Eliana Willis

Elyse Betters Picaro / ZDNETAs part of my AI coding evaluations, I run a standardized series of four programming tests against each AI. These tests are designed to determine how well a given AI can help you program. This is kind of useful, especially if you’re counting on the AI to help you produce code. The last thing you want is for an AI helper to introduce more bugs into your work output, right?Some time ago, a reader reached out to me and asked why I keep using the same tests. He reasoned that the AIs might succeed if they were given different challenges.Also: Want free AI training from Microsoft? You can sign up for its AI Skills Fest nowThis is a fair question, but my answer is also fair. These are super-simple tests. I’m using PHP and JavaScript, which are not exactly challenging languages, and I’m running some scripting queries through the AIs. By using exactly the same tests, we’re able to compare performance directly. One is a request to write a simple WordPress plugin, one is to rewrite a string function, one asks for help finding a bug I originally had difficulty finding on my own, and the final one uses a few programming tools to get data back from Chrome. But it’s also like teaching someone to drive. If they can’t get out of the driveway, you’re not going to set them loose in a fast car on a crowded highway. To date, only ChatGPT’s GPT-4 (and above) LLM has passed them all. Yes, Perplexity Pro also passed all the tests, but that’s because Perplexity Pro runs the GPT-4 series LLM. Oddly enough, Microsoft Copilot, which also runs ChatGPT’s LLM, failed all the tests. Also: The best AI for coding (and what not to use)Google’s Gemini didn’t do much better. When I tested Bard (the early name for Gemini), it failed most of the tests (twice). Last year, when I ran the $20-per-month Gemini Advanced through my tests, it failed three of the four tests.But now, Google is back with Gemini Pro 2.5. What caught our eyes here at ZDNET was that Gemini Pro 2.5 is available for free, to everyone. No $20 per month surcharge. While Google was clear that the free access was subject to rate limits, I don’t think any of us realized it would throttle us after two prompts, which is what happened to me during testing. It’s possible that Gemini Pro 2.5 is not counting prompt requests for rate limiting but basing its throttling on the scope of the work being requested. My first two prompts asked Gemini Pro 2.5 to write a full WordPress plugin and fix some code, so I may have used up the limits faster than you would if you used it to ask a simple question. Even so, it took me a few days to run these tests. To my considerable surprise, it was very much worth the wait. Test 1: Write a simple WordPress pluginWow. Well, this is certainly a far cry from how Bard failed twice and Gemini Advanced failed back in February 2024. Quite simply, Gemini Pro 2.5 aced this test right out of the gate. Also: I asked ChatGPT to write a WordPress plugin I needed. It did it in less than 5 minutesThe challenge is to write a simple WordPress plugin that provides a simple user interface. It randomizes the input lines and distributes (not removes) duplicates so they’re not next to each other. Last time, Gemini Advanced did not write a back-end dashboard interface but instead required a shortcode that needed to be placed in the body text of a public-facing page. Gemini Advanced did create a basic user interface, but that time clicking the button resulted in no action whatsoever. I gave it a few alternative prompts, and it still failed. But this time, Gemini Pro 2.5 gave me a solid UI, and the code actually ran and did what it was supposed to. More

<!–> ZDNET’s key takeaways The Plantaform Rejuvenate is a smart indoor garden available for $540. It’s an all-in-one garden structure that only requires power for the grow lights and for you to add water and the included fertilizer when it runs low; thankfully, the app gives you notifications and detailed instructions. Unfortunately, you can’t easily […] More

Valeriia Mitriakova/Getty Images Looking for advice on how to protect your home and office from cyberattacks? A good place to start is with the people who do this work every day on behalf of the US government. The folks at the National Institute of Standards and Technology (NIST) have created a simple Cybersecurity Basics page […] More

Elyse Betters Picaro/ZDNETI have spent a lot of time writing about how battery wear is a fact of life, and the more a battery is used, the more it will wear. It is a consumable item, and it will wear. Also: 12 Android phone settings you should change to dramatically increase battery lifeBut there are also things that we can do to prevent battery wear. A research paper led by Jihyun Hong at Postech and Jongsoon Kim at Sungkyunkwan University on EV (electric vehicle) batteries uncovers a new enemy — too much discharge. Discharging EV batteries harms themWithout getting too deep into the chemistry and physics of battery wear, the study discusses a newly identified mechanism of oxygen loss in layered oxide cathodes used in lithium-ion batteries, specifically during the discharge process at voltages below 3.0V. Because of this additional wear, the study emphasizes the importance of carefully setting DCOVs (discharge cut-off voltages) to slow down degradation and improve battery longevity. Basically, excessively discharging batteries harms them. What about the batteries in our devices?While the study is limited to EV batteries, can we assume that this chemistry applies to the lithium-ion batteries found in smartphones, tablets, laptops, and other similar devices? Yes and no. Also: iOS 18.4 update draining your iPhone’s battery? Try these 6 fixesTo strike a good balance between battery runtime and battery life, the typical point at which the battery management controller (a circuit that controls the charge and discharge of rechargeable batteries) sets the DCOV cutoff is normally around 2.8 to 3.0V. So, batteries in all sorts of devices dip below that 3.0V damaging discharge point mentioned in the study. But not all batteries will go that low, and I have found that higher-end devices and devices built to better handle temperature extremes have more conservative battery management and might cut off at 3.3V. For reference, iPhone batteries that I have tested appear to have DCOVs in the range of 3.1 to 3.3V and do not normally go below the 3.0V threshold, so they should not be subject to the damage highlighted by the study. More

<!–> ZDNET’s key takeaways The Woburn 3 is the most expensive home audio speaker from Marshall. It has fantastic sound quality, strong bass, and clear mids. However, the system only supports the SBC codec. –> The Marshall Woburn 3<!–> commands a premium price, and while it’s not the best value on specs alone, its rich, […] More

Prakhar Khanna/ZDNETSamsung’s One UI 7 is my favorite Android skin right now. It is fast, responsive, and intuitive. But nothing comes fine-tuned to your experience straight out of the box. You need to personalize your smartphone to make it more appealing. I change almost a dozen settings on every Samsung Galaxy phone to best suit my needs, and I believe these will elevate your user experience, too. Also: The best Samsung phones to buyFrom setting the highest available screen resolution to more privacy-focused features, here are 11 Galaxy phone settings that I recommend changing to enhance your Galaxy phone experience. Please note that some settings might be phone-specific.1. Turn off pop-up notifications More

<!–> ZDNET’s key takeaways The Tessan 65W GaN Universal Travel Adapter retails for $42. It’s the perfect size, weight, and power output for traveling. It doesn’t convert mains AC voltage, and the USB ports on the bottom can be tricky to use. –> Gone are the days of packing multiple chargers with different connectors when […] More

<!–> ZDNET’s key takeaways Mullvad VPN has a unique fixed-pricing system for short- and long-term subscribers. The VPN is optimized to provide strong protection and achieves top speeds ideal for high-bandwidth browsing and streaming. Mullvad lacks native apps for some devices, has a small server count, and limits simultaneous connections. –> Mullvad is a VPN […] More