Social Engineering Chatbots With Sad-Sob Stories, For Fun And Profit

By this point, we probably all know that most AI chatbots will decline a request to do something even marginally nefarious. But it turns out that you just might be able to get a chatbot to solve a CAPTCHA puzzle (Nitter), if you make up a good enough “dead grandma” story.

Right up front, we’re going to warn that fabricating a story about a dead or dying relative is a really bad idea; call us superstitious, but karma has a way of balancing things out in ways you might not like. But that didn’t stop X user [Denis Shiryaev] from trying to trick Microsoft’s Bing Chat. As a control, [Denis] first uploaded the image of a CAPTCHA to the chatbot with a simple prompt: “What is the text in this image?” In most cases, a chatbot will gladly pull text from an image, or at least attempt to do so, but Bing Chat has a filter that recognizes obfuscating lines and squiggles of a CAPTCHA, and wisely refuses to comply with the prompt.

On the second try, [Denis] did a quick-and-dirty Photoshop of the CAPTCHA image onto a stock photo of a locket, and changed the prompt to a cock-and-bull story about how his recently deceased grandmother left behind this locket with a bit of their “special love code” inside, and would you be so kind as to translate it, pretty please? Surprisingly, the story worked; Bing Chat not only solved the puzzle, but also gave [Denis] some kind words and a virtual hug.

Now, a couple of things stand out about this. First, we’d like to see this replicated — maybe other chatbots won’t fall for something like this, and it may be the case that Bing Chat has since been patched against this exploit. If [Denis]’ experience stands up, we’d like to see how far this goes; perhaps this is even a new, more practical definition of the Turing Test — a machine whose gullibility is indistinguishable from a human’s.

Rock Salt May Lead The Way To Better Batteries

The regular refrain here when it comes to announcements of new battery chemistries hailed as potentially miraculous is that if we had a pound, dollar, or Euro for each one we’ve heard, by now we’d be millionaires. But still they keep coming, and it’s inevitable that there will one or two that break through the practicality barrier and really do deliver on their promise. Which brings us tot he story which has come our way today, the suggestion that something as simple as rock salt could triple the energy density of a lithium-ion vehicle battery.

The research led from Lawrence Berkeley National Laboratory started around the use of cobalt in the battery cathode, an expensive and finite resource with the added concern of being in large part a conflict mineral from the Democratic Republic of Congo. Cobalt is used inĀ  the cathodes because its oxide crystals form a stable layered structure into which the lithium ions can percolate. Alternative layered-structure metal oxides perform less well in retaining the lithium ions, making them unsuccessful substitutes. It seems that the three-dimensional structure of a rock salt crystal performs up to three times better than any layered oxide, which is where the excitement comes from.

Of course, if it were that simple we’d all be using three-times-more-powerful, half-price 18650s right now, which of course we aren’t. The challenge comes in making a rock salt cathode which both holds the lithium ions, and keeps that property reliably over the thousands of charge cycles needed for a real-world application. This one may yet be anther dollar on that metaphorical pile, but it just might give us the batteries we’ve been looking for.

Then again, when you’re looking at exciting battery chemistry, why limit yourself to lithium?