.
That might be more interesting, actually. AI photo game where you need to guess the prompt.
The path forward as a foundation video model company closed, so they worked hard on end-to-end story creation workflows and mobile.
Turns out that's hard to gain traction and distribution amongst dozens of other similarly shaped startups. So they hack on games and fun viral loops.
Keep at it! This is super clever. You're getting noticed.
Video is going to be huge, and even though power law dictates there will be only a few winners, I think there's space for teams hustling this hard if you can find distribution.
Let the foundation video model companies fight to the death. They've over-raised and are being commoditized by Tencent and Alibaba's open source foundation video models (Hunyuan and Wan). You can use their APIs on the cheap and still provide value. And value will accrue to the application layer.
Focus on what the creators want and need.