What happens to our memory of May 4, 1970 when generative AI starts filling in the archive?
This experimental video essay explores that question by combining original Kent State footage with AI-generated protest imagery and Black Power visual motifs, layered against Crosby, Stills, Nash & Young’s “Four Dead in Ohio” and fragments of late 1960s counterculture sound. Some of this footage is real. Some of it never happened.
This is a hybrid archive. In many ways, it isn’t new. Storytelling has always blurred the line between fact and interpretation. What is new is the speed and realism with which generative tools turn imagination into something that looks like record. The difference now is not that we mix fiction and nonfiction, but that it is becoming harder to tell them apart. Which is why, more than ever, AI literacy matters. Not just technically, but through storytelling. We learn this by doing, by making, by creating and studying the work itself. And we do it transparently, with careful attention to attribution and source. Not by banishing these tools, but by understanding them.
This is not an attempt to fabricate “lost footage.” It is an exploration of how generative tools can reshape our relationship to the visual record, especially around moments of state violence, protest, and youth culture in the USA.
As AI begins to extend and reinterpret historical imagery, the boundary between documentation and imagination becomes less stable. What we see may feel authentic, even when it never existed. Over time, that raises a harder question. How will future viewers distinguish between what was recorded and what was generated?
This piece sits at the intersection of experimental documentary, video essay, and media theory. It is an attempt to probe how memory, technology, and history are starting to blur.
Within the first 12 hours of release, the video reached 900 views, 12 likes, and 3 comments. One comment was removed. Early signals like this are small, but they hint at how viewers are engaging with the format and the questions it raises.
As you watch, consider:
- What feels real, and why?
- Where do you draw the line between documentation and speculation?
- How might synthetic images reshape collective memory over time?
And maybe the most important question:
If it looks real and feels real, does it become real in memory?
Let me know what you think. Does this kind of synthetic archive deepen your understanding of history, or make it harder to trust what you see?
Production Notes
Format: Vertical video (designed for YouTube Shorts and social media viewing)
First release in the Hybrid Archive series
Archival footage sourced via YouTube (ClipGrab)
Archival footage + AI video: Runway: Seedance 2.0, Kling 3.0, Nano Banana 2
Edit: Canva
First release in the Hybrid Archive series
A final note. A friend of mine and former colleague was a freshman at Kent State when this happened. He had been instructed to stay in his dorm room, which he did. He did not see the events unfold, but he heard the gunshots.
Interesting, and a necessary exercise/line of inquiry for building media literacy. However, as we say in New Media, there is no such thing as new media. All media build upon past media, whether in linear or non-linear progression. Media editors have always fabricated “truths” and “fictions.” It is well established that there is no such thing as “objectivity” in media production. Even how to frame a single shot includes editorial choices, expresses voice. (“All poets are liars,” as Plato noted forever ago.) As you point out, Gen AI just makes weaving the obfuscations faster. In the last chapter of media tech history, non-linear editing on computers made the process faster than hand-splicing physical tape. –all thoroughly covered territory in media theory and practice.
Therefore, this raises much more interesting question for me than addressed above. 1) For starters, can the use of Gen AI melded with archives artistically express ideas/interpretations about the nature of Memory? –because our brains, too, fill in gaps and re-write, re-wire, when we reflect upon the past, and memory is so subjective. It’s always a kick to recall events with my mom and my sister; my sister and I will remember family moments from the 70s and 80s similarly, and my mom will remember them so differently…even though we were all in the same place at the same time. Public history works similarly.
2) How might memory, consciousness, storytelling, and AI dance in a posthuman (not to be confused with posthumanist) future? When does human-guided Gen AI evolve into emergent storytelling, whereby the stories learn from themselves, take on a life of their own, even birth and terminate themselves? It is already happening with social media bots that share their own online social media community! That starts to sound like sentience, but it’s simulated sentience. So what, then is real sentience? It’s a good time to ground back into the written archives and re-read Alan Turing’s own thoughts on “Can Machines Think?” from his 1950 essay, “Computing Machinery and Intelligence”: https://courses.cs.umbc.edu/471/papers/turing.pdf. Maybe humans will return to telling stories around campfires IRL community, and bots will do all the digital media.
3) Issues of IP and copywrite burn in my mind as I watch this clip. Friends who are professional documentary filmmakers pay hefty sums per SECOND for archival footage. So when Gen AI starts scraping the web for such footage and uses it for free, is that footage public domain? If not, is using it rebellion (“let the information be free”) or theft, and under what circumstances is it either? Meaning, I would lean towards “rebellion” if the footage was from big corporate media conglomerates, and if the AI companies were not making money from steeling the IP (while We the People pay their bills for the infrastructure that makes the Gen AI run). But the AI companies ARE profitting off of other people’s ideas and labor–including ours when we use and train the tools–with no kick-back to the laborers. So therefore, I say: theft. And theft at whose expense? ABCs, impoverished indie filmmakers, or struggling, underfunded archives?
4) How do we justify the significant environmental impact of using Gen AI for videos? (Ben and I have been round and round about this.) You can look up how much energy it takes to make just 6-seconds of AI video. Are these experiments worth the tradeoff of building nuclear reactors to power them, or should we just keep melting ice caps, so to speak, to make them? Should we pause until we figure out how to safely and sustainably power this beast? Or should we limit use of Gen AI video to circumstances in which it can potentially SAVE carbon expenditure? –as examples, when the alternative is flying film crews to distant locales, or when the AI negates the need to render 3D animations from scratch? (You can look up how much energy it took for Pixar to render, ironically, “Wall-E.” Does AI use less energy than render farms? Has anyone done comparative studies yet?) If we do not answer the energy and carbon questions NOW, there will be no future archives.
We are the ones to create the next pages of media tech history. What legacy do we want to leave? 🙂
PS Another point about Gen AI and memory — I am interested in how AI can help us document the memories of things that are no longer there to physically document. For example, in 2023 I started working on an animatic (there was no AI video yet) about an old bridge across the Monongahela River that was emotionally important to me as a small child because it connected my grandmothers’ houses. The City of Pittsburgh eventually demolished the bridge, and I was devastated, like a friend had been murdered. I wanted to tell a story about this, but how do you document something that is no longer VISIBLY there? –like the bridge, but also things like the Algonquin spirit of the land? Ah! AI and the vast archive that is the www! But my results at that time were unsatisfying, and the piece already looked dated after a couple of months because the tech was changing so fast. Maybe I’ll eventually try again as the tech stabilizes! 🙂 And please forgive typos– I didn’t use AI to write these posts, ha ha.