Running AI Locally Without Spending All Day On Setup

January 8, 2025 by Al Williams 33 Comments

There are many AI models out there that you can play with from companies like OpenAI, Google, and a host of others. But when you use them, you get the experience they want, and you run it on their computer. There are a variety of reasons you might not like this. You may not want your data or ideas sent through someone else’s computer. Maybe you want to tune and tweak in ways they aren’t going to let you.

There are many more or less open models, but setting up to run them can be quite a chore and — unless you are very patient — require a substantial-sized video card to use as a vector processor. There’s very little help for the last problem. You can farm out processing, but then you might as well use a hosted chatbot. But there are some very easy ways to load and run many AI models on Windows, Linux, or a Mac. One of the easiest we’ve found is Msty. The program is free for personal use and claims to be private, although if you are really paranoid, you’ll want to verify that yourself.

What is Msty?

Msty is a desktop application that lets you do several things. First, it can let you chat with an AI engine either locally or remotely. It knows about many popular options and can take your keys for paid services. For local options, it can download, install, and run the engines of your choice.

For services or engines that it doesn’t know about, you can do your own setup, which ranges from easy to moderately difficult, depending on what you are trying to do.

Of course, if you have a local model or even most remote ones, you can use Python or some basic interface (e.g., with ollama; there are plenty of examples). However, Msty lets you have a much richer experience. You can attach files, for example. You can export the results and look back at previous chats. If you don’t want them remembered, you can chat in “vapor” mode or delete them later.

Each chat lives in a folder, which can have helpful prompts to kick off the chat. So, a folder might say, “You are an 8th grade math teacher…” or whatever other instructions you want to load before engaging in chat.

Continue reading “Running AI Locally Without Spending All Day On Setup” →

Watch A 3D Scan Become A Car Body Model

December 20, 2024 by Donald Papp 1 Comment

Not all 3D scanning is alike, and the right workflow can depend on the object involved. [Ding Dong Drift] demonstrates this in his 3D scan of a project car. His goal is to design custom attachments, and designing parts gets a lot easier with an accurate 3D model of the surface you want to stick them on. But it’s not as simple as just scanning the whole vehicle. His advice? Don’t try to use or edit the 3D scan directly as a model. Use it as a reference instead.

Rather than manipulate the 3D scan directly, a better approach is sometimes to use it as a modeling reference to fine-tune dimensions.

To do this, [Ding Dong Drift] scans the car’s back end and uses it as a reference for further CAD work. The 3D scan is essentially a big point cloud and the resulting model has a very high number of polygons. While it is dimensionally accurate, it’s also fragmented (the scanner only captures what it can see, after all) and not easy to work with in terms of part design.

In [Ding Dong Drift]’s case, he already has a 3D model of this particular car. He uses the 3D scan to fine-tune the model so that he can ensure it matches his actual car where it counts. That way, he’s confident that any parts he designs will fit perfectly.

3D scanning has a lot of value when parts have to fit other parts closely and there isn’t a flat surface or a right angle to be found. We saw how useful it was when photogrammetry was used to scan the interior of a van to help convert it to an off-grid camper. Things have gotten better since then, and handheld scanners that make dimensionally accurate scans are even more useful.

Continue reading “Watch A 3D Scan Become A Car Body Model” →

Would An Indexing Feature Benefit Your Next Hinge Design?

November 27, 2024 by Donald Papp 2 Comments

[Angus] of Maker’s Muse has a video with a roundup of different 3D-printable hinge designs, and he points out that a great thing about 3D printing objects is that adding printable features to them is essentially free.

These hinges have an indexing feature that allows them to lock into place, no additional parts needed.

A great example of this is his experimental print-in-place butt hinge with indexing feature, which is a hinge that can lock without adding any additional parts. The whole video is worth a watch, but he shows off the experimental design at the 7:47 mark. The hinge can swing normally but when positioned just right, the squared-off pin within slots into a tapered track, locking the part in place.

Inspired by a handheld shopping basket with a lockable handle, [Angus] worked out a design of his own and demonstrates it with a small GoPro tripod whose legs can fold and lock in place. He admits it’s a demonstration of the concept more than a genuinely useful tripod, but it does show what’s possible with some careful design. Being entirely 3D printed in a single piece and requiring no additional hardware is awfully nice.

3D printing is very well-suited to this sort of thing, and it’s worth playing to a printer’s strengths to do for pennies what one would otherwise need dollars to accomplish.

Want some tips on designing things in a way that take full advantage of what a 3D printer can achieve? Check out printing enclosures at an angle with minimal supports, leveraging the living hinge to print complex shapes flat (and fold them up for assembly), or even print a one-piece hinge that can actually withstand a serious load. All of those are full of tips, so keep them in mind the next time you design a part.

A Laser With Mirrors Makes A CRT-like Display

November 26, 2024 by Maya Posch 22 Comments

[bitluni]’s laser-based display pretending to be a an old-school vector CRT.

Phosphor-based displays like CRTs rely on the phosphor to emit light for a set amount of time after being activated, allowing them to display a seemingly persistent image with one drawing beam per color. Translated to UV-sensitive PLA filament, this means that you can totally use a printed sheet of this material in combination with a 405 nm laser diode to create a display that doesn’t look dissimilar to an early CRT. This is exactly what [bitluni] did in a recent video, meshing together said laser diode, UV-sensitive PLA, stepper motors and two mirrors with an Arduino-based controller to create a rather interesting vector display.

In the video, [bitluni] goes over the development steps, including a range of improvements like being able to turn off the laser when moving between the end of a line and the beginning of a new one. While the Arduino Nano board does the driving of the stepper motor controllers, an ESP32 provides the drawing instructions. The STL and other project files including Nano & ESP32 firmware can be found on the GitHub project page.

While far from being a practical display with a single-digit Hz refresh rate, it does provide an interesting demonstration of these types of persistence of vision based displays, and without the use of exotic MEMS mirror modules or the like.

Continue reading “A Laser With Mirrors Makes A CRT-like Display” →

Dial-up Internet Using The Viking DLE-200B Telephone Line Simulator

November 19, 2024 by Maya Posch 27 Comments

Who doesn’t like dial-up internet? Even if those who survived the dial-up years are happy to be on broadband, and those who are still on dial-up wish that they weren’t, there’s definitely a nostalgic factor to the experience. Yet recreating the experience can be a hassle, with signing up for a dial-up ISP or jumping through many (POTS) hoops to get a dial-up server up and running. An easier way is demonstrated by [Minh Danh] with a Viking DLE-200B telephone line simulator in a recent blog post.

This little device does all the work of making two telephones (or modems) think that they’re communicating via a regular old POTS network. After picking up one of these puppies for a mere $5 at a flea market, [Minh Danh] tested it first with two landline phones to confirm that yes, you can call one phone from the other and hold a conversation. The next step was thus to connect two PCs via their modems, with the other side of the line receiving the ‘call’. In this case a Windows XP system was configured to be the dial-up server, passing through its internet connection via the modem.

With this done, a 33.6 kbps dial-up connection was successfully established on the client Windows XP system, with a blistering 3.8 kB/s download speed. The reason for 33.6 kbps is because the DLE-200B does not support 56K, and according to the manual doesn’t even support higher than 28.8 kbps, so even reaching these speeds was lucky.

Continue reading “Dial-up Internet Using The Viking DLE-200B Telephone Line Simulator” →

The Hardware pipeline consists of three parts: antenna, signal conditioners, and computer. The solid lines indicate LMR-400 cable (low loss microwave coax), whereas the dotted line represents USB 3.0. (Credit: Jack Phelps)

Tracking Hydrogen In Space With A Home Radio Telescope For 21 Cm Emissions

November 5, 2024 by Maya Posch 7 Comments

What do you get when you put a one-meter parabolic dish, an SDR, a Raspberry Pi, and an H1-LNA for 21 cm emissions together? The answer is: a radio telescope that can track hydrogen in the Milky Way as well as the velocities of hydrogen clouds via their Doppler shifts, according to a paper by [Jack Phelps] titled “Galactic Neutral Hydrogen Structures Spectroscopy and Kinematics: Designing a Home Radio Telescope for 21 cm Emission“.

The hardware pipeline consists of three parts: antenna, signal conditioners, and computer, as per the above graphic by [Jack Phelps]. The solid lines are low-loss microwave coax LMR-400 cable, and the dotted line represents USB 3.0 between the RTL-SDR and Raspberry Pi 4 system. This Raspberry Pi 4 runs a pre-made OS image (NsfSdr) by [Dr. Glenn Langston] at the National Science Foundation, which contains scripts for hydrogen line observation, calibration and data processing.

After calibration, the findings were verified using publicly available data, and the setup could be used to detect hydrogen by pointing the antenna at the intended target in space. Although a one-meter parabolic dish isn’t going to give you the most sensitivity, it’s still pretty rad that using effectively all off-the-shelf components and freely available software, you too can have your own radio telescope.

Phoniebox: A Family-Friendly Simple Music Box

October 5, 2024 by Arya Voronova 5 Comments

Ever hear of the Phoniebox project? If not – tune in, that’s a hacker’s project your entire family will appreciate. Phoniebox is a software suite and tutorial for building a jukebox controlled through RFID cards, and it can play audio from a wide variety of sources – music and playlists stored locally, online streams like internet radio stations, Spotify, podcasts of your choice, and so on. It’s super easy to build – get a Raspberry Pi board, connect an NFC reader to it, wire up a pair of speakers, and you’re set. You can assemble a PhonieBox together with your kids over the weekend – and many do.

Want some inspiration, or looking to see what makes Phoniebox so popular? Visit the Phoniebox gallery – it’s endearing to see just how many different versions have been built over the six years of project’s existence. Everyone’s Phoniebox build is different in its own special way – you bring the hardware, Phoniebox brings well-tested software and heaps of inspiration.

You already have a case to house a Phoniebox setup – if you think you don’t, check the gallery, you’ll find that you do. Experiencing a problem? There’s a wealth of troubleshooting advice and tutorials, and a helpful community. Phoniebox is a mature project and its scale is genuinely impressive – build one for your living room, or your hacker’s lair, or your hackerspace. RFID-controlled jukeboxes are a mainstay on Hackaday, so it’s cool to see a project that gives you all the tools to build one.