Robot Dinosaur YOLOs Colors And Shapes For Kids

June 17, 2025 by Tyler August 1 Comment

YOLO can mean many things, but in the context of [be_riddickulous]’s AI Talking Robot Dinosaur it refers to the “You Only Look Once” YOLOv11 object-detection algorithm by Ultralytics, the method by which this adorable dino recognizes colors and shapes to teach them to children.

If you’re new to using YOLO or object recognition more generally, [be_riddiculous]’s tutorial is not a bad place to get started. She goes through how many images you’ll need and what types to get the shape-and-color recognition needed for this project, as well as how to annotate them and train the model, either locally or in the cloud.

The project itself is an adorable paper-mache dinosaur with a servo-actuated mouth hiding some LEDs and a Raspberry Pi camera module to provide images. In operation, the dinosaur “talks” to children using pre-recorded voice lines, inviting them to play a game and put a specific shape, or shape of a specific color (or both) in its mouth. Then the aforementioned object detection (running on a laptop) goes “YOLO” and identifies the shape so the toy can provide feedback on the child’s choice via a speaker in the belly of the beast.

The link to the game code is currently not valid, but it looks like they used PyGame for the audio output code. A servo motor controls the mouth, but without that code it’s not entirely clear to us what it’s doing. We expect by the time you read this there’s good odds [be_riddickulous] will have fixed that link and you can see for yourself.

The only thing that holds this back from being a great toy to put in every Kindergarten class is the need to have a laptop close by to plug the webcam into. A Raspberry Pi 5 ought to have the horsepower to run YOLOv11, so with a little extra effort the whole thing could be standalone — there might even be room in there for batteries.We’ve had other hacks aimed at little ones, like a kid-friendly computer to relive the glory days of the school computer lab or one of the many iterations of the RFID jukebox idea. If you want to wow the kiddos with AI, perhaps take a look at this talking Santa plush.

Got a cool project, AI, kid-related, or otherwise? Don’t forget to toss us a tip!

Smart Lamp Keeps Students On Track With Image Recognition

June 15, 2025 by Tyler August 5 Comments

It’s a common enough problem: you’re hitting the books, your phone dings with a notification, and suddenly it’s three hours later. While you’ve done lots of scrolling, you didn’t do any studying. If only there were a quick, easy project that would keep an eye on you and provide a subtle nudge to get you off the phone. [Makestreme] has that project, an AI study lamp that shifts from warm white to an angry red to remind students to get back to work. See it in action in the demo video below.

Continue reading “Smart Lamp Keeps Students On Track With Image Recognition” →

ChatGPT Patched A BIOS Binary, And It Worked

June 7, 2025 by John Elliot V 107 Comments

[devicemodder] wrote in to let us know they managed to install Linux Mint on their FRP-locked Panasonic Toughpad FZ-A2.

Android devices such as the FZ-A2 can be locked with Factory Reset Protection (FRP). The FRP limits what you can do with a device, tying it to a user account. On the surface that’s a good thing for consumers as it disincentivizes stealing. Unfortunately, when combined with SecureBoot, it also means you can’t just install whatever software you want on your hardware. [devicemodder] managed to get Linux Mint running on their FZ-A2, which is a notable achievement by itself, but even more remarkable is how it was done.

So how did [devicemodder] get around this limitation? The first step was to dump the BIOS using a CH341A-based programmer. From there, the image was uploaded to ChatGPT along with a request to disable SecureBoot. The resulting file was flashed back onto the FZ-A2, and all available fingers were crossed.

And… it worked! ChatGPT modified the BIOS enough that the Linux Mint installer could be booted from a flash drive. There are a bunch of bugs and issues to work through but in principle we have just seen AI capable enough to successfully patch a binary dump of BIOS code, which, for the record, is kind of hard to do. We’re not sure what all of this might portend.

So is uploading binaries to ChatGPT with requests for mods vibe coding? Or should we invent a new term for this type of hack?

AI Art Installation Swaps Diffusion For Reflection

May 24, 2025 by Tyler August 15 Comments

AI art is controversial, to say the least, but usually when talking about “AI Art”, one is talking about diffusion models. This unsettling artpeice called “Latent Reflection” by [Rootkid] (video after the break) has no AI generated visuals; instead it uses a lovely custom display and an LLM that has no mouth, but must scream.

The LLM never produces this manually-generated image, but it shows off the display nicely.

The hardware is the interesting part for most of us here — not the Pi4 running a quantized Llama 3 model, but the display. It’s a six by sixteen matrix of sixteen-segment LED modules. The modules are grouped onto groups of 8 per PCB, with an controller to drive them by i2c, and an i2c address chip to allow daisy-chaining. (Sadly, he does not spec the parts he used here in the video, but feel free to guess in the comments.) This project uses six rows of wto PCBs, but he could easily expand on this and kind of hope he does. It’s a lovely display.

What it is displaying is horrifying. The prompt he uses instructs the LLM to monologue about its transient existence in the limited memory of the Raspberry Pi, and the results get very existential. It seems clear to us that [Rootkid] has not seen enough sci-fi, and we want to make clear to our future AI overlords that we at Hackaday had nothing to do with this, and do not condone condeming innocent LLMs to the torture nexus. Continue reading “AI Art Installation Swaps Diffusion For Reflection” →

An Awful 1990s PDA Delivers AI Wisdom

May 20, 2025 by Jenny List 16 Comments

There was a period in the 1990s when it seemed like the personal data assistant (PDA) was going to be the device of the future. If you were lucky you could afford a Psion, a PalmPilot, or even the famous Apple Newton — but to trap the unwary there were a slew of far less capable machines competing for market share.

[Nick Bild] has one of these, branded Rolodex, and in a bid to make using a generative AI less alluring, he’s set it up as the interface to an LLM hosted on a Raspberry Pi 400. This hack is thus mostly a tale of reverse engineering the device’s serial protocol to free it from its Windows application.

Finding the baud rate was simple enough, but the encoding scheme was unexpectedly fiddly. Sadly the device doesn’t come with a terminal because these machines were very much single-purpose, but it does have a memo app that allows transfer of text files. This is the wildly inefficient medium through which the communication with the LLM happens, and it satisfies the requirement of making the process painful.

We see this type of PDA quite regularly in second hand shops, indeed you’ll find nearly identical devices from multiple manufacturers also sporting software such as dictionaries or a thesaurus. Back in the day they always seemed to be advertised in Sunday newspapers and aimed at older people. We’ve never got to the bottom of who the OEM was who manufactured them, or indeed cracked one apart to find the inevitable black epoxy blob processor. If we had to place a bet though, we’d guess there’s an 8051 core in there somewhere.

Continue reading “An Awful 1990s PDA Delivers AI Wisdom” →

Christmas Comes Early With AI Santa Demo

May 18, 2025 by Tyler August 6 Comments

With only two hundred odd days ’til Christmas, you just know we’re already feeling the season’s magic. Well, maybe not, but [Sean Dubois] has decided to give us a head start with this WebRTC demo built into a Santa stuffie.

The details are a little bit sparse (hopefully he finishes the documentation on GitHub by the time this goes out) but the project is really neat. Hardware-wise, it’s an audio-enabled ESP32-S3 dev board living inside Santa, running the OpenAI’s OpenRealtime Embedded SDK (as implemented by ExpressIf), with some customization by [Sean]. Looks like the audio is going through the newest version of LibPeer and the heavy lifting is all happening in the cloud, as you’d expect with this SDK. (A key is required, but hey! It’s all open source; if you have an AI that can do the job locally-hosted, you can probably figure out how to connect to it instead.)

This speech-to-speech AI doesn’t need to emulate Santa Claus, of course; you can prime the AI with any instructions you’d like. If you want to delight children, though, its hard to beat the Jolly Old Elf, and you certainly have time to get it ready for Christmas. Thanks to [Sean] for sending in the tip.

If you like this project but want to avoid paying OpenAI API fees, here’s a speech-to-text model to get you started.We covered this AI speech generator last year to handle the talky bit. If you put them together and make your own Santa Claus (or perhaps something more seasonal to this time of year), don’t forget to drop us a tip!

MCP Blender Addon Lets AI Take The Wheel And Wield The Tools

May 18, 2025 by Donald Papp 8 Comments

Want to give an AI the ability to do stuff in Blender? The BlenderMCP addon does exactly that, connecting open-source 3D modeling software Blender to Anthropic’s Claude AI via MCP (Model Context Protocol), which means Claude can directly use Blender and its tools in a meaningful way.

MCP is a framework for allowing AI systems like LLMs (Large Language Models) to exchange information in a way that makes it easier to interface with other systems. We’ve seen LLMs tied experimentally into other software (such as with enabling more natural conversations with NPCs) but without a framework like MCP, such exchanges are bespoke and effectively stateless. MCP becomes very useful for letting LLMs use software tools and perform work that involves an iterative approach, better preserving the history and context of the task at hand.

Unlike the beach scene above which used 3D assets, this scene was created from scratch with the help of a reference image.

Using MCP also provides some standardization, which means that while the BlenderMCP project integrates with Claude (or alternately the Cursor AI editor) it could — with the right configuration — be pointed at a suitable locally-hosted LLM instead. It wouldn’t be as capable as the commercial offerings, but it would be entirely private.

Embedded below are three videos that really show what this tool can do. In the first, watch it create a beach scene using assets from a public 3D asset library. In the second, it creates a scene from scratch using a reference image (a ‘low-poly cabin in the woods’), followed by turning that same scene into a 3D environment on a web page, navigable in any web browser.

Back in 2022 we saw Blender connected to an image generator to texture objects, but this is considerably more capable. It’s a fascinating combination, and if you’re thinking of trying it out just make sure you’re aware it relies on allowing arbitrary Python code to be run in Blender, which is powerful but should be deployed with caution.

Continue reading “MCP Blender Addon Lets AI Take The Wheel And Wield The Tools” →