Over the previous few years an AI summer time has been heating up like by no means earlier than, and plenty of new and fascinating purposes have been unveiled throughout this time. As is normally the case, numerous hype additionally got here alongside for the experience. A variety of overhyped AI assistants, particularly, have emerged currently that promise to do completely every thing for you, however find yourself doing little greater than a typical smartphone, all whereas proving to be frustratingly unreliable.
{Hardware} hacker Jared Carrillo was fed up with these under-delivering AI assistants and, relatively than complaining, determined to attempt to do one thing about it. His aim was to construct a transportable AI assistant that would not solely reply questions, but in addition take some actions, like inserting an order for a pizza. He form of succeeded, however actually ended up with an assistant that’s about as irritating as some other product in the marketplace. However no less than it’s his irritating AI assistant. And it was additionally a very good alternative for experimentation, which Carrillo believes will give him the insights he must ultimately construct a greater machine.
Assembling the {hardware} (📷: Jared Carrillo)
The assistant is named the Clever System for Automated AI Computing (ISAAC). The preliminary prototype was constructed right into a 3D-printed case, however in the end a nicer steel case was manufactured by PCBWay. Contained in the case, there’s a Raspberry Pi Compute Module 4 for processing, in addition to a Nano Base Board to offer for straightforward peripheral connections. There may be additionally a 2.8-inch show for interactive options, and a Raspberry Pi digital camera to seize photos. Audio recording and playback are made attainable with a RASPIAUDIO sound card. A chargeable battery offers energy to the transportable assistant.
ISAAC operates in an identical method to many different voice assistants made by different {hardware} hackers. After urgent a button on the machine, it information 5 seconds of audio. That audio is then transcribed to textual content utilizing the OpenAI Whisper API. That textual content is fed into ChatGPT, and at last the response is transformed to audio with the eSpeak speech synthesizer earlier than being performed by ISAAC.
This structure allows the machine to answer spoken questions, and likewise clarify what’s current in photos captured by the digital camera. One of many large advantages of constructing your individual machine is you can program it to do no matter you need. On this case, Carrillo constructed some hooks into the software program that made it attainable to order a pizza with a easy voice request. He additionally in-built a function that may get again at a pal that has been bugging him by spamming them with a gentle stream of textual content messages. That isn’t precisely a typical function of AI assistants — though that’s most likely a very good factor.
ISAAC just isn’t going to vary the world, however the strategies utilized by Carrillo can simply be copied, so it must be fairly easy to clone ISAAC. Make sure you take a look at the video for all the small print if you wish to create your individual customized AI assistant.
