e530 — Vibe It! – Ready Player Chum

Friendly bipedal robot strolling down a path
Photo by Kindel Media from Pexels: https://www.pexels.com/photo/white-robot-toy-on-gray-concrete-floor-9026299/

Published 29 September 2025

e530 with Michael and Michael – an AI extravaganza with vibe coding, AI gaming chums, rating LLMs via Infocom games, robots for construction, self assembling space habitats and a whole lot more.

Michael and Michael get things moving this episode with an AI extravaganza while Andy is away.  The co hosts start things off with a vibe coding assistant to help you with your QBasic programming needs.  Next up, the pair consider a couple of stories dealing with assistants who can help users be more effective in playing games.  There is a real Goldilocks zone for the assistant to help the player remain in a state of flow, where the game is neither too easy due to the assistant’s help, nor too frustrating to play.  Michael R gives an example of his trying to get to Orc Town to progress in Mines of Moria.  Continuing on the theme of AIs playing games, Michael and Michael take a look at TextQuests, where a variety of LLMs take up the challenge of playing Infocom text based games.  With all the discussion on AI slop in the news, the article from Computerworld about the mathematical inevitability of hallucinations is particularly timely.

Michael and Michael move from AI to robotics and take a look at the construction bot from Dusty Robotics, which prints out a life size blueprint directly on the floor.  Michael M shares a space habitat construction solution from Aurelia that uses magnets to self assemble in orbit.  Michael R shares a story about the engineering feat of moving a viking ship without damaging it, which reminded Michael M of the challenge of moving the Cape Hatteras lighthouse.  Check out the links below for all the details.

What would your ideal game chum be like?  What do you think about the current state of AI chum?  Have your bots 🤖 drop our bots 🤖 a line at @gamesatwork_biz (our home for now) and let us know! 

These show notes were lovingly hand crafted by a real human, and not by a bot.  All rights reserved.  That’s our story and we’re sticking to it.

Selected Links

AI

hackaday.io AI Coding Assistant for Microsoft QBasic

Engadget article: Google is turning Gemini into a gaming sidekick with a new Android overlay

PC Gamer article: Microsoft’s new Gaming Copilot AI tool promises to be ‘your personal gaming sidekick’ but it mostly seems to do the work of a Google search, with the potential for ‘hallucinations’

Games at Work e488: Fight. For Your Right. To Pla-aaay! for Jane McGonigal and flow 

The Gamer article: How To Find Orc Town In The Lord Of The Rings: Return To Moria

404 Media article: AI-Powered Animal Crossing Villagers Begin Organizing Against Tom Nook

TextQuests.ai 

Wikipedia article: Infocom

OpenAI admits AI hallucinations are mathematically inevitable, not just engineering flaws
computerworld.com/article/4059

— Charlie Stross (@cstross) 2025-09-21T17:14:32.576Z

Computerworld article: OpenAI admits AI hallucinations are mathematically inevitable, not just engineering flaws

Rule 34 by Charles Stross

Accelerando by Charles Stross

Games at Work e306: Weak Ties for Accelerando 

hitchhikers.fandom.com: Infinite Improbability Drive

Washington Post article: AI firm Deepseek writes less secure code for groups China disfavors

Robots

Dusty Robotics

Aurelia: Tesserae: Self-Assembling Prototypes

Magnatiles

This is Colossal article: A Feat of Engineering Transports the World’s Best-Preserved Viking Ship to Its New Home

National Park Service article: Moving the Cape Hatteras Lighthouse

Two More Things

Six Colors article: Apple Announces a New Set of Immersive Film Releases

Random Thoughts post: My AirPods Review

e529 — Shake, Shake, Shake Your iPhone

iPhone and a shake with a straw on a table next to one another
Photo by Ravi Sharma on Unsplash

Published 15 September 2025

e529 with Michael, Andy and Michael – stories about AR glasses & snarky AI wearables, Carrot Weather, Rabbit OS2, shaking to summarize, Doomscrolling and a whole lot more.

Michael, Andy and Michael get things moving this episode with all things AI.  After starting with a parody about camera less phones which generate pictures, the team moves to an article about Amazon’s project Jayhawk AR glasses for their drivers.  Next up is a new gesture for Firefox users on iOS – the ability to shake to summarize.  After an article on AI audio manipulation, Andy and Michael M are reminded of how Denmark is providing a defense against deepfakes by updating copyrights to provide individuals the right to their own appearance and voice.

Following up on a plethora of stories in recent episodes on AI powered wearables, this episode takes on the Futurism article about the Friend pendant.  Apparently, this companion has a bit of a snarky personality by design, and that got the co hosts talking about Carrot’s weather application.  After mentioning that the Rabbit portable AI device gains a new OS upgrade, the team takes on a couple of game topics, including iPod click wheel game preservation and a Doomscroll game to try.

Would you rather play Doomscroll or just doomscroll manually?  Have your bots 🤖 drop our bots 🤖 a line at @gamesatwork_biz (our home for now) and let us know! 

These show notes were lovingly hand crafted by a real human, and not by a bot.  All rights reserved.  That’s our story and we’re sticking to it.

Selected Links

AI

These iPhone features are getting ridiculous!

(By Simon Meyer on IG (simonmeyer_director)

— 🎬 John • A Film Nerd • 🎥 (@UKFilmNerd) 2025-09-09T19:45:34.929Z

The Verge article: Amazon drivers could be wearing AR glasses with a built-in display next year

Amazon Accelerate Sept 16-18, 2025

Meta Connect Sept 17 – 18, 2025

The Verge article: Firefox launches ‘shake to summarize’ on iPhones

AskVG post: How to Disable and Remove All AI Features in Mozilla Firefox

Firefox article: Ready to shake things up?

News & Observer article: An NC senator’s words were manipulated by AI in an ad. Now she’s suing

The Guardian article: Denmark to tackle deepfakes by giving people copyright to their own features

Futurism article: New AI Necklace Listens Constantly and Uses All That Data to Complain About You

Friend

Carrot Weather

rabbit post: rabbit overhauls r1 experience with rabbitOS 2

Games at Work e502: Humane Rabbits

Games

Retrododo article: The Complete Range Of iPod Clickwheel Games Has Finally Been Preserved

Ironic Sans post: Doomscrolling: The Game

Doomscroll

e528 — Monstrous Mice & Nano Bananas

ChatGPT 5 generated image of a banana in the midst of an atom cloud generated 31 August 2025
ChatGPT 5 generated image of a banana in the midst of an atom cloud
generated 31 August 2025

Published 8 September 2025

e528 with Michael, Andy and Michael – stories about AI image editing with Nano Banana, GAN enabled LLM evolution with R-Zero, MentraOS open source smart glasses, automotive software, Making Monsters, Kazeta and a whole lot more.

Michael, Andy and Michael get things rolling with the Nano Banana image editing software from Google.  While the generated and altered images are very sophisticated, there are still a few tells that the photos came from AI.  An example from the Washington Post article calls out the “AI gibberish” replacement of numbers on the phone keypad – while the replacement of the human in the phone booth with a water buffalo replete with smart ring is ultra realistic.  Andy’s ChatGPT generated nano banana is a fun visualization for an atom-sized banana, even though he was “AI-splained” by the chatbot that “a banana at that scale couldn’t exist in any realistic way.” Ha!  

The team touches on a couple more AI stories dealing with with the Fast-VLM video captioning model and a generative adversarial network method of self evolving reasoning LLM with R-Zero.  Next is a springboard for the MentraOS open source smart glasses operating system that reminds the team of Andy’s experience in 2024 with the Brilliant Labs Monocle.  

Then the co-hosts talk about automotive software – and the challenges posed by the need to troubleshoot and correct for the intersection between evolving software and existing hardware.  The frequency for software updates for a vehicle, phones and more requires a level of testing and integration that can be very frustrating when things don’t work as expected.  Understatement of the year, I’m sure.

Wrapping up the episode are a couple of games – a kickstarter called Making Monsters, Office Job, which has a television sized screen and suitcase sized mouse and Kazeta for cartridge gaming.

What’s been your most frustrating automotive software experience?  Have your bots 🤖 drop our bots 🤖 a line at @gamesatwork_biz (our home for now) and let us know! 

These show notes were lovingly hand crafted by a real human, and not by a bot.  All rights reserved.  That’s our story and we’re sticking to it.

Selected Links

AI

Washington Post article: Masterful photo edits now just take a few words. Are we ready for this?

Nano Banana AI Image Editing

9 to 5 Mac article: You can try Apple’s lightning-fast video captioning model right from your browser

FastVLM-webgpu on Huggingface Spaces

Venture Beat article: Forget data labeling: Tencent’s R-Zero shows how LLMs can train themselves

R-Zero: Self-Evolving Reasoning LLM from Zero Data paper on arXiv

Unacceptable situation to wear camera glasses of the moment: while doing a bikini wax
futurism.com/wax-center-meta-g

— Mike Elgan (@MikeElgan) 2025-08-31T17:06:05.260Z

MentraOS Open Source Smart Glasses OS on Github

Games at Work e453: Vision Pro a Pro-Pro (for Brilliant Labs Frame)

Games at Work e436: Squishy Purple Doom (for Andy’s experience with Brilliant Labs Monocle)

Automotive Software

TechCrunch article: BMW, I am so breaking up with you

BMWblog post: Apple’s iOS 18 Update Is Causing BMW Digital Car Key Problems: Solutions Inside from October 2024

Games

Making Monsters on Kickstarter

Games at Work e455: Star Trek vs Douglas Adams (for Spore)

Felix Fisgus post: Office Job from 2022

hackster.io article: Alesh Slovak’s Kazeta Turns Mini-PCs Into ’90s Throwback “Cartridge”-Based Games Consoles

Kazeta

e527 — AI Taco Trolls

Taco truck with the phrase “In tacos we trust” written across the front of the truck
Photo by Daniel Hooper 🌊 on Unsplash

Published 1 September 2025

e527 with Andy, Michael and Michael – stories about AI restaurant experiences, historical LLMs, zoetropes and a whole lot more.

After Michael R gives his impressions of the PhotoDome app, the team starts things off with a story about the AI powering Taco Bell’s drive through point of sale experience.  In the past few days, there have been a multitude of stories about the attempt to order 18,000 cups of water from the Yum Foods franchise.  Check out the conversation in the podcast and the referenced articles in the show notes below.  Continuing on the AI and restaurant theme, the team considers another article that reports on nonexistent specials that the restaurant has to deal with.  While discussing the Wired article about which jobs AI is eliminating first, Michael M (mistakenly!) references a zoom seminar on the subject from Stanford University’s Human-Centered Artificial Intelligence Digital Economy Lab.  This seminar is scheduled for 29 September, so there’s still plenty of time to register for it at the link below!  After touching on a couple of articles dealing with ChatGPT scanning conversations and instituting parental controls, the team switches to an AI use case that is very close to home for Andy’s educational background as a historian.  Check out the GitHub link to TimeCapsuleLLM below and give it a whirl for yourself! 

The team wraps up this episode with two interesting links – the trailer for the upcoming game The Expanse, and a fantastic piece of vinyl zoetrope technology from Atliens (please check out the link to see the visual for the alien abduction visuals – so cool!)

What is your favorite vinyl zoetrope?  We’d love to share it with the Games at Work audience!   Have your bots 🤖 drop our bots 🤖 a line at @gamesatwork_biz (our home for now) and let us know! 

These show notes were lovingly hand crafted by a real human, and not by a bot.  All rights reserved.  That’s our story and we’re sticking to it.

Selected Links

PhotoDome reprise

Random Thoughts blog post: PhotoDome for visionOS

PhotoDome

Games at Work e526: Beans and Bricks (for the initial discussion on PhotoDome)

AI

The Verge article: Taco Bell’s AI drive-thru plan gets caught up on trolls and glitches

AI Business article: Taco Bell Expands AI Voice Ordering at Drive-Thrus Nationwide

BBC article: Taco Bell rethinks AI drive-through after man orders 18,000 waters

Wikipedia article: Troll

Futurism article: Local Restaurant Exhausted as Google AI Keeps Telling Customers About Daily Specials That Don’t Exist

Games at Work e522: Pointing at Doomed Fish (for how Google’s AI Overview oversimplifies)

Wired article: AI Is Eliminating Jobs for Younger Workers

Stanford University Human-Centered Artificial Intelligence paper and seminar: Canaries in the Coal Mine? Six Facts about the Recent Employment Effects of Artificial Intelligence

Futurism article: OpenAI Says It’s Scanning Users’ ChatGPT Conversations and Reporting Content to the Police

The Verge article: OpenAI will add parental controls for ChatGPT following teen’s death

Games at Work e524: Googlenight AI (for discussion on publishing exchanges with ChatGPT)

Ars Technica article: College student’s “time travel” AI experiment accidentally outputs real 1834 history

Github: haykgrigo3/TimeCapsuleLLM

Software

atliensofficial.com post: Leaving The World Behind Vinyl