When you see a ventriloquist like [Jeff Dunham], you probably expect to see him with a puppet. This time – spoilers ahead – you won’t. Besides his fame on stage, [Dunham] is also a collector of vintage tech and a die-hard television enthusiast. In the video below, [Dunham] has gotten his hands on a rarity: an unboxed 1958 Philco Predicta TV. The original tape was still on the box. We get to follow along on his adventure to restore this sleek, retro-futuristic relic!

[Dunham]’s fascination with the Predicta stems from its historical significance and bold design. At a time when television was making its way into American homes, the Predicta dared to be different with its swivel-mounted picture tube and early printed circuit boards. Despite its brave aesthetics, the Predicta’s ambition led to notorious reliability issues. Yet, finding one in pristine condition, sealed and untouched for over six decades, is like unearthing a technological time capsule.

What makes this story unique is [Dunham]’s connection to both broadcasting and his craft. As a ventriloquist inspired by Edgar Bergen — whose radio shows captivated America — [Dunham] delights in restoring a TV from the same brand that first brought his idol’s voice to airwaves. His love for storytelling seamlessly translates into this restoration adventure.

After unboxing, [Dunham’s] team faces several challenges: navigating fragile components, securing the original shipping brace, and cautiously ramping up voltage to breathe life into the Predicta. The suspense peaks in the satisfying crackle of static, and the flicker of a 65-year-old screen finally awakened from slumber.

Have you ever come across an opportunity like this? Tell us about your favorite new old stock find in the comments. Buying these can be a risk, since components have a shelf life. We appreciate when these old TVs play period-appropriate shows. Who wants to watch Game of Thrones on a Predicta?

[EXO Labs] demonstrated something pretty striking: a modified version of Llama 2 (a large language model) that runs on Windows 98. Why? Because when it comes to personal computing, if something can run on Windows 98, it can run on anything. More to the point: if something can run on Windows 98 then it’s something no tech company can control how you use, no matter how large or influential they may be. More on that in a minute.

What’s it like to run an LLM on Windows 98? Aside from the struggles of things like finding compatible peripherals (back to PS/2 hardware!) and transferring the required files (FTP over Ethernet to the rescue) or even compilation (some porting required), it works maybe better than one might expect.

A Windows 98 machine with Pentium II processor and 128 MB of RAM generates a speedy 39.31 tokens per second with a 260K parameter Llama 2 model. A much larger 15M model generates 1.03 tokens per second. Slow, but it works. Going even larger will also work, just ever slower. There’s a video on X that shows it all in action.

It’s true that modern LLMs have billions of parameters so these models are tiny in comparison. But that doesn’t mean they can’t be useful. Models can be shockingly small and still be perfectly coherent and deliver surprisingly strong performance if their training and “job” is narrow enough, and the tools to do that for oneself are all on GitHub.

This is a good time to mention that this particular project (and its ongoing efforts) are part of a set of twelve projects by EXO Labs focusing on ensuring things like AI models can be run anywhere, by anyone, independent of tech giants aiming to hold all the strings.

And hey, if local AI and the command line is something that’s up your alley, did you know they already exist as single-file, multi-platform, command-line executables?