Compromised dYdX npm and PyPI packages delivered wallet-stealing malware and a RAT via poisoned updates in a software supply chain attack.

“AI is not going to take your job. The person who uses AI is going to take your job.” This is an idea that has become a refrain for, among others, Nvidia CEO Jensen Huang, who has publicly made the prediction several times since October 2023. Meanwhile, other AI developers and stalwarts say the technology will eliminate countless entry-level jobs. These predictions have come at the same time as reports of layoffs at companies including IBM and Amazon, causing anxiety for tech workers—especially those starting their careers, whose responsibilities are often more easily automated. Early reports have borne out some of these anxieties in employment data. For example, entry-level hiring at the 15 biggest tech firms fell 25 percent from 2023 to 2024, according to a report from SignalFire last May. Still, it’s unclear what the long-term effects will be, or whether hiring cuts are actually a result of AI. For instance, while Meta laid off 600 employees from its AI division in October (and continued hiring other AI researchers), OpenAI began hiring junior software engineers. In 2026, all new graduates may face a tougher job market in the United States. Employers’ rating of the job market for college graduates is now at its most pessimistic since 2020, according to data from the National Association of Colleges and Employers (NACE) Job Outlook 2026 survey. However, 49 percent of respondents still consider the job market “good” or “very good.” So, what does the rise of generative AI mean for early-career engineers? “This is a tectonic shift,” says Hugo Malan, president of the science, engineering, technology and telecom reporting unit within the staffing agency Kelly Services. AI agents aren’t poised to replace workers one-to-one, though. Instead, there will be a realignment of which jobs are needed, and what those roles look like.How Jobs Are Changing When publicly available AI tools first arrived, Malan says the expectation was that jobs like call-center roles would be most vulnerable. “But what nobody predicted was that the biggest impact by far would be on programmers,” a trend he attributes to the relatively solitary and highly structured nature of the work. He notes that, while other economic conditions also factor into the job market, the pace of programmer employment decline has accelerated since generative AI came on the scene. In the United States, overall programmer employment fell a dramatic 27.5 percent between 2023 and 2025, according to data from the U.S. Bureau of Labor and Statistics. But employment for software developers—a distinct, more design-oriented position in the government data—only fell 0.3 percent in the same period. At the same time, some positions, such as information security analyst and AI engineer are actually growing, Malan says. “There’s been this pretty dramatic readjustment of the job landscape, even with as narrow a field as IT. Within IT, some jobs have exploded, like InfoSec analysts have grown in double digits, whereas programmers declined double digits” over the past few years, he says. (Eventually, Malan says he expects generative AI to affect all intellectual work.) Job responsibilities also appear to be changing. For recent graduates pursuing roles labeled as software-engineering jobs, “they’re not necessarily just coding,” says Jamie Grant, senior associate director for the engineering team at the University of Pennsylvania’s career services. “There tends to be so much higher-order thinking and knowledge of the software-development life cycle,” as well as a need to work with other parties, such as understanding user and client demands, she says.Using AI to Your Advantage In her work advising Penn students, Grant hears concerns about AI’s effects on the job market from many engineering students and their parents. But during conversations with them, she says she tries to maintain an ethos of “we can make this work for us, not against us.” According to a report from the Stanford Digital Economy Lab, jobs involving tasks that could be automated with AI appear to be more susceptible to early-career employment dips than those where AI augments an employee’s ability to perform their job. The NACE data supports this: Sixty-one percent of employers say they are not replacing entry-level jobs with AI, while 41 percent are discussing or planning to augment these jobs with AI within the next five years. Over the past few years, computer-programmer employment in the United States has dropped sharply—but overall employment in the computing industry hasn’t seen the same decline. “Think about an exoskeleton that you could wear that allows you to lift 1,000 pounds,” Grant says. “AI should be, just as the people at Stanford say, an augmentation to your work, to your higher-order critical-thinking skills.” That being said, she advises students to be cautious of the risks, such as sharing sensitive or proprietary information with a chatbot. At this point, Grant thinks proficiency with AI tools is an unwritten expectation of many employers. But students and early-career workers should also recognize where AI can’t help. “AI can’t necessarily be with you in that moment of negotiation or of client-relationship development,” she says. “You still need to be able to perform at your highest level of capabilities.” And foundational skills like problem solving and communication are consistently prioritized by employers.How Education Needs to Change With AI tools performing more of the “grunt work” that has served as a training ground for early-career workers, expectations for recent graduates are high. In the past, junior engineers have cultivated proficiency while doing simpler, more task-oriented work. “But if all of those are going to get taken over, you need to slot in at a higher level almost from day one,” Malan says. This leaves recent graduates in a difficult spot. To help students prepare, the education system will likely need to change, for instance by encouraging students to become proficient using AI and take on more hands-on, experiential learning. Today’s employers are looking for demonstrated skills, says Grant. “If you’re just going to class and doing projects and maybe getting a great GPA, that’s amazing. But you also need to be applying what you’re learning,” she says. Industry experience and demonstrated proficiencies are among the top factors considered by employers surveyed in NACE’s Job Outlook 2026. One solution may even lie in entirely different educational models, like apprenticeship. “Often, students in a more traditional computer-software degree program get a lot of theoretical knowledge,” but they may not have much experience building software on a team, says Mike Roberts, founder and CEO of the nonprofit Creating Coding Careers. Recent graduates may not be ready to ship code on day one—but AI can. Apprenticeship allows students to learn on the job in a structured program, and helps “to much more effectively close the experience gap,” Roberts says. Training the next generation of humans might also better serve the long-term interests of employers, he says. In today’s software engineering, many companies tend to be short-sighted in their hiring, thinking more of the next quarter than four or five years down the line. But “if you don’t train new early entrants into the market, you will eventually have no more people becoming mid-levels,” says Roberts. “It’s very myopic.” Also, AI can help ramp up new employees faster than ever. “I find it an exciting time, because it’s never been faster to build high-quality software,” Roberts says. “But it’s weird that folks are not seeing the virtue of continuing to invest in humans.”

State-backed hackers from China, Russia, Iran, and North Korea target defense contractors using espionage, malware, hiring scams, and edge exploits.

This year, AI continued looming large in the software world. But more than before, people are wrestling with both its amazing capabilities and its striking shortcomings. New research has found that AI agents are doubling the length of task they can do every seven months—an astounding rate of exponential growth. But the quality of their work still suffers, clocking in at about a 50 percent success rate on the hardest tasks. Chatbots are assisting coders and even coding autonomously, but this may not help solve the biggest and costliest IT failures, which stem from managerial failures that have remained constant for the past twenty years or more. AI’s energy demands continue to be a major concern. To try to alleviate the situation, a startup is working on cutting the heat produced in computation by making computing reversible. Another is building a computer of actual human brain cells, capable of running tests on drug candidates. And some are even considering sending data centers to the moon.1. The Top Programming Languages 2025 iStock While the rankings of software languages this year were rather predictable—yes, Python is still number one—the future of software engineering is as uncertain as can be. With AI chatbots assisting many with coding tasks, or just coding themselves, it is becoming increasingly different to gather reliable data on what software engineers are working on day-to-day. People no longer post their questions on StackExchange or a similar site—they simply ask a chatbot. This year’s top programming languages list does its best to work with this limited data, but it also poses a question: In a world where AI writes much of our code, how will programming languages change? Will we even need them, or will the AI simply bust out optimized assembly code, without the need for abstraction?2. How IT Managers Fail Software Projects Eddie Guy Robert Charette, lifelong technologist and frequent IEEE Spectrum contributor, wrote back in 2005 about all the known, preventable reasons software projects end in disaster. Twenty years later, nothing has changed—except for trillions of more dollars lost on software failures. In this over 3,500-word screed, Charette recounts multiple case studies, backed up by statistics, recounting the paltry state of IT management as it is—still—done today. And to top it off, he explains why AI will not come to the rescue.3. Human Brain Cells on a Chip For Sale Cortical Labs Australian startup Cortical Labs announced that they are selling a biocomputer powered by 800,000 living human neurons on a silicon chip. For US $35,000, you get what amounts to a mini-brain in a box that can learn, adapt, and respond to stimuli in real time. The company already proved the concept by teaching lab-grown brain cells to play Pong (they often beat standard AI algorithms at learning efficiency). But the real application is drug discovery. This “little brain in a vat,” as one scientist put it, lets researchers test whether experimental drugs restore function to impaired neural cultures.4. Large Language Models Are Improving Exponentially Model Evaluation & Threat Research It’s difficult to agree on a consistent way to evaluate how well large language models (LLMs) are performing. The nonprofit research organization Model Evaluation & Threat Research (METR) proposed an intuitive metric—tracking how long it would take a human to do the tasks AI can do. By this metric, LLM capabilities are doubling every seven months. If the trend continues, by 2030, the most advanced models could quickly handle tasks that currently take humans a full month of work. But, for now, the AI doesn’t always do a good job—the chance the work will be done correctly, for the longest and most challenging tasks, is about 50 percent. So the question is: How useful is a fast, cheap employee that produces garbage about half the time?5. Reversible Computing Escapes the Lab in 2025 Edmon de Haro There is a surprising principle that connects all software to the underlying physics of hardware: Erasing a bit of information in a computer necessarily costs energy, usually lost as heat. The only way to avoid losing this energy is to never erase information. This is the basic idea behind reversible computing—an approach that has remained in the academic sphere until this year. After three decades of academic research, reversible computing is finally going commercial with startup Vaire Computing. Vaire’s first prototype chip recovers energy in an arithmetic circuit. The team claims that with their approach, they could eventually deliver a 4,000x energy efficiency improvement over conventional chips. The catch is that this requires new gate architectures, new design tools, and integrating MEMS resonators on chip. But with a prototype already in the works, reversible computing has graduated from “interesting theory” to “we’re actually building this.”6. Airbnb’s Dying Software Gets a Second Life Nicole Millman Apache Airflow—the open-source workflow orchestration software originally built by Airbnb—was basically dead by 2019. Then, one enthusiastic open-source contributor stumbled across it while working in IoT and thought “this is too good to die.” He rallied the community, and by late 2020 they shipped Airflow 2.0. Now the project is thriving. It boasts 35 to 40 million downloads per month and over 3,000 contributors worldwide. And Airflow 3.0 launched with a modular architecture that can run anywhere.7. The Doctor Will See Your Electronic Health Records Now iStock/IEEE Spectrum In 2004, President Bush set a goal for the United States to transition to electronic health records (HER) by 2014, promising transformed healthcare and huge cost savings. Twenty years and over $100 billion later, we’ve achieved widespread EHR adoption—and created a different nightmare. Doctors now spend on average 4.5 hours per day staring at screens instead of looking at patients, and clicking through poorly designed software systems. The rush to adopt EHRs before they were ready meant ignoring warnings about systems engineering, interoperability, and cybersecurity. Now we’re stuck with fragmented systems that don’t talk to each other (the average hospital uses 10 different EHR vendors internally) and physicians experiencing record burnout levels. And to top it off, data breaches have exposed 520 million records since 2009. Healthcare costs haven’t bent downward as promised—they’ve hit $4.8 trillion, or 17.6 percent of GDP. The irony? AI scribes are now being developed to solve the problems that the last generation of technology created, allowing doctors to actually look at patients again instead of their keyboards.8. Is it Lunacy to Put a Data Center On the Moon? Intuitive Machines Whether space-based or moon-based data centers are a promising avenue or a fever dream is the subject of much debate. Nevertheless, earlier this year company Lonestar Data Holdings sent a 1-kilogram, 8-terabyte mini data center to the moon aboard an Intuitive Machines lander. The goal is to protect sensitive data from Earthly disasters (undersea cable cuts, hurricanes, wars) and exploit a loophole in data sovereignty laws—because the moon isn’t subject to any nation’s jurisdiction, you can host black boxes under any country’s law you want.The lunar surface offers permanently shadowed craters at -173 °C, which may make cooling easier (although the lack of atmosphere makes thermal radiation challenging). Nearby sunlit peaks would provide solar power. Governments are interested—Florida and the Isle of Man are already storing data there. But the problems are obvious: 1.4-second latency rules out real-time applications, fixing anything requires a moon mission, and bandwidth is terrible.

Discover how Samsung Knox enhances mobile network security with granular controls, Zero Trust principles & seamless integration for a safer enterprise

After years of hype about generative AI increasing productivity and making lives easier, 2025 was the year erotic chatbots defined AI’s narrative.

Suspected Russian actor deploys CANFAIL malware via phishing, targeting Ukrainian defense, energy, and aid sectors using LLM-assisted lures.

Asian state-linked hackers breached 70 entities, used phishing, N-day exploits, and rootkits for global espionage.

Meta says the volume of content being generated via its AI app has increased significantly.

The option gives users the capacity to change what they see in-feed.

YouTube is making a bigger push into CTV subscriptions.

AI will compose a note and humans will be able to refine it.

Dating apps and AI companies have been touting bot wingmen for months. But the future might just be good old-fashioned meet-cutes.

YouTube's latest report looks at the rising engagement with NFL content in the app and not just on the day of the big game. 

CISA orders federal agencies to inventory, upgrade, and remove unsupported edge devices within 12–18 months to reduce cyber-espionage risk.

Achieve reliable hermetic sealing for millimeter-scale microbatteries using dual-seal epoxy adhesive methods that maximize energy density while preventing electrolyte leakage and moisture ingress. What Attendees will Learn“Seal smart, not complex” -- Dual-seal approach combines epoxy adhesives with gaskets for optimal hermeticity.2mm breakthrough -- Successfully demonstrated microbatteries operating at 120°C with 22-hour continuous performance.Energy density maximized -- Surface-area-to-volume optimization maintains high Wh/L and Wh/kg ratios.Proven materials -- Epoxy adhesives with Kapton/neoprene gaskets deliver chemical resistance and low permeability.Download this free whitepaper now!

China-linked DKnife framework uses router-level AitM implants for traffic hijacking, credential theft, and malware delivery targeting edge devices.

There is a misconception among some that IEEE accredits engineering programs in the United States, but that is the responsibility of ABET. The global, nonprofit agency accredits academic programs leading to degrees in specific disciplines. It does not accredit the institution, school, college, department, facilities, courses, or faculty—only specific academic programs. IEEE and other professional organizations help evaluate programs for ABET, but they do not have the authority to accredit programs themselves. There are 34 organizations, including IEEE, that are ABET members and assist the nonprofit with setting policy, developing strategy, and conducting accreditation activities worldwide. IEEE’s partnership with ABET began in 1932 with an IEEE predecessor society, the American Institute of Electrical Engineers. AIEE, along with six other engineering organizations, founded the Engineers’ Council for Professional Development, which evolved into ABET. Today more than 4,770 programs at 930 colleges and universities in 42 countries and regions are accredited by ABET. IEEE serves as the lead society for 877 of the programs.The evaluation structure IEEE and the other professional societies provide ABET with volunteer program evaluators. The evaluators are assigned to visit educational institutions that seek accreditation. The evaluators provide assessments based on specific criteria developed in collaboration with ABET and the societies. Evaluators must have experience in industry, academia, or government. Once IEEE volunteers have five or more years of experience serving as a program evaluator, they may be nominated to serve on the IEEE Committee on Engineering Technology Accreditation Activities (CETAA) or the IEEE Committee on Engineering Accreditation Activities (CEAA). IEEE Educational Activities supports these committees, and all of IEEE’s responsibilities with ABET. After spending two to four years on one of the committees, a volunteer may be nominated to serve on one of ABET’s commissions, giving them the opportunity to serve as a team chair.“Years of developing and leading undergraduate electrical and computer engineering programs, including preparing for ABET accreditation reviews, led me to believe that becoming an ABET program evaluator would be a great way to learn new ways to improve the quality of our own programs while also assisting others.” —Victor Nelson Each accreditation visit is led by a team chair, who is the primary point of contact for an institution whose programs are being evaluated. The term for the position is typically five years, with the option to serve a three-year term on the executive committee of ABET’s Engineering Accreditation Commission (EAC) and Engineering Technology Accreditation Commission (ETAC). There are about 380 IEEE evaluators, 26 of whom are currently serving as IEEE commissioners on ABET’s EAC and ETAC.Become a program evaluator The CETAA and CEAA choose new program evaluators annually. The number of applicants selected varies from year to year to ensure there are enough evaluators available for future accreditation visits. For the 2025–2026 academic year, IEEE received 126 applications for the EAC and the ETAC. Applications were received from 24 countries, with 105 from academia and 21 from industry or government. Victor Nelson, an IEEE life senior member, has been a program evaluator for more than two decades. He is a professor emeritus of electrical and computer engineering at the Ginn College of Engineering at Auburn University, in Alabama. Nelson’s service as an evaluator was recognized with the 2024 IEEE EAB Meritorious Achievement Award in Accreditation Activities. The award was established in 1984 to recognize “efforts to foster the maintenance and improvement of education through the process of accreditation.” “Years of developing and leading undergraduate electrical and computer engineering programs, including preparing for ABET accreditation reviews, led me to believe that becoming an ABET program evaluator would be a great way to learn new ways to improve the quality of our own programs while also assisting others,” Nelson says. “My 23 years of conducting ABET reviews have more than confirmed that belief and have been incredibly rewarding. “As a program evaluator, I have had the privilege of studying and visiting programs around the world, and I never fail to be impressed with and learn from the efforts and achievements of the many students and faculty in those programs. “I always feel a sense of pride in being able to make modest contributions to improving the quality of engineering education through the accreditation review process.” To learn more about why accreditation matters, read “How IEEE Ensures Quality in Engineering Education,” published last year in The Institute.To become an IEEE program evaluator, apply here.

Germany’s BSI and BfV warn of state-linked Signal phishing using fake support chats, PIN theft, and device linking to access sensitive accounts.

US support for nuclear energy is soaring. Meanwhile, coal plants are on their way out and electricity-sucking data centers are meeting huge pushback. Welcome to the next front in the energy battle.

Free tools to help you grow your brand on social media, whether you're just starting out or already established. A little growth never hurt nobody!

OpenClaw integrates VirusTotal Code Insight scanning for ClawHub skills following reports of malicious plugins, prompt injection & exposed instances.

Google's AI is now even smarter, and more versatile.

CISA orders federal agencies to inventory, upgrade, and remove unsupported edge devices within 12–18 months to reduce cyber-espionage risk.

Usually, I start off these annual highlights posts by saying that it was the best year ever for robotics. But this year, I’m not so sure. At the end of 2024, it really seemed like AI and humanoid robots were poised to make a transformative amount of progress towards some sort of practicality. While it’s certainly true that progress has been made, it’s hard to rationalize what’s actually happened in 2025 with the amount of money and hype that has suffused robotics over the course of the year. And for better or worse, humanoids are overshadowing everything else, raising questions about what will happen if the companies building them ultimately do not succeed. We’ll be going into 2026 with both optimism and skepticism, and we’ll keep doing what we always do: talking to the experts, asking as many hard questions as we can, and making sure to share all the cool robots, even (or especially) the ones that you won’t see anywhere else. So thanks for reading, and to all you awesome robotics folks out there, thanks for sharing your work with us! IEEE Spectrum has a bunch of exciting new stuff planned for 2026, and as we close out 2025, here’s a quick look back at some of our best robotics stories of the year.1. Reality Is Ruining the Humanoid Robot Hype Eddie Guy Humanoid robots are hard, and they’re hard in lots of different ways. For some of those ways, we at least understand the problems and what the solutions will likely involve. But there are other problems that have no clear solutions, and most humanoid companies, especially the well-funded ones, seem quite happy to wave those problems away while continuing to raise extraordinary amounts of money. We’re going to keep calling this out whenever we see it, and expect even more skepticism in 2026.2. Exploit Allows for Takeover of Fleets of Unitree Robots CFOTO/Future Publishing/Getty Images Security is one of those pesky little things that is super important in robotics but that early-stage robotics companies typically treat as an afterthought because it doesn’t drive investment. Chinese manufacturer Unitree is really the one company with humanoids robots that are available enough and affordable enough for clever people to perform a security audit on them. And to the surprise of no one, Unitree’s robots had serious vulnerabilities, which as of yet have not all been fixed.3.Amazon’s Vulcan Robots Now Stow Items Faster Than Humans Amazon The thing I appreciate about the folks at Amazon Robotics is how relentless they are in finding creative solutions for problems at scale. Amazon simply doesn’t have time to mess around, and they’re designing robots to do what robots do best: specific repetitive tasks in structured environments. In the current climate of robotics hype, it’s refreshing, honestly.4. Large Behavior Models Are Helping Atlas Get to Work Boston Dynamics Did I mention that humanoids robots are hard? Whether or not anyone can deliver on the promises being made about them (and personally, I’m leaning more and more strongly towards not), progress is being made towards humanoids that are much more capable and versatile than they ever have been. The collaboration between Toyota Research and Boston Dynamics on large behavior models is just one example of how far we’ve come, and how far we still have to go.5. iRobot’s Cofounder Weighs In on Company’s Bankruptcy Lindsey Nicholson/Universal Images Group/Getty Images My least favorite story to write happened right at the end of the year—iRobot filed for bankruptcy. This was not a total surprise; regulators shutting down an acquisition by Amazon in 2024 essentially gutted the company, and it’s been limping along towards the inevitable since then. Right after the news was announced, we spoke with iRobot co-founder and ex-CEO Colin Angle, who had plenty to share about where things went wrong, and what we can learn from it.6. How Dairy Robots Are Changing Work for Cows (and Farmers) Evan Ackerman My favorite story of 2025 was as much about cows as it was about robots. I was astonished to learn just how many fully autonomous robots are hard at work on dairy farms around the world, and utterly delighted to also learn that these robots are actively improving the lives of both dairy farmers and the dairy cows themselves. Dairy farming is endless hard work, but thanks to these robots, small family farms are able to keep themselves sustainable (and sane). Everybody wins, thanks to the robots.