Schooling ChatGPT On Antenna Theory Misconceptions

November 17, 2024 by Dan Maloney 38 Comments

We’re not very far into the AI revolution at this point, but we’re far enough to know not to trust AI implicitly. If you accept what ChatGPT or any of the other AI chatbots have to say at face value, you might just embarrass yourself. Or worse, you might make a mistake designing your next antenna.

We’ll explain. [Gregg Messenger (VE6WO)] asked a seemingly simple question about antenna theory: Does an impedance mismatch between the antenna and a coaxial feedline result in common-mode current on the coax shield? It’s an important practical matter, as any ham who has had the painful experience of “RF in the shack” can tell you. They also will likely tell you that common-mode current on the shield is caused by an unbalanced antenna system, not an impedance mismatch. But when [Gregg] asked Google Gemini and ChatGPT that question, the answer came back that impedance mismatch can cause current flow on the shield. So who’s right?

In the first video below, [Gregg] built a simulated ham shack using a 100-MHz signal generator and a length of coaxial feedline. Using a toroidal ferrite core with a couple of turns of magnet wire and a capacitor as a current probe for his oscilloscope, he was unable to find a trace of the signal on the shield even if the feedline was unterminated, which produces the impedance mismatch that the chatbots thought would spell doom. To bring the point home, [Gregg] created another test setup in the second video, this time using a pair of telescoping whip antennas to stand in for a dipole antenna. With the coax connected directly to the dipole, which creates an unbalanced system, he measured a current on the feedline, which got worse when he further unbalanced the system by removing one of the legs. Adding a balun between the feedline and the antenna, which shifts the phase on each leg of the antenna 180° apart, cured the problem.

We found these demonstrations quite useful. It’s always good to see someone taking a chatbot to task over myths and common misperceptions. We look into baluns now and again. Or even ununs.

Continue reading “Schooling ChatGPT On Antenna Theory Misconceptions” →

Internet Connected TI-84 To Cut Your Academic Career Short

September 29, 2024 by Danie Conradie 22 Comments

In an educational project with ethically questionable applications, [ChromaLock] has converted the ubiquitous TI-84 calculator into the ultimate cheating device.

The foundation of this hack lies in the TI-84’s link protocol, which has been a mainstay in calculator mods for years. [ChromaLock] uses this interface to connect to a tiny WiFi-enabled XIAO ESP32-C3 module hidden in the calculator. It’s mounted on a custom PCB with a simple MOSFET-based level shifting circuit, and slots neatly into a space on the calculator rear cover. The connecting wires are soldered directly to the pads of the 2.5 mm jack, and to the battery connections for power.

But what does this mod do? It connects your calculator to the internet and gives you a launcher with several applets. These allow you to view images badly pixelated images on the TI-84’s screen, text-chat with an accomplice, install more apps or notes, or hit up ChatGPT for some potentially hallucinated answers. Inputting long sections of text on the calculator’s keypad is a time-consuming process, so [ChromaLock] teased a camera integration, which will probably make use of newer LLMs image input capabilities. The ESP32 doesn’t handle all the heavy lifting, and needs to connect to an external server for more complex interfaces.

To prevent pre-installed programs from being used for cheating on TI-84s, examiners will often wipe the memory or put it into test mode. This mod can circumvent both. Pre-installed programs are not required on the calculator to interface with the hardware module, and installing the launcher is done by sending two variables containing a password and download command to the ESP32 module. The response from the module will also automatically break the calculator out of test mode.

We cannot help but admire [ChromaLock]’s ingenuity and polished implementation, and hopefully our readers are more interested in technical details than academic self-sabotage. For those who need even more capability in their calculator, we’d suggest checking out the NumWorks. Continue reading “Internet Connected TI-84 To Cut Your Academic Career Short” →

Uncovering ChatGPT Usage In Academic Papers Through Excess Vocabulary

June 22, 2024 by Maya Posch 23 Comments

Frequencies of PubMed abstracts containing certain words. Black lines show counterfactual extrapolations from 2021–22 to 2023–24. The first six words are affected by ChatGPT; the last three relate to major events that influenced scientific writing and are shown for comparison. (Credit: Kobak et al., 2024)

That students these days love to use ChatGPT for assistance with reports and other writing tasks is hardly a secret, but in academics it’s becoming ever more prevalent as well. This raises the question of whether ChatGPT-assisted academic writings can be distinguished somehow. According to [Dmitry Kobak] and colleagues this is the case, with a strong sign of ChatGPT use being the presence of a lot of flowery excess vocabulary in the text. As detailed in their prepublication paper, the frequency of certain style words is a remarkable change in the used vocabulary of the published works examined.

For their study they looked at over 14 million biomedical abstracts from 2010 to 2024 obtained via PubMed. These abstracts were then analyzed for word usage and frequency, which shows both natural increases in word frequency (e.g. from the SARS-CoV-2 pandemic and Ebola outbreak), as well as massive spikes in excess vocabulary that coincide with the public availability of ChatGPT and similar LLM-based tools.

In total 774 unique excess words were annotated. Here ‘excess’ means ‘outside of the norm’, following the pattern of ‘excess mortality’ where mortality during one period noticeably deviates from patterns established during previous periods. In this regard the bump in words like respiratory are logical, but the surge in style words like intricate and notably would seem to be due to LLMs having a penchant for such flowery, overly dramatized language.

The researchers have made the analysis code available for those interested in giving it a try on another corpus. The main author also addressed the question of whether ChatGPT might be influencing people to write more like an LLM. At this point it’s still an open question of whether people would be more inclined to use ChatGPT-like vocabulary or actively seek to avoid sounding like an LLM.

Wrencher-2: A Bold New Direction For Hackaday

April 1, 2024 by Jenny List 44 Comments

Over the last year it’s fair to say that a chill wind has blown across the face of the media industry, as the prospect emerges that many content creation tasks formerly performed by humans instead being swallowed up by the inexorable rise of generative AI. In a few years we’re told, there may even be no more journalists, as the computers become capable of keeping your news desires sated with the help of their algorithms.

Here at Hackaday, we can see this might be the case for a gutter rag obsessed with celebrity love affairs and whichever vegetable is supposed to cure cancer this week, but we continue to believe that for quality coverage of the latest and greatest in the hardware hacking world, you can’t beat a writer made of good old-fashioned meat. Indeed, in a world saturated by low-quality content, the opinions of smart and engaged writers become even more valuable. So we’ve decided to go against the trend, by launching not a journalist powered by AI, but an AI powered by journalists.

Announcing Wrencher-2, a Hackaday chat assistant in your browser

Wrencher-2 is a new paradigm in online chat assistants, eschewing generative algorithms in favour of the collective expertise of the Hackaday team. Ask Wrencher-2 a question, and you won’t get a vague and made-up answer from a computer, instead you’ll get a pithy and on-the-nail answer from a Hackaday staffer. Go on – try it! Continue reading “Wrencher-2: A Bold New Direction For Hackaday” →

Tech Support… Can AI Be Worse?

March 28, 2024 by Al Williams 56 Comments

You can’t read the news today without another pundit excitedly reporting how AI is going to take every job you can imagine. Of course, AI will change the employment landscape. It will take some jobs and reduce the need for others. What about tech support? Is it possible that an AI might be able to help people with technical issues better than humans? My first answer was no way, but then I was painfully reminded of something. The question isn’t if AI can help you better than any human can. The question is if AI can help you better than the low-paid person on the other end of the phone you are likely to talk to. Sadly, I think the answer to that question is almost certainly yes.

In all fairness, if you read Hackaday, you probably don’t encounter many technical support people who can solve a problem you can’t. By the time you call them, it is a lost cause. But this is more than just “Hackday folks are smarter than the tech support agents.” The overall quality of tech support at many companies is rock bottom no matter who you are. Continue reading “Tech Support… Can AI Be Worse?” →

Generative AI Now Encroaching On Music

March 22, 2024 by Bryan Cockfield 62 Comments

While it might not seem like it to a novice, music turns out to be a highly mathematical endeavor with precise ratios between chords and notes as well as overall structure of rhythm and timing. This is especially true of popular music which has even more recognizable repeating patterns and trends, making it unfortunately an easy target for modern generative AI which is capable of analyzing huge amounts of data and creating arguably unique creations. This one, called Suno, does just that for better or worse.

Unlike other generative AI offerings that are currently available for creating music, this one is not only capable of generating the musical underpinnings of the song itself but can additionally create a layer of intelligible vocals as well. A deeper investigation of the technology by Rolling Stone found that the tool uses its own models to come up with the music and then offloads the text generation for the vocals to ChatGPT, finally using the generated lyrics to generate fairly convincing vocals. Like image and text generation models that have come out in the last few years, this has the potential to be significantly disruptive.

While we’re not particularly excited about living in a world where humans toil while the machines create art and not the other way around, at best we could hope for a world where real musicians use these models as tools to enhance their creativity rather than being outright substitutes, much like ChatGPT itself currently is for programmers. That might be an overly optimistic view, though, and only time will tell.

Learn AI Via Spreadsheet

March 18, 2024 by Al Williams 8 Comments

While we’ve been known to use and abuse spreadsheets in the past, we haven’t taken it to the level of [Spreadsheets Are All You Need]. The site provides a spreadsheet version of an “AI” system much like ChatGPT 2. Sure, that’s old tech, but the fundamentals are the same as the current crop of AI programs. There are several “lesson” videos that explain it all, with the promise of more to come. You can also, of course, grab the actual spreadsheet.

The spreadsheet is big, and there are certain compromises. For one thing, you have to enter tokens separately. There are 768 numbers representing each token in the input. That’s a lot for a spreadsheet, but a modern GPT uses many more.

Continue reading “Learn AI Via Spreadsheet” →