It’s week five in the world of AI Maddeness, and the Jets are a franchise history-making 4-0 to start the season. As it just so happens, in that other universe 25 years ago the NY Jets also opened 4-0 only to go 9-7 on the season and miss the playoffs. The real 2000-01 season was a heart breaker, but AI Maddeness is where dreams come true.
Week 5 is the Jets bye week, and it couldn’t come soon enough. There are quite a few things to work through before week 6 starts, what’s more I’ve become a bit obsessed so this break in the action allows me to take a breath. A few things to do:
Style the AI Maddeness, AI Sports Zone, and Gangus Green sites. I’ve been promising this for weeks, but is this the weekend I’ll truly lock-in?
Create a separate official Jets site for team news, injury reports, comprehensive stats, etc. This will be a model for having a site for every team (aspirational I know), but if I come up with a solid template it would be easy enough with WPMS.
Another dream is to see if there’s any way to dig into the guts of Madden 2001 and get some of the stats out in an automated fashion that can be fed directly into OpenAI GPTs. Tom Woodward’s comment makes it that much more fun to explore such a far-fetched ambition.
Play a few games against some other undefeated teams in week 5. In particular, the Jaguars against Steelers and the Bills against the Colts. Both the Steelers and the Colts are undefeated and are upcoming match-ups for the Jets, so it will be good to get an in-game sense of those teams.
Get around to doing a highlight video of a game.
Finally, testing out what it would be like to make an AI-generated podcast reflecting on previous week’s game and getting ready for the next week’s, the bye week may provide the perfect occasion to reflect on the Jets vs Steelers going into week 6.
If nothing else, the to-do list highlights that AI Maddeness can quickly become a pretty significant time sink. I do love it, but I find myself wondering WTF I’m doing after spending hours scraping screenshots for stats 🙂
One thing that might help in this department is the power of GPTs, or pre-trained chats that have all the instructions I’ve been typing and re-typing into chats stored so that when I paste in the screenshots with stats, it knows exactly what to do. Tom Woodward opened me up to this brave new world and it has already paid dividends. I have GPTs for scraping stats, creating specific graphics, writing game previews, etc. Instructions can be fine-tuned over time and with this setup I can actually imagine a world where stats, text, and images might be automated between ChatGPT and the blog. The holy grail would be getting the data directly out of Madden 2001 into OpenAI—avoiding the current manual screenshotting and scraping process. Hope springs eternal in the bava breast.
Monday Night Football featuring Colts vs Jags which should be at the RCA Dome, not Lucas field—although I still love the graphic
In terms of new developments since last week, one of the things I ruminated about in the “Stats and Intangibles” post was how I might be able to have game previews and recaps written about the other 13 games each week that are simulated by Madden 2001. There are no game play specifics, rather just the team and individual stats before and after the each week’s game.* So my idea was screen shot all the stats for each team before the match-up (including their record) and have ChatGPT provide a compelling preview of the coming week’s game. Here are two previews ChatGPT created for the Falcons vs Rams and the Colts vs Jaguars. I have to say, the breakdown of the Colts strengths gives me a lot to think about given they are divisional rivals:
The Colts come in unbeaten at 2–0 after wins over the Chiefs and Raiders. Peyton Manning has started steady, throwing for 379 yards and 2 TDs, and the offense runs through Edgerrin James, who has already piled up 300 rushing yards and 4 TDs at 5.4 yards per carry. Indy’s defense has been sharp, giving up just 31 points across two games, and ball security has also been a strength: just 2 giveaways so far.
It kind of feels like scouting other teams as the Jets prepare for future games. But the real fun part was having ChatGPT hallucinate game highlights. For example, I loved the recap of the nail biter in Atlanta that saw the Rams eek out a win against a tough Falcons team:
A Wild Fourth Quarter
The Rams continued to chip away at the lead early in the fourth with a Jeff Wilkins 32-yard field goal to make it 17–16. But Atlanta’s kicking game was sharp too: Jay Feely drilled a 38-yarder, then added another from 36 yards to stretch the Falcons’ lead to 23–16 with just under two minutes left.
That left Warner with the ball — and the game in his hands. Starting from his own 25, he strung together completions to Torry Holt and Ricky Proehl, methodically moving the Rams across midfield. With the final seconds ticking away and Atlanta dropping deep to protect against the field goal, Warner pump-faked to Holt and found Bruce streaking on a skinny post. Bruce hauled it in at the 10, cut inside a diving defender, and scored the go-ahead touchdown with 3 seconds left on the clock.
It’s like the game happened in some alternate universe wherein ChatGPT helped streamline the imaginary. So, my experiment with using pre and post-game stats each week for simulated games worked. The other piece would be having some AI-engine create GIFs and video clips of the imagined moments for the highlight reels. But for right now I’m pretty happy with the outcome. it underscores that it would be doable to turn AI Maddeness into a full blown league news preview and recap site, rather than just a myopic focus on the Jets. I want to see how much writing previews for all the games adds to the weekly time sink, guessing it’s significant with my current manual methods.
Anyway, things are moving along. After just a few weeks in it’s become readily apparent how folks get sucked into the machine. I’m spending too much time solipsistically writing into a chat box, which can feel really alienating. That said, there are also moments of joy when I’m endlessly entertained by some of the insane results, like this cartoon of Curtis Martin steam rolling the Tampa Bay Buccaneers:
Curtis Martin steam rolling the Tampa Bay Buccaneers defense
While I’m enjoying my AI Maddeness project, I’m also thankful it has a definitive end date just a few months from now. It can quickly consume my week if I’m not careful and the last thing I need right now is another hobby to feed my unbridled mania.
That said, what would really make AI Maddeness amazing is if you could have 31 people (or however many teams there are that year) each take ownership of a team and you have weekly games on Sunday that are played and streamed live. After that, each of the teams manage their own PR and marketing but the AI Maddeness admin (the league commissioner) manages each week’s previews and recaps in an attempt to remain somewhat unbiased while the various teams drive their own media empire based on the season. Each participant gets a site for their team, another for a local news outlet, and a fan site to start. For this setup to work we would’ve had to already figured out pulling in targeted team stats into each of the sites seamlessly, and the recaps and previews could be automated based on those stats and any specific parameters each person in-charge of the franchise wants to customize. It’s something we have time to work up to given Madden doesn’t get online head-to-head play until 2003.
___________________________________
*Turns out I was wrong in that post when i said madden 2001 has an incomplete record of individual player stats on display. All the stats are there for each and every player, I just didn’t do the quick gamepad switches to see them. The have full stats for all players, with everything from leaders in the league, conference, division, and team. It’s all there, so no more excuses, Jimmy.
Many lifetimes ago, when I played Pee Wee football for the Baldwin Bombers, our head coach (Mr. Lamonde) would always talk about the “intangibles” of the game.* A kind of otherworldly sense a player has that you couldn’t really quantify (or even teach). I guess some 10 year olds shine, and some don’t 🙂
Pee Wee Football in action. Photo Credit: Amherst Patriots IMG_0300
I’m still fascinated by this idea, despite being far, far removed from the game—which has changed dramatically in the 40 years since I suited up. I mean the financial stakes alone for some of these elite teenagers today is hard to wrap your head around. Luckily, those problems were never mine when it came to football. The game is dear to me given I played it during the formative years of elementary school, but once I joined the Junior High School team it became apparent I was mediocre at best.
I still enjoyed playing the game a lot, even if it was becoming more and more of a slog with a commitment of 5 or 6 days a week. By my sophomore year in high school I snapped my arm pretty bad skateboarding, and was in a cast for much of the rest of high school. So my paltry football career would end about where it should’ve 🙂
But back to the point at hand, I was not one of those players that found themselves in the right place at the right time to make the play: the oft heralded “big play makers.” But I love the whole idea of this sixth sports sense. As I’m playing Madden 2001 for the AI Maddeness season, part of the limitation is that the game does not preserve certain stats. For example, game-by-game stats don’t exist, which is why I’m manually capturing and scraping all the data for every player on the Jets week-by-week. Additionally, it only shows league leaders in passing, rushing, receiving, defense, etc., by certain parameters, so the top 25 receivers will be those with the most receptions, not necessarily those with the most yards.
It seems to follow that the more receptions a player has, the more yards they have, right? Not always, in the case of Wayne Chrebet, for example, he has 8 receptions for 227 yds and 3 TDs. These numbers are better than many of the league leaders (such as Tampa Bay’s Keyshawn Johnson) when it comes to reception yards, but because his receptions numbers are lower, he’s never featured in that category. This is just one example of how the stats for Madden 2001 paint an often incomplete picture. The possibility to sort by TDs, receptions, overall yards, or even reception percentage is not available, which is understandable given the designers of Madden 2001 were probably not aiming for comprehensive stats—or maybe it was a technical limit? I’m not sure, but I imagine in subsequent years they have developed more comprehensive stats that can be filtered by category—which could bode well for future years of this experiment 🙂
The Buccaneers Season Stats through Week 3
With incomplete player stats I’m beginning to think ChatGPT can actually do what it does best: hallucinate the details of simulated games each week. Because while Madden 2001 has an incomplete picture of player stats, it keeps a pretty comprehensive tally of a team’s season stats: things like total offense, defense, turnovers, third down conversions time of possession, etc. So, my experiment this week will be to get the comprehensive season stats for 2-4 teams that are playing each other prior to week 4’s game, and then compare them to the season stats after the week’s game is simulated. This should give me numbers in the aggregate that I can then ask ChatGPT to compare and then hallucinate something that never happened, albeit guided by the overall stats.
More Team Stats for the Tampa Bay Buccaneers going into week 3
I’m wondering if ChatGPT will be able to intuit the intangibles for certain players and the big plays that make the game magical. I mean, that’s kind of the thing about any sport, right, watching an individual or team move beyond the stats and provide a sense of wonder. That was the magic of the late 90s Yankees. It’s part of the mythos of sports, and even when I play this graphically challenged 2001 video game I find it captures some small sense of that—which I know sounds crazy. Maybe fake can be just as good?
While I would like to take the credit for this post title, it came as a response to an AI-generated image I created celebrating the Jets going 3-0 in an alternative universe set 25 years ago, which lives on AI Maddeness. The image showed Vinny Testaverde delivering a pizza with a “W,” the cheese sticking to the box in the shape of the letter. I thought it was pretty awesome.
It is all in reference to Testaverde getting things done on Sunday and ensuring the Jets were triumphant in what was a defensive struggle. You can read all about it in this AI Maddeness post, with extra special GIFs highlighting all the action. The image is part of a Jets superfan’s ongoing obsession with both Testaverde and Curtis Martin on his website Gangus Green. He used a different image of Testaverde in his week 3 round-up that has the quarterback delivering pizza in the shape of a W sporting a Jets Pizza shirt and a throwback football helmet. He’s something between a Domino’s delivery driver and a 1950s cartoon salesman.
Testaverde delivers with “W” -this time with pepperoni
Charles’ joke plays off the reality that the real Jets have started the 2025-26 season 0-3, in many ways the upside down of mine. Life is about to get uncomfortable in NYC for Jets head coach Aaron Glenn, while in my football universe he continues to make plays in the Jets’ secondary. I was wondering what would happen when I played the AI Maddeness season week-for-week with the real one, and this sense of competing, alternative universes is key. It highlights how easy it is to create and exist within a media world where “black is white and white is black, people.” A space where we become increasingly unmoored from any sense of reality, and in that regard the In the Mouth of Madness reference in my last post about this project takes on more and more relevance.
AI maddeness Week 3 preview graphic
That’s my deep thought for this post, now on to some of the work I’ve been doing to get the endless hours I’m sinking into this “efficiency engine” under control. I’ve started to come up with a weekly rhythm to the posts. By Thursday or Friday I do a preview post before the coming weekend’s game, like this one for the Jets vs. Bills last week. The deeper we get into a season, the more stats there are to work with, which can make these posts fun. The game preview post goes on the AI Maddeness site, which is kind of a stand-in for nfl.com—I’ll talk more about that shortly.
Throw-back feature image for the AI Sports Zone week 3 recap
The recap post happens on AI Sports Zone either Monday or Tuesday. This task takes a lot of time given I need to get all the data from Sunday’s (or Monday’s) game scraped off the screenshots, organized in a CSV file, and then imported into a spreadsheet. One of the things I want to talk to Tom Woodward about today is seeing how I can go directly to the spreadsheet and save a step. This post also has roughly 5-10 GIFs highlighting plays from the game. Also, on top of all the stat-scraping and GIF-making, I spend an hour or so each week writing up a pretty thorough breakdown of the game, done while re-watching the recording.
The other big post of the week is from Gangus Green, and that’s just a fan’s take on the post AI Sports Zone writes, so that’s pretty easy. I spend most of the time for that site trying to get fun images based on something “he” writes, like the “Vinny Delivers” image. Apart from that, I try and add a “Players of the Week” post to AI Maddeness to mix it up a bit. Madden 2001 features the best performances from an offensive and defensive player for that week, so I just scrape that image and have ChatGPT write a post about it. I also have ChatGPT make a featured image. You can see week 3’s “Players of the Week” post to get a sense of this.
Screenshot image Madden 2001 Player of Week feature
ChatGPT’s re-factoring of the screenshot into a featured graphic for the AI Maddeness blog
That’s a rundown of all the different posts I do at the moment on the various sites, and once I have them it’s trivial to have ChatGPT write a social post to announce and link them for Mastodon—which is where I have accounts setup for AI Maddeness and Gangus Green on social.ds106.us. The automatic comments are humming along, and I still have to get around to adding more commenters.
The difference between the AI Sports Zone and AI Maddeness sites is still a bit arbitrary, they could work on the same site for sure, but the idea is that AI Maddeness represents the professional league voice and AI Sports Zone provides a bit more editorial take. It’s hard to see the difference between all of these big sports news outlets when it comes to game recaps or previews. I think having an editorial writer that does more hot takes for AI Sport Zone would be a good development, and providing more good-natured corporate-style posts about how much AI Maddeness gives back to its community would be good for the league site.
GIFs made with ezgif.com are used to highlight the each in each week’s recap
Also, in order to have both of these feel like more full blown sites, I could essentially feed all the scores from the games that were simulated into ChatGPT and have it come up with recaps and previews for each of them. That might be fun, and I have enough generic stats week-over-week where it would be interesting to see what it does. This would also push me to create a fourth site that is a more official Jets site given AI Maddeness and Ai Sport Zone will be much more than just the Jets if I were to feed in everything.
NFL.com’s early 2000s website featuring divisional standings
NFL Stat leaders from the 2001/2002 nfl.com website
I even had ChatGPT put together a team schedule that’s based on a couple of screenshots from the team calendars built into Madden 2001.
Jets schedule built into Madden 2001 that was repurposed with some scraping, CSV and HTML creation
It’s now on Gangus Green’s site, with the excuse that he just started learning HTML for work, so this seemed like a good way to put his labor in service of his real passion.
In terms of other things to do:
I’ve yet to style each site differently, and while I did get Understrap installed, I haven’t got Visual Code, Copilot and a dev WP environment up and running. Something I’m going back to the Woodward Well for
A 60-90 seconds AI Sports Zone video recap of the Jets game is on the to-do list
A NFL Films-style video would also be fun to do here soon
A podcast with either sports pundits or fans
I think the real break-through I made this week is learning how to organize my chats into specific tasks. My chats were all over the place, and I was writing so much into them that it was impossible to find stuff, so now I have chats for “Weekly League Leaders,” “Standings,” “Player Stats,” “Game Summaries,” etc. I even break out each game preview and recap into its own chat, and I’m finding that a bit of logic and order to the chats is making me far more efficient. Pretty basic file management here, frankly.
Jets vs. Bucs week 4 preview image is now the model for all other weeks
The other piece is I’m asking ChatGPT to provide me with a breakdown of the prompts to get me a repeatable graphic, CSV form, or post. For example, I have settled on the idea of having the helmets of opposing teams for the week’s match face each other on the background of a stadium with the AI Maddeness logo. The one for this coming week’s game came out really well, so I asked ChatGPT to breakdown the components so I can save that prompt for coming week’s graphics, and it did. So I now have it and will just drop it in the chat for coming weeks, removing the trial and error with graphics that was so painful.
Create a horizontal promotional graphic (1200×600 px) in the style of Madden 2001. The image should feature:
“AI Maddeness” logo (replace any EA Sports branding).
Two 2000–2001 style NFL helmets, facing each other, centered
The background should be a packed football stadium with sky above.
“Week [X]” text at the bottom in bold, large font.
New York Jets helmet on the left and the [Opponent Team] helmet on the right (update opponent as needed).
Match the style of the “Jets vs Buccaneers – Week 4” graphic you made previously: retro, bold, Madden-2001 inspired. Center the helmets better and make “Week [X]” highly visible.
And I’m starting to do this for all my requests chat-by-chat so that here soon I should at least have a cache of repeatable chats that I can use to quickly get the data in CSV or HTML form, as well as the accompanying images. I mean, a basic logic of organizing your chats that’s simply fashioning requests with predictable outcomes.*
Once I’ve this down for my various tasks, it would be cool to see how seamlessly they can move from request to finished product without the intervention of moving between Google Sheets, the blog, or Mastodon that’s currently happening. How easily can I let the machine know this will be the preview image, here is the game summary, and these will be the 4 or 5 plays I want featured. The GIFs are still manual, I had luck with ChtGPT early, but recently it has been pushing me to EZgif.com. To be fair that site is pretty damn good and easy enough, but it all takes precious time that I was supposed to be saving 🙂
________________________________________________
*In fact, it is all pretty basic to be fair, but that’s probably why it is so damn popular—easy wins in tech again and again.
I’m not sure how I’m gonna get my hands entirely around this post, but damn it all I’m going to try. It’s been a while since I came at the blog with a long one, but if I don’t start documenting some of the AI Maddeness work I’ll be too far in to find my way out 🙂
In the Mouth of Madness GIF
Strange thing is despite the post count this month on the blog, I’m writing a lot. But I’m writing into a text box postmarked to oblivion. I’ve become fascinated with what it might spit out. It’s often strangely wrong and oddly glitchy, but the generic beats it hits and the sense of over-the-topness it deems a personality where there’s none is mesmerizing. It’s all very confounding, I’ll be the first to admit, but I’ve come to the machine on a mission. I’m employing it to take on the personas of stock sports writers, fans, and a strange assortment of characters that populate an imagined universe. It’s become particularly fun, at least for me, but it might be worth taking a step back to explain what the hell I’m talking about.
Madden 2001 Loading Page via the Video Games Museum
Looking for an excuse to explore AI, I decided to play an entire season of the 25 year old video game Madden 2001 and use AI tools to create a universe around a single season of video game football. I imagined it would be very rudimentary to start (which it definitely is) and build over 17 to 20 weeks (20 assumes playoffs and more) to a more fine-tuned content production machine standing in for localized sports media.
Ai Maddeness Logo Created by Tom Woodward using AI. I love it so!
What’s more, thanks to Tom Woodward, we’ve automated the bots that populate the discussion in that universe using an API call to ChatGPT that’s tied to unique character profiles that use those parameters to comment on blog posts (there are no social media bots yet, but I imagine that’s in the future). The average bot leaves 1 to 2 comments a post, but after a few posts I’m realizing we need to add more commentator bot profiles so that we can have fewer repeaters. Tom blogged how he made it happen, and I appreciate as always his practical approach to making all the cool things associated with this project happen—funny how great things materialize when you leave Non-Programmistan.
So, the thrust of the project is playing and recording a game of Madden 2001 each week throughout the season as the NY Jets. This is the real reason why I’m doing this, to be clear. I’m looking for an excuse to play this video game and somehow have it matter. One of the ways I’ve justified this amazing time sink is to simultaneously play with AI given Madden 2001 was that game in the early 2000s that I first saw AI called out as part of the settings interface. It is also the first game I encountered wherein the complex sets of rules and impressive attention to detail helped bring the NFL to life as a videogame.
Aaron Glenn forces a fumble on Kevin Faulk that is recovered by Victor Green
These factors made it feel like a new breed of sports game and it was really appealing to get high and play it for endless hours when it came out. According to legend, John Madden would not put his name on anything that didn’t capture the authenticity of an 11-on-11 game. Tiburon Entertainment met that benchmark during the late 80s and early 90s, and by 1998 they’d been bought and brought into the EA empire. As a result an iconic game franchise was born.
Vinny Testaverde to Laveranues Coles on a clutch 3 and 14 for the 1st down and more
So, as you can imagine, playing this game on the Playstation in 2000 was an experience. As mentioned above, one of the things that struck me was how the menu integrates the ability to customize the AI for the game.
Customize the AI on Madden 2001
In fact, when you enter this menu, you get a sense of how rudimentary those settings are with the Coaching Strategy for the CPU (the machine!) moving between normal, aggressive, or conservative. The Defense Strategy has three options too: normal, blitz, or zone. The slider moves between pass or run.
AI settings for Coaching Strategy in Madden 2001
You can move from coaching to Defense and Offense were you can switch between the CPU and Human (one of the first times I recall this dichotomy in a mass entertainment product):
Customize AI Defense settings in Madden 2001 for the CPU
So you can fine tune the game’s “AI” to create the type of gaming experience you want for not only the CPU, but also the human, which in many ways already assumes a majority of the experience is not dependent on that puny human with the controller in their hands.†
Customize AI Defense settings in Madden 2001 for the human
As my son tells me, it’s not the same AI as ChatGPT, and he goes on to quote some smart Youtuber he’s watched that explains neural networks, LLMs and the like, all very good sense to be sure. That said, it was no practical help for me given I’m trying to pass off this rather frail connection with anything called AI as further justification for the project. Dare I say work? You’ll be glad to know I didn’t let his appeal to reason and finer distinctions stop the AI Maddeness show, I just decided build an AI-based media empire around it as further justification.
Probably the most amazing game for Rodney Harrison that he never played
I spent much of this spring and summer playing Madden 2001 with the idea I’d ramp-up to an entire season this month, just with teams from 25 years ago. It’s kinda wild writing about players from 25 years ago, it’s as if they were still playing and the simple act of re-visiting this season via Madden somehow collapses time.* I also wanted to play the games at roughly the same times as the real 2025 season, so the first week of the 2025 NFL season would also be the first week of AI Maddeness. By doing this I’m hoping to approximate the real time of a season, the build-up, the sense of growing intensity, and the real physical and mental toll it takes on the players of a real team, albeit virtually. What’s more, a huge part of that equation is the media storm surrounding those 17-21 weeks of play. So even if I play the game for less than an hour Sunday or Monday night, I can spent the rest of the week trying to automate the ensuing hype-building media machine.
Gangus Green header image for this AI character’s Mastodon and soon-to-be blog header
The media world I’m creating is somewhat insular in that it’s AI first and foremost. It’s not trying to blog like I blog, it’s trying to comprehend and reproduce a reflection of sports reporting from a scraped web. What the hell does that look like? I mean, that fact is itself somewhat alluring, if not downright seductive—as it was in my sorry case. So after months of training on the game and trying to figure out what this AI Media world might look like, I spent much of the summer vacationing, which was awesome. But, it brought me to the beginning of the season, the first week of September, with a half-finished plan.
Apocalypse Now has nothing on the NFL Military flyover
But who cares, it’s a playful way to learn about AI somewhat outside the polarizing admonitions from either camp about what AI is and isn’t. That said, I know sports are political, I’m playing the season just before 9/11, which provides a crucial inflection point that marks a historical moment were surrendering constitutional rights for the sake of national security was increasingly normalized—in many ways a direct precursor to the sorry state of the union in which we currently find ourselves. So much of sports media has become increasingly empire adjacent, the media closing ranks against Colin Kaepernick, a process led by the NFL, is a good recent example of this. In fact, the. rise of bot and meme culture just further exacerbates these divisions, which makes the political world of sports a media-driven hall of mirrors. It’s hard to situation yourself when you have questionable facts, hot-takes, and editorials coming at you from all angles.
Post-9/11 was also the era when the military flyover of NFL stadiums took on new meanings, as did the omnipresence of the flag. These things were not just sideshows, but became central to a consolidated display of national pride that seemed rooted in the deeper symbolic comparisons constantly made in the sport. The reference to gladiators, dynasties, and endless “wars” campaigns made football the embodiment of a more militaristic form of nationalism. So it makes sense that much of sports media both mimics and helps shape the norms that define this kind of chest-puffing patriotism. What might this AI technology add to an already well-oiled assault on reason that social media has achieved so well in recent years? There’s surely a deeper mouth of Madness beyond AI, but this technology is “trending”so it makes sense to try and understand as much, or little, as I can.
Anyway, I started playing the season early this month and currently heading into week 3 of the season, with the Jets (my team) going 2-0 in a couple of tough games. I recorded the game play and put both games on Youtube. I was originally going to provide commentary on top of John Madden and Pat Summerall, but having tested this in the spring I found I was too busy playing to have anything intelligent to say. I’m older now, so I have to think beyond my guns.
The games come out as a tight 48 minute affair, and so far the recordings have been solid. For week 2 I tried to have the video automatically stream at a pre-determined time, but somehow the time zones got messed up, so I was never streaming. No worries there because I was also recording locally, so I could upload and premiere the game on Youtube after the fact. I’m not sure there’s any need for it to be a live stream, but I still want to figure that out. Apart from that, you’ll notice if you watch the videos that during halftime and the end of the game I go through all the stats provided somewhat meticulously. This is so I can capture the halftime and end of game summaries, the scoring summaries, as well as the various players stats. I collect these via screenshots and put them in a folder that I will then take to ChatGPT.
A screenshot from the game video with half time stats for the defense
After the game I have a whole series of data that I can provide to ChatGPT to come up with an article about that week’s game. Given the stats, it does a good job of conforming to the details of the game. So, at the point of asking ChatGPT to write the article, it has more than enough details to fill in around. Turns out I spend a good amount of time fashioning the request for an article I want. I was a quasi-sports writer in high school with my friend, who actually did all the real work. I liked seeing how quickly he boiled down the game to its basics: names, plays, scores. I have no desire to write like this, and in many ways with outlets like the NY Post, Daily News, and Newsday all continuing to struggle in the world of online media, the sports journalism industry has simultaneously exploded and declined.
6 screenshots from the game that are transformed by ChatGPT into a CSV ready table of data
The best way to get the data out of Madden 2001 is to feed screenshots of the game stats, scoring summaries, and player stats into ChatGPT, which then organizes the image text into quite accurate tables of data that can be exported via CSV. That’s still pretty much magic. Then I’m able to import the data manually into Google Sheets, but it’s clear once I have the sheets set with consistent data I want to collect that this piece can be automated weekly. Also, with the data from the screenshots in readable format, I can ask ChatGPT to write an article. from various voices, as well as create graphics (a struggle), social media posts, and even scripts for a podcast or video highlight reel.
ChatGPT generated scripts for TV/Radio broadcasts
Of all the media ChatGPT creates, I’ve been struggling most with the graphics. I spent a lot of time trying to correct strange repetitive inconsistencies in the image results. This rarely happens with the text, to be honest, but it’s non-stop with the graphics and posters. Despite the struggles, I also find the images oddly impressive. So I fed Chat GPT this screenshot of the final score:
Jets vs Patriots screenshot from Madden 2001
I asked it to create something similar, more specifically I said:
Use the following image to create a graphic in the Madden 2001 style with the icon titled “AI Sports Maddeness 2001.” The graphic should have the score Jets 21 Patriots 16 and have their helmets facing each other on the background of the Jets football stadium
It came up with the following on the first try:
ChatGPT’s realization of the Madden 2001 screenshot i uploaded
I was impressed. I loved the grainy, almost baseball card like aesthetic. Maddeness was spelt “Maddness” so I tried to have that cleaned up, but that’s usually where things get further and further from what you want. Because every new ask leads to an entirely new image with often increasingly bizarre mistakes and omissions, I returned to the chat with the following ask:
This good, but “Maddness” should be “Maddeness” and can we make the graphic’s orientation landscape. Also, you have to put Jets under the 21 and Patriots under the 16
And I got the following image, which was damn near perfect, save the fact that there was no score for the Patriots and AI Sports reverts back to EA Sports:
Second on the image getting closer, but still a major omission with no score for Patriots and EA Sports instead of AI Sports
And so it goes with graphics, it’s almost better to start fresh with the graphic you want, as I do for the Gangus Green fan art stuff, than feed a graphic that is meant to take the data off a specific screenshot—at least that’s my experience. Nonetheless, after multiple attempts that led me further and further from what I wanted, I settled on the above image and just photoshopped in the 16 after Patriots.
As for the text articles, they usually come out spot on, but after a couple of weeks they’re already feeling formulaic. I’ve been posting posting on AI Maddeness, AI Sports Zone, and Gangus Green, and if you read them you can already get a sense of uniformity across the postings. I wonder how folks mix that up more? Is the idea you can get it to sound general enough with a unique voice? I mean re-caps of sports events usually sound route, but this is somehow different, it’s like routine with a fake persona. Would love to get any advice here.
I wrote week two’s game recap, spending time outside the machine. When copying it into ChatGPT it proceeded to strip out a fair amount of details to be tighter and more organized. Mine might have been better in my heart, but it also might have been long-winded and boring–I’ve been known. But if what I’m trying to do is give each journalist/media outlet a voice, I’m struggling with how to make a voice (or voices) from the machine that sound more compelling than a bad novel?
In fact, the comments on the posts are a lot of fun at first, Tom made-up some awesome stock football fans that show and respond to the post, but they quickly become identifiable as bots. One solution is just more commentators, or better yet a more nuanced prompt? I don’t know, my head hurts.
Beyond the sites AI Maddeness and AI Sports Zone, I created a sports fan that I basically told ChatGPT was a huge Jets fan, they think Curtis Martin is god, and continually breaks QB Vinny Testaverde’s chops. The fun thing to see is where this leads, but soon enough it becomes repetitive, how do we make our fake fans more convincing? A.I. Jock, the author for AI Zone and AI Maddeness, is something of a mesh between organizational marketing and sports writing. They kind of get away with their pieces, even if they are repetitive, because that is almost what is expected, whereas a fan’s personality is actually harder to nail.
AI created image of Jets fan blogger Gangus Green
The cool piece is I can define these character’s personas right in WordPress, which will control their writing style. Again, almost like a series of characters in a strange fake blogroll. I’ve been laughing hysterically at the comments from the NFL conspiracy theorist and the overly pedantic fan. I am going to have to do some more character studies if this project is going to have anything resembling a soul. 🙂
Conspiracy Theorist Jet Fan that Tom helped define the persona of, all this happening right in WP dashboard
The other piece is my sites are all just stock WordPress themes at the moment. I’ve never programmed a theme, but I’m going to use CoPilot to guide me through the process on top of the base theme Understrap. That’s this weekend’s project, and I hope to have some early 2000s web pages up sometime soon, maybe even in time for the Jets showdown with division rival the Buffalo Bills. They’re home, and they have momentum on their side!
AL Maddeness Week 3: Jets vs Bills
So far the most frustrating thing has been creating supporting graphics and other charts and tables based on the data collected. I’ve spent way too much time on these, and I may need to diversify to other AI image solutions like Dall E or Midjourney, but that’s how they suck you in. Soon I’ll have a new tool for every media element, it’s already the case with ElevenLabs for AI Audio voiceover. I had fun with the NFl Films style voiceover while figuring things out this spring, but I’ve not gotten around to that level of media entertainment just yet.
The easiest images to create thus far have been the fan posters for Gangus Green’s blog. They usually consist of one set of descriptions and done. For example, after ChatGPT takes my game description and various stats and turns it into a weekly recap by AI Jock, it can then be re-written from a rabid fan’s perspective, which is the Gangus Green blog. After that’s done, I simply ask for some fan art, like so:
This works, now I am wondering if you have any ideas for some fan art from Gangus Green based on this post
From which I got the following:
I had a field day with these.
For no. 1 it created the following image, which is interesting cause I don’t know what “DOWN” means in this context: “Martin Keeps Moving the Chains Down?” I mean Down Field Makes sense, but just down loses the narrative a bit. But still, an awesome image for my purposes.
“Martin Keeps Moving the Chains Down”
Also, no. 2 is fun because it takes a direct quote from the article, and seems to love this idea of Testaverde throwing wiffle balls throughout the game given he put up some rough numbers. The image is awesome, but I also love the “Houstcon” —so close and so far all at once. There is also this strange sense that ChatGPT “knows” when it has good lines, which is bizarre to me
“Houstcon We Have a Wiffle Ball”
Another awesome one is no. 3, this image depicts the defensive backs as ball hawks given they had a solid second quarter keeping Bledsoe under wraps. The weird thing is the supposed jersey numbers are inconsistent, at times wrong, and often repeated. Not to mention the hawks are downright scary. You almost had it, ChattyG!
“Ballhawks in Fligh”
Finally, the bonus idea ChatGPT threw at me was a trading card for Curtis Martin’s epic game. I took it up on the offer and this one came out quite well. One shot and done:
Curtis Martin: AFC Beast of the East trading card
Worth noting that ChatGPT’s top 3 image recommendations were also mine. Spooky.
When it comes to more complex, data-driven graphics with summaries, ChatGPT gets regularly confused, repeating the same lines, make the graphic text run off the edges, jumbling table formatting, and so on. Below are a few examples of some of the weirder ones.
For week 1’s Players of the Week it kept on insisting on putting Michael Westbrook’s face twice
Still with Westbrook’s image twice, but now with an undecipherable chart, who did what?
Close to perfect for Martin’s graphic, but the penchant for repeating yards and touchdowns is strong, not to mention the poor formatting
It could have been a contender! But the edges are cut off!
Another contender, but that extra 1760 yards will never cut it!
The other piece I’m trying to have feed into the AI Maddeness and AI Sports Zone sites are updated reports like player stats, divisional standings, the schedule, and more. I think these will be easy once I have the workflow for moving OCR’d into ChatGPT that then are pulled directly into an updating Google Sheet that’s hooked into a specific page in WordPress. I’m sure there’s more I can do with the stats, and as I learned from my early tests and experiments during the sping and summer, the cumulative stats are important for play-off predictions, wild-card berths, and more. I found getting them post facto from week 17 backwards all at once a pretty daunting task. I did it, but the OCR data was not nearly as consistent so that much of it was manual work.
Divisional standings for AI Maddeness 2001 after week 1
This brings me to a final point. I’m certain this hasn’t saved me any time—on the contrary. The time I spend manually creating GIFs, getting the stats in order, and trying to get the graphics to comply is a total black hole. But the comments on the site and the quick creation of blog posts and social media posts does give the illusion of time savings. That said, the lead up work is a lot. It’s like prepping to paint: the wall-prep, taping, tarps, and cleaning takes much longer than the 30 minutes of painting, Prepping is everything and it makes me wonder how folks out there manage and organize the various chats they use to take care of repetitive tasks like getting text off the image and putting them in CSV tables. At this point it’s almost automatic with the Madden 2001 images no matter what chat I’m in. It seems that the system in general has been training on what I’m asking it across chats, which is interesting.
AI “Maddenness” Week 3: Jets vs. Bills Week 3
Anyway, that’s where I’m at with AI Maddeness thus far, I would write more, but I have a game against Buffalo this Sunday that I’ll have to both market and practice for 🙂
_____________________________________________
*I imagine Curtis Martin or Vinny Testaverde searching their names and finding a post about stats for a game they never played.
†For Madden this is definitely the case given you can only control 1 out of 11 players on your team at any given time—so “AI” is controlling the other 21 players on the field
As part of this year’s Reclaim Open Conference we were hoping to highlight student work coming out of any assorted Reclaim Hosting projects. So, if you’re working with students in a Domain of One’s Own, Shared Hosting or a WordPress Multisite, we want to hear from you!
We’re running a showcase that aims to highlight emerging voices from across our community of institutions. We”re hoping this will provide an opportunity to celebrate the work students do on the web. Keep in mind this can be either existing or new work, including work from previous academic years.
If you ave any projects you would like to submit, just use the entry form on the Reclaim Open site, and help us celebrate the work that keeps the web weird 🙂
Time to promote the best conference this side of the … well it’s fully online and distributed so that geographical metaphor would crash and burn in the Mississippi. In fact, this is a region-free conference, just like all media should be. [I knew I’d find my conceit eventually 🙂 ]
Re-wilding the Network, Making New Connections
From November 4 through the 6th Reclaim Hosting will be putting on its 5th bi-annual conference, which makes for 10 years of Reclaim conferencing if you’re following the math. The theme this time around is “Rewilding the Network,” inviting folks to think about how we imagine a web beyond the mega-platforms that have sucked much of the fun out of our online networks. We’ve already gotten some really awesome submissions, and with less than two weeks to get your submission in, I’m hoping some of you brave souls that still read the bava might submit and join us for what promises to be three days of old school fun.
Hell, I even read a blog post suggesting that the great Todd Conaway might submit a session about his adventures in the ever-becoming world of VR. It might even prove true that he plays mini-golf in virtual space with Gardner Campbell on the regular!
Anyway, I’m not just the President of Reclaim Hosting, I am also a client. So I’m looking forward to a few sessions of my own. In fact, Andy Rush already submitted his talk on thinking through what a federated media empire might look like, and our shared interest in PeerTube was enough for him to let me ride is presentation coattails.
I’m also planning on presenting with Michael Branson Smith about how our Family Pictures Podcast has emerged over the last nine months to be a weekly lovefest. This will be a live podcast session that will not only dig into the technical bits of how we manage the labor of a podcast, but also wax poetic about how the process is everything. More than the likes and subscribes, doing this ongoing project has been about building a real, authentic conversation around and with the things we love, i.e. movies. It’s all about the personal relationships, which is probably a good way to promote Reclaim Open.
Ai Maddeness Logo Created by Tom Woodward using AI. I love it so!
Finally, I’m hoping Tom Woodward will join me for a session to explore the AI Maddeness project, which will be getting off the ground this coming weekend. This is something I’ve been slowly building off the side of my desk with Tom, and the short story is it’s an attempt to build an AI-driven sports media empire around a season of Madden 2001. I understand there’s a lot to unpack in that statement, but suffice to say I’ve become obsessed with the idea of resurrecting a 25 year old video game to explore AI. What’s more, Tom is absolutely the guy you want on-board when you are trying to realize a non-sensical and arguably absurd idea. No one groks the absurd and meaningless as deeply as Tom, and that is why he is so damn awesome.
While in Portland, Oregon last week doing some serious DVD, VHS, comic, and vinyl shopping (what a city for physical media!), I came across The Incredible Hulk #315 from January of 1986. The title “Bruce Banner … Free at last?” references the theme of this series wherein Doc Samson is trying to free Banner from his volatile alter ego.
I came across the actual comic for a GIF I made for ds106 nearly 15 years ago
The reason why I’m even posting about this discovery is it returns me to that wonderful web vision that was ds106. I actually took more time than I care to admit (and recruited several folks in the process) to create an animated version of this cover for one of many awesome assignments.
Anyway, I hope this helps explain why I had to buy the comic so I had an excuse to return to the blog 13+ years later as a reminder that making silly things is a reward that keeps on giving.
I’ve been recovering from a pretty intense regiment of vacation over the last month, but I’m finally back at home playing Madden 2001 in preparation for the AI Maddeness season kickoff this coming weekend.
This morning I decided to play the penultimate exhibition game from the 2001 season featuring the Jets vs. the Giants in the battle for New York. Deep into the first quarter the Jets struck first when wide receiver Dedric Ward returned a punt 72-yards for a touchdown. It was pretty wild. You can see the return in all its jukey awesomeness in the video embedded below.
Now I mention this because I’ve been playing Madden 2001 regularly for 6-8 months now, and this was my first punt return for a TD during that span. That might be because I suck, but it might also mean it’s hard to do. So, you can imagine my exhilaration when deep in the 4th quarter with the game knotted at 21, the Giants were forced to punt with just 41 seconds left in the game. The crowd was booing the call (though there was no real alternative) which gave Dedric Ward’s second punt return for 62-yards and a TD that much more of a punch. Like the first, it started up the middle and then broke out to the right sideline. A finish with authority! Even a 25 year-old game has its moments.
Two punt returns, two TDs and each of them for 60+ yards. While Madden ultimately gave Jets cornerback Marcus Coleman “Player of the Game” honors for his 3 interceptions, there’s no question in my mind the real king of NY today was Dedric Ward. Game winner on a punt return? How often does that happen?
Who knows, maybe the Giants just have particularly terrible special teams, but I’m beginning to believe the Jets are ready for the 2000-2001 AI Maddeness season—-this could finally be the year when no one can stop the creeping Gang Green.
A few months back I learned that you canemulate handheld video games from the early 80s on systems like Retropie or Batocera. That seemed pretty crazy to me. I had luck getting it working on the Batocera, so I started trying to play handheld games from the 80s like Electronic Quarterback, Coleco’s tabletop Galaxian, Donkey Kong, and Zaxxon, Nintendo’s Game & WatchDonkey Kong and many, many more. TO be honest, getting them to work was hit or miss at best.
Nintendo’s Game & Watch Donkey Kong handheld game
As a result of this discovery I remembered one of my favorite handheld games from this era: Bandai’s Packri Monster. Packri Monster is a port of Pac-man for handhelds that along with Entex’s Space Invaders and Coleco’s Head to Head Football were the holy trinity of my handheld period. I found the game files for Packri Monster and tried to emulate it but it was terrible, unrecognizable really. But all was not lost because not being able to emulate the game prompted me to acquire an actual Packri Monster on Ebay for $30, and I once again own the holy trinity 🙂
Bandai’s Packri Monster image from Handheld Museum, which rules.
Trying to play Packri Monster on the plane back to Italy from New York reminded me of the simplicity of these early handhelds. One game, simplified pixels, no volume control, maybe a start button, and no headphone jack—these games were not designed for crowded rooms or airplanes 🙂 When turning on Packri Monster once settling on the plane I quickly realized it would be impossible given how loud it was. I felt like someone watching their Youtube videos without headphones, and I hate those bastards!
Anyway, above is some video of me playing Packri Monster which will give you a better sense of the game than me describing it ever will.
My last post was supposed to detail the “Hot Summer 70s Family Horror” series MBS and I are doing right now for the Family Pictures Podcast, but it turned into a love letter to that podcast. We’re gonna record episode 28 and 29 later this week before I go on vacation, so that means we have just about 30 episodes in the can since November of 2024. That averages out to an episode a week for 8 months, which for those who have ever started a podcast know is no small feat.
The cool part of all that is we’re just starting to catch our stride; we’re starting to feel really comfortable with one another and realizing how valuable it is to have carved out the time to commune around something as awesome as movies (be they good or bad!) and bloviate at length about them—which might be the real joy of podcasting!
I spent this morning watching the documentary Birth Pains in preparation for our chat about David Cronenberg’s most personal and classic horror film The Brood (1979). That’s a damn good way to channel my energy, it gives my passion focus. The fact that MBS always brings his A-game with brilliant insights pushes me to stop pretending I know more than I do. It forces me to dig deeper and that’s the very thing you want when you’re trying to not just watch movies, but use them as a tool to make sense of the world around you…it’s what bridges them to a sense of culture. The joy of this particular podcast is using movies to try and understand how these artefacts inform the world in which we live. The episode on Fellini’s Amarcord (1973) was a moment wherein the film spoke to me about how an artist deals with the dark past of fascism in an honest way without erasing the deeply human players caught in its web. In fact, the post I wrote about that episode highlights just that—I wouldn’t have written that if I hadn’t have put in the work with MBS to think harder about that film.
The process of podcasting has been joyful because all the time I already spend watching movies is now channeled into a weekly event that psuhes me to research, reflect, negotiate, discuss, and ultimately write about it all. I have to think that’s at the heart of what undergirds the idea of an education that is everywhere promoted, no?
So, MBS and I are planning on doing a live session* for Reclaim Open wherein we do a meta-episode to discuss our podcast and highlight what I’m calling “The Joy of Podcasting.” Academic podcasting is nothing new at this point, but it might be fun to hear two goofballs talk about their film podcast and try and draw connections to higher ed, edtech, and open education. I’m sure we can shoehorn a few more themes in there as well, like say video production studios? 🙂
_______________________________________
*If you are keeping count, that’s my second shared presentation for Reclaim Open. What’s more, I have at least one more coming on AI Maddeness with Tom Woodward. Is there a fourth on the horizon?
is an ongoing conversation about media of all kinds ...
Testimonials:
Generations from now, they won't call it the Internet anymore. They'll just say, "I logged on to the Jim Groom this morning.
-Joe McMahon
Everything Jim Groom touches is gold. He's like King Midas, but with the Internet.
-Serena Epstein
My understanding is that an essential requirement of the internet is to do whatever Jim Groom asks of you while you're online.
-James D. Calder
@jimgroom is the Billy Martin of edtech.
-Luke Waltzer
My 3yr old son is VERY intrigued by @jimgroom's avatar. "Is he a superhero?" "Well, yes, son, to many he is."
-Clint Lalonde
Jim Groom is a fiery man.
-Antonella Dalla Torre
“Reverend” Jim “The Bava” Groom, alias “Snake Pliskin” is a charlatan and a fraud, a self-confessed “used car salesman” clawing his way into the glamour of the education technology keynote circuit via the efforts of his oppressed minions at the University of Mary Washington’s DTLT and beyond. The monster behind educational time-sink ds106 and still recovering from his bid for hipster stardom with “Edupunk”, Jim spends his days using his dwindling credibility to sell cheap webhosting to gullible undergraduates and getting banned from YouTube for gross piracy.
As part of this year’s 
