Header Ads

ChatGPT Powers a Different Kind of Logic Analyzer

If you’re hoping that this AI-powered logic analyzer will help you quickly debug that wonky digital circuit on your bench with the magic of AI, we’re sorry to disappoint you. But if you’re in luck if you’re in the market for something to help you detect logical fallacies someone spouts in conversation. With the magic of AI, of course.

First, a quick review: logic fallacies are errors in reasoning that lead to the wrong conclusions from a set of observations. Enumerating the kinds of fallacies has become a bit of a cottage industry in this age of fake news and misinformation, to the extent that many of the common fallacies have catchy names like “Texas Sharpshooter” or “No True Scotsman”. Each fallacy has its own set of characteristics, and while it can be easy to pick some of them out, analyzing speech and finding them all is a tough job.

To make things a little easier, [Matt] threw together a Raspberry Pi with a sound card and microphone for capturing live conversations. He also lists an HDMI audio extractor in the BOM, presumably for capturing audio from TV programs, likely a rich source of fallacies that would be needed for testing. A Rainbow LED hat and a touchscreen round out the UI end of the build. The code is pretty straightforward — audio is captured and saved to a file, which is sent to Whisper for speech-to-text conversion. The text file is then sent to ChatGPT along with a prompt asking the chatbot to find all the logical fallacies in the clip. The code parses the output of ChatGPT and displays which particular fallacies the speaker committed, if any. None were detected in the video below, but we suspect it wouldn’t be long before at least one cropped up.

Hats off to [Matt] for bringing us yet another fun way to use ChatGPT. We’ve seen a few in the short time the chatbot has been in the zeitgeist, including hitting the airwaves with hams and even making video game NPCs more interesting.


No comments