We present NN4SysBench, a benchmark suite for neural network verification that is composed of applications from the domain of computer systems. We call these neural networks for computer systems or NN4Sys. NN4Sys is booming: there are many proposals for using neural networks in computer systems--for example, databases, OSes, and networked systems--many of which are safety critical. Neural network verification is a technique to formally verify whether neural networks satisfy safety properties. We however observe that NN4Sys has some unique characteristics that today's verification tools overlook and have limited support. Therefore, this benchmark suite aims at bridging the gap between NN4Sys and the verification by using impactful NN4Sys applications as benchmarks to illustrate computer systems' unique challenges. We also build a compatible version of NN4SysBench, so that today's verifiers can also work on these benchmarks with approximately the same verification difficulties.

'Bigfooters' often employ credible scientific methods in their searches. Breakthroughs, discoveries, and DIY tips sent every weekday. Bigfoot remains firmly in the realm of cryptozoology, along with the likes of the Loch Ness monster . However, its pursuers often are not the stereotypical crackpots depicted across pop culture. According to two social scientists, they frequently rely on widely accepted, reliable methods and tools to search for the elusive Sasquatch.

The AI Industry's Scaling Obsession Is Headed for a Cliff Huge AI infrastructure deals assume that algorithms will keep improving with scale. A new study from MIT suggests the biggest and most computationally intensive AI models may soon offer diminishing returns compared to smaller models. By mapping scaling laws against continued improvements in model efficiency, the researchers found that it could become harder to wring leaps in performance from giant models whereas efficiency gains could make models running on more modest hardware increasingly capable over the next decade. "In the next five to 10 years, things are very likely to start narrowing," says Neil Thompson, a computer scientist and professor at MIT involved in the study. Leaps in efficiency, like those seen with DeepSeek's remarkably low-cost model in January, have already served as a reality check for the AI industry, which is accustomed to burning massive amounts of compute.

Google had proposed less drastic solutions, such as limiting its revenue-sharing agreements with firms like Apple to make its search engine the default on their devices and browsers. On Tuesday, the company indicated that it viewed the ruling as a victory, and said the rise of artificial intelligence (AI) probably contributed to the outcome. "Today's decision recognizes how much the industry has changed through the advent of AI, which is giving people so many more ways to find information," Google said in a statement after the ruling. "This underlines what we've been saying since this case was filed in 2020: Competition is intense and people can easily choose the services they want," the statement continued. The tech giant had denied wrongdoing since charges were first filed against it in 2020, saying its market dominance is because its search engine is a superior product to others and consumers simply prefer it to others.

We present NN4SysBench, a benchmark suite for neural network verification that is composed of applications from the domain of computer systems. We call these neural networks for computer systems or NN4Sys. NN4Sys is booming: there are many proposals for using neural networks in computer systems--for example, databases, OSes, and networked systems--many of which are safety critical. Neural network verification is a technique to formally verify whether neural networks satisfy safety properties. We however observe that NN4Sys has some unique characteristics that today's verification tools overlook and have limited support.

Breakthroughs, discoveries, and DIY tips sent every weekday. A truly sustainable future requires solar power, but trying to consistently maximize the energy harvested by panel arrays remains one of the industry's biggest challenges. Unlike fossil fuels, solar power yields are dictated by the complex interplay of weather and atmospheric variables, as well as the sun's own activity. This means it's basically impossible to craft a universal prediction model, so localized solar forecast systems are a necessity. While machine learning technology has significantly improved today's forecast models, there is still a lot of room for improvement.

In a new study published this morning, and shared exclusively with TIME ahead of its release, we got the first hard numbers on how experts think the risk of a new pandemic might have increased thanks to AI. The Forecasting Research Institute polled experts earlier this year, asking them how likely a human-caused pandemic might be--and how likely it might become if humans had access to AI that could reliably give advice on how to build a bioweapon. What they found -- Experts, who were polled between December and February, put the risk of a human-caused pandemic at 0.3% per year. But, they said, that risk would jump fivefold, to 1.5% per year, if AI were able to provide human-level virology advice. You can guess where this is going -- Then, in April, the researchers tested today's AI tools on a new virology troubleshooting benchmark.

Crucially, the surveyors then asked another question: how much would that risk increase if AI tools could match the performance of a team of experts on a difficult virology troubleshooting test? If AI could do that, the average expert said, then the annual risk would jump to 1.5%--a fivefold increase. What the forecasters didn't know was that Donoughe, a research scientist at the pandemic prevention nonprofit SecureBio, was testing AI systems for that very capability. In April, Donoughe's team revealed the results of those tests: today's top AI systems can outperform PhD-level virologists at a difficult troubleshooting test. In other words, AI can now do the very thing that forecasters warned would increase the risk of a human-caused pandemic fivefold.

Why is it that we still get a tiny thrill from checking the mailbox each day? Rationally, we know what's in there: bills we don't want, catalogs we never ordered, and that bulky Valpak stuffed with coupons we'll never use. But somehow, despite the noise, there's a quiet hope we might find something meaningful. And every once in a while, we do. In a society obsessed with social media, texts, AI, speed and automation, the handwritten thank-you note has become an endangered species.

When Hans Hartman, a civil engineer, attempted to film the ocean depths in 1917, he pioneered what would become the first deep-sea ROV, or remotely operated vehicle. During an era of silent movies and wartime U-boats, Hartman's ambitious invention--a 1,500-pound electric, submarine camera--could be lowered to a depth of 1,000 feet to capture images of sunken ships and submerged treasures. Despite featuring a gyroscope for stability, a motorized propeller for controlled rotation, and an innovative light source, as Popular Science explained, it had a serious limitation: The hulking apparatus had to be operated blindly from a ship's deck, which meant it was impossible for the camera's operator to see what they were filming until the footage was viewed later. In 1925, Popular Science showcased his next breakthrough--a cylindrical apparatus (seen above) attached to a ship by a cable, housing a submersible, motor-driven camera, as well as enough room for a person who could control the camera, or communicate with crew members nearby to aid with various underwater missions, such as salvaging. The vertical, tin-can-like submarine, equipped with porthole windows and a powerful spotlight, allowed "the operator to go down into the water with a camera and photograph whatever he chooses."