Large language models (LLMs) might be the most accessible and flexible technology we've ever had access to. By default, they're presented as chatbots—but that's just one way to interact with them. With the right prompts, you can transform an LLM into something that behaves like an entirely different app, complete with its own custom interface.

In an ideal world, the role of technology would be to make all of our lives easier. And although all the ads suddenly appearing in our smart TVs and gaming systems might make it seem otherwise, some technology can still improve our lives if we work hard at it. For [Cian], that meant training a neural network to read his gas meter so he wouldn’t have to do it himself.

The root issue here is twofold, first that [Cian]’s gas company hasn’t upgraded their own technology to modern, remote-readable meters, and second that the meter can’t be read by a gas employee because it’s hidden in the depths of [Cian]’s basement. This latter fact requires him to delve into Moria-like depths to get to the meter, so the solution here was to place a Raspberry Pi in this location instead. With a camera pointed at the meter, it’s not quite capable of discerning digits on its own so a neural network was trained in order to get accurate readings of the dial. And, finally, since the machine is networked already [Cian] set it up to automatically notify the gas company of its reading so he is now completely out of the loop.

For automating tedious tasks like these, the Raspberry Pi with something like OpenCV as a computer vision tool is a fairly mature platform for light machine learning duties like these. We’ve seen license plate readers as well as neighborhood traffic surveys built on these platforms to help automate human labor away, making our lives easier one single-board computer at a time.

The way to use a chatbot is given in the name. They are designed to be used by having two-way conversations with the LLM using natural language. You type something into the chatbot, and it replies. In some cases, continually typing stuff into a chatbot isn't the most efficient way to do things, so I set up a system that does it for me.

We all know that Google and other big players pick and choose what information people see, but we sometimes overlook it outside of the search and social media space. [Lauren Leek] decided to take a look at how Google Maps picks winners and losers in the restaurant scene in London.

Building a machine learning model to determine a new restaurant recommendation (as one does), [Leek] uncovered interesting, and perhaps concerning, elements of how Google Maps ranks restaurants. Broken down by relevance, proximity, and prominence, many new restaurants face the issue of not drawing traffic without reviews and vice-versa causing a vicious cycle. Relevance and proximity are fairly straightforward, but what goes into “prominence?”

[Leek] found that “it is not just what people think of a place – it is how often people interact with it, talk about it, and already recognise it.” This leads to chains and high foot traffic areas awash in reviews while more out-of-the-way places find it more difficult to draw traffic. Some of this is expected and would be happening even when word of mouth was the primary way to find out where to eat, but as with many things, the algorithm amplifies this, along with the undisclosed paid placement of restaurants in Maps results.

While still in its infancy, [Leek] built a public dashboard where people can sort restaurants in the city. The machine learning algorithm is designed to identify places that are hidden gems that punch above their Google Maps weight and may make you look like the trendy one (if you live in London).

Zooming out further, [Leek] found larger clusters that revealed restaurant “diversity, in other words, is not just about taste. It is about where families settled, which high streets remained affordable long enough for a second generation to open businesses, and which parts of the city experienced displacement before culinary ecosystems could mature.”

If you want to step outside the algorithm mayhem, how about a good old-fashioned Web Ring? We’ve also addressed what’s an AI versus an algorithm, and Cory Doctorow advised us on how to reverse course on the current wave of enshittification.

I used to spend far too much time building and debugging complex Excel formulas. Now, I can describe a problem to AI and get a working answer in seconds. But when I asked ChatGPT, Claude, and Gemini for the "best" Excel formula, they all gave me different answers.

The more comfortable I get using AI to help me code, the more curious I become about how the major platforms compare when they're given the exact same job. It's easy to ask Claude, ChatGPT, or Gemini to create a simple app and come away impressed when something functional appears a few seconds later. But that doesn't necessarily tell you whether the code is secure, well structured, or capable of handling situations beyond the most obvious use case.

If there are three things folks typically know about me, it's that I love Linux, I'm an avid reader and I have a bit of an obsession with modding Kindles and Fire Tablets. I would say, "Hey, I resemble that remark!" and then wait patiently while no one catches the reference. One Kindle has eluded me all these years, but I finally found one: a Kindle Fire 7 (2012). I tried to mod it, with a little help from Claude.

Are you deeply invested in the Google ecosystem? Do you actively use Google Keep, Tasks, Calendar, and Drive in your day-to-day life? Individually, each of these is an excellent tool—minimal by design but solid in functionality. The only problem is that these apps are mostly isolated from one another. But if you add Gemini as an orchestration layer, all of these tools can start talking to each other. That's exactly what I did, effectively turning Gemini into my personal project management system.

When I first installed a local LLM, I expected to use it the same way that I'd been using ChatGPT. It soon became apparent that on my modest hardware, this wasn't going to work. By changing the way I use my local LLMs, they've become much more useful.

Windows has a way of breaking in ways that feel almost personal. What makes these issues so draining isn't that the problems are complicated; it's that the built-in tools Microsoft gives you to fix them either don't work or don't even come close to addressing what's actually wrong. I started handing these problems to Claude instead, to see if it can do more than just free up space on your Windows PC. I was surprised at how good it was at finding a reasonable solution.

AI promises to make tedious work easier, but I wanted to know whether it could deliver in real Excel projects. Rather than asking Claude for formulas or snippets of code, I tested whether it could handle three types of automation: creating a workbook from scratch, building a reusable reporting system, and developing a tool that analyzes existing spreadsheets. The goal was to see how much of the work Claude could handle and where I would still need to step in.

Popular AI chatbots such as Claude, Gemini, and ChatGPT can analyze data from spreadsheets and other uploaded files. You can upload spreadsheets and ask them to create summaries, find patterns, and more. I wanted to use ChatGPT to analyze my spending to see if it could find ways to save money, but I didn't want to upload my personal information to the cloud. Using a PII-detection tool and a local LLM, I was able to strip away the personal information before I uploaded my files.

Speaking is much faster than typing, and while it’s an increasingly convenient way to interact with computers, it’s hardly private. Providing speech privacy in a way we haven’t seen before is this prototype tongue-reading system that uses machine learning and ultrasound to read tongue movements and turn them into decoded speech. Not only can a user speak without emitting a sound, since it doesn’t read sound waves it’s completely immune to noisy environments.

It turns out that tongue movements are a very rich source of information about speech, and an ultrasound probe under the chin takes very clear video of a tongue. With a dataset consisting of only around 50 hours of training data, the system has a 15.6% error rate and generalizes across different speakers (as long as they speak with similar accents).

That error rate may seem high at first glance, but keep in mind this is for a prototype system built in a month around a relatively small training dataset. All indications are that better results are just a matter of better training.

Probably the biggest drawback at the moment is the size of the ultrasound probe and the way it must be held under one’s chin like a contact microphone, but at the moment the probe is an off-the-shelf model that is hardly optimized for either size, weight, or wearability. If the system seems promising enough, a probe resembling an adhesive patch might even be possible.

It’s certainly a different approach from others we’ve seen in the past, including whispering while inhaling and reading lip and mouth movements.

AI hiring in India’s IT sector rose 16% in June, outpacing broader IT recruitment as companies shift toward specialized talent.

The post AI Jobs Rise 16% in India’s IT Sector as Overall Listings Fall appeared first on TechRepublic.