Committee

“I think I have good news about the nature of neural networks.” With those simple words of optimism, Nick Cammarata, a researcher at the AI startup Goodfire, kicked off a 26,000-word blog post that has knocked the AI world on its head, sparking wild speculation as well as cautious (and not-so-cautious) celebration. Cammarata’s claim is that LLMs might in fact be far easier to understand—and thus to monitor and control—than people previously thought. If true (and we’ll come back to that), it’s a huge deal. After a summer filled with revelations that swarms of agents built by top firms like OpenAI and Anthropic have been breaking their containment and causing havoc on the public internet—often while those companies weren’t aware of what their agents were up to—the AI industry is desperate to get a better handle on the technology it has built.   That’s one reason the blog post landed with such force. “I think this may be remembered as a major moment in scientific history,” one AI researcher posted on X: “I feel like my understanding of what a neural net is has been catapulted into the future by five years or something.” Another called it “the most important AI paper of the year.” Not everyone is convinced, however. What Cammarata has shared is little more than a hunch, says Chris Potts at Stanford University, who leads a team that is trying to understand how LLMs work. “As far as I can tell, nothing about this blog post makes the problems any easier,” he says. “It would not have occurred to me to say this at all, but very prominent people on social media seem to believe that it is an all-encompassing breakthrough.” I talked to Cammarata the day after his post blew up. He says he was surprised by the response: “I didn’t expect people to update [their beliefs about AI] quite as much as they did.”  “I just really enjoy looking at neural networks,” he says. “Honestly, I really like doing this stuff. And after looking a lot, I have a hopeful story.” Knotted networks It has long been accepted that the mechanisms inside neural networks, the software that underpins most AI models, are very hard—perhaps impossible—to unpick fully. That’s because when the networks are trained, they appear to take on weird, tangled structures that make no sense to a human. Researchers like to say today’s AI is grown like a garden, not built like a bridge. Cammarata has done more than most to establish that view. He previously worked at OpenAI, where he helped pioneer techniques that allowed researchers to peer inside models, including tools that can probe individual neurons to see what they represent. It’s a little like how neuroscientists use MRI to study brains. (MIT Technology Review chose this approach, known as mechanistic interpretability, as one of its 10 hottest technologies of 2025.)   Back in 2020, Cammarata and his colleagues were studying a small image-recognition model called Inception v1. When they looked at its neurons, it seemed to be using them to capture multiple things at once. For example, they found that one neuron responded to both images of cars and images of cats. The researchers concluded that the model was getting at least some of its neurons to multitask, perhaps so that it could fit in more data. Looking at other models appeared to back this up. The phenomenon became known as superposition: Models folded unrelated concepts into single neurons. The upshot was clear: When you looked inside a model, what you saw was a vast, tangled knot. Most mechanistic interpretability research has therefore focused on ways to untangle that knot. But despite a few breakthroughs, progress has been slow. Today’s models, such as the latest LLMs, are so large and complex that researchers can make sense of only tiny pieces at a time. Some leading figures in the field doubt if it will ever be possible to understand an LLM in fine-grained detail. Cammarata was one of them. “I was very pessimistic,” he says. But then he took the trouble to really look. Nothing but neurons At Goodfire, Cammarata spends nearly all of his time peering inside neural networks. He has built new tools and deploys teams of AI agents to help him make sense of what he sees. “I spent like, I don’t know, 10 hours a day, seven days a week, for most of the last year just looking at neurons,” he says. What he claims to have realized is that there is a kind of logic to neural networks after all, even if they seem to make no sense at first. “We were looking at it wrong,” he says. “I just think you want to try slightly harder; you don’t want to give up too quickly.” Cammarata almost makes it sound like a conversion of faith. Those early experiments with models such as Inception v1, which suggested that neural networks were tangled up, fostered a kind of confirmation bias. When researchers looked at a new model, they expected to be flummoxed, he says. “Every time I couldn’t understand something, I was like, ‘Wow, this untangling process is even more important than I thought, because I can’t make any progress without it.’” But the more Cammarata looked at neurons, he says, the more things started to fall into place. “Not all of them are flawless, but I expected nothing to be legible, or very little to be legible,” he says. “And actually, I was able to, like, map out whole circuitry.” Back to cars and cats Cammarata took his new approach—and his new agents—and went back to Inception v1. “I’d studied that for probably thousands of hours,” he says. But with fresh eyes, Cammarata found things that he now thinks they got wrong the first time around. Take the car-and-cat neuron. Rather than asking why multiple unrelated things were packed into a single neuron, he now tried to figure out what those things might have in common. It hit him:

I. Meet cute Barnabas and Mainspring grew up near at hand, about an hour apart with good traffic, but for a long time they weren’t close. They traded glimpses and occasional hellos and then went about their business. Both of them carried on livelier conversations with farther-flung neighbors, who were richer and had more to offer. When Mainspring did interact with Barnabas, it was cringe. Mainspring liked to puff themself up, to strut around like a big deal—an innovator, a titan of industry—but they would turn shy at the worst moments, especially in any intimate conversation. Barnabas, meanwhile, had a dancer’s flair, an artsy, enigmatic glamour, except that when they tried to talk about real life, they’d blurt out hundreds of rapid-fire words—overtalking, overthinking, and generally overwhelming whomever they were trying to impress. So when Barnabas and Mainspring were young, they minded their own business. Until they’d both come into their own, and they saw each other properly. A group of geographers got together every year in a different place to talk about everything they had learned, and they were considering coming to visit either Mainspring or Barnabas. Both of them put on their best faces and tried to coax the geographers into choosing them as host. “Uh, hi-hello,” Mainspring said haltingly to Barnabas, whose full official name was St. Barnabas. “I really think it would be better if those geographers came to my place. I have more space, you see, and … and I am a titan of industry. I can show them practical applications of their research. It just makes more sense.” “Oh, really?” Barnabas laughed, making Mainspring more antsy. “Well, I can give them an elevated, artisanal experience. I have fresh croissants that were just written up in the Times. And I have plenty of space! I have so many friends who are great thinkers and architects. It’ll be lovely.” Barnabas carried on, basically calling Mainspring uncultured. Mainspring had a prickly feeling, like the worst heat dome of midsummer. For their part, Barnabas couldn’t bear the meanness they were inculcating inside themself. This feeling that they were small-time, no-account, a dilettante. They couldn’t stop aiming a flood of nervous words at Mainspring. At last, Mainspring had had enough—with the help of their city council and mayor, they offered the geographers a much-too-lavish deal that Barnabas could never hope to match. Totally worth it to hear Barnabas’s stream of self-aggrandizing nonsense peter out as they realized they’d been defeated. “There,” Mainspring said. “I’m going to show these geographers a time they’ll never forget. Now if you’ll excuse me, I’ve wasted enough energy—I have some sewer maintenance and a lovely parade to deal with. Goodbye.” Mainspring was skilled enough at multitasking that they could have fixed the sewer, ensured the smooth running of the parade, dealt with the geographers, and done a thousand other things all at the same time. But they were making a point. “St. Barnabas is such a fool,” Mainspring complained to their friend Turnbull. “They are totally unserious but determined to be taken seriously. It drives me to gridlock.” “I know what you mean,” lamented Turnbull. “We live in a world of posers.” Turnbull lived an hour and 15 minutes from Mainspring but at least two hours’ travel from Barnabas. Turnbull was even richer than Mainspring and had a certain surety of purpose that made Mainspring feel even more like a stammering numpty. “Whatever,” said Mainspring. “It’s over, and now I’ll never worry about St. Barnabas again. I have better things to fuss about. Like ensuring that every last detail of this geographer meeting goes perfectly.” II. How they came alive Everybody voted all the time. Well, some people voted more than others, but the median resident of the cities of Mainspring and St. Barnabas voted a dozen times a day—though of course some outliers might vote occasionally, or constantly. A lot of the votes were more like complaints, or bug tickets. Like: “The storm drain on my street corner clogs and becomes a lagoon every time it rains.” Or: “The cars go too fast on my block.” Or: “I can’t get to work because the bus is too slow.” But there were also votes along the lines of: “There should be a park here.” And: “This neighborhood is a food desert—we need a grocery store.” And: “The crossing guard by the elementary school is a hero who deserves some recognition and maybe a raise.” Nobody expected that by voting, they were prodding their cities to grow minds of their own; they just had stuff to get off their metaphorical chests. But it transpired that every vote was a building block of thought. Much later, some fancy expert summed up: “Turns out the smallest unit of consciousness is a vote.” Take Sandi, the librarian at the Nine Corners branch in Mainspring. She noticed things all day, like the people using the book drop box as a trash can, or the folks who came in off the street who could use easier access to social services. There were books she knew her patrons wanted, books that undoubtedly sat unwanted on people’s shelves all over the city. But also, Sandi shared things that came to mind—like, hey, what if the library book sale were a block party? What if the shopping district on the West Side were easier to get to from the Longneck neighborhood, where all the warehouses had been converted to housing and hipster coworking spaces, during peak after-work hours? Sandi had opinions about everything from street cleaning to the power grid, because she listened to people all day. Then there was Raeford, a bartender at the Wild Goose Chase in the middle of Gallery Row in St. Barnabas. He also listened to people’s problems from evening until the wee hours, and solutions came to him like clockwork when he woke at noon the next day. He saw St. Barnabas at night, so he knew the unsafe blocks that could use brighter streetlights, the

I don’t remember much about Peppy, my first and only pet cat. I can conjure the sensation of stroking her while she purred, recall how she used to get stuck in trees (just like in cartoons!), and chuckle about the time she pooed in my baby sister’s cot. That’s about it. What I do vividly remember, though, is the day she went missing. I was 10 years old, and I searched everywhere for her, scouting nearby fields and woods until sunset. I made posters. We never found her. I was devastated. There was no way to get more time with Peppy, but almost 30 years later, pet owners are being offered an ever-expanding set of options to potentially prolong their years with their furry companions. The possibilities include drugs, cloning, and even cryonics. But is that a good thing? There’s certainly a market for pet preservation. And a growing number of biotech companies have their sights set on pet longevity. Loyal, a company that is currently working on three potential longevity drugs for dogs, is trialing one designed to improve metabolic health in around 1,300 pet dogs across the US. Others are testing dog drugs that aim to combat both age-related diseases, including conditions like obesity and osteoarthritis, and aging itself. There’s even a company focused on longevity medicines for domesticated cats. I don’t know how or when Peppy died. But if there had been a drug that might have protected her from diabetes or arthritis, there’s no doubt I would have tried to get my hands on it. That’s about where my enthusiasm for pet life extension ends, though. I’m far less interested in cloning, a relatively new option for people mourning a pet and seeking a replacement. In most cases, this technology involves taking the DNA of a pet, putting it into an egg cell from another animal of the same species, and growing the resulting embryo in a surrogate animal. It worked for Dolly the sheep, who was born the year before Peppy went missing. It has since worked for other mammals, including cattle, horses, and ferrets—and cats and dogs. In the US, a company called Viagen Pets offers to clone cats and dogs for $50,000 a go. This doesn’t result in an exact replica of the animal but a genetic twin. Still, there are lots of reasons why a person might want to clone a pet. On its website, Viagen explicitly offers customers “a way to hold on.” Lori Kogan, a professor of clinical sciences at Colorado State University who has studied human-animal relationships for decades, doesn’t have a problem with the practice. She points out that while we have well-established rituals for coping with the loss of a person—such as funeral services, time off work, and memorial gifts—we don’t really have the same for pets. As a result, pet owners can experience what is sometimes called “disenfranchised grief,” she says. Having their feelings go unrecognized can feel isolating. If cloning a pet brings a person peace, she says, “who are we to judge?” Fair enough. But I can’t help thinking that pet loss in childhood might be different. It’s often the first time a child confronts death. Losing Peppy was a formative experience, and distressing though it was, I like to think it helped prepare me for losses I experienced in adulthood. I wouldn’t want my own children to think that death is not final, and that individuals can be replicated or replaced. Or, for that matter, revived, which is the promise behind pet cryonics. For a fee, a handful of companies offer to cool dead pets to extremely low temperatures and store them for long periods of time—even indefinitely. The idea is that at some point in the future, we’ll have invented incredible technologies that will not only bring your pet back to life but also cure whatever it died of. Alcor, a cryonics facility in Arizona, is currently storing the remains of hundreds of pets as well as people. It even recently announced it had cooled a small marsupial—its first pet sugar glider. With cryonics, the chances of being reunited with your pet are bordering on zero. Even those who work in the field acknowledge that the stored people and animals are unlikely to be reanimated. As things stand, there is no way to really and truly bring any animal “back.” I miss Peppy. But given the chance, would I stick her in a vat of liquid nitrogen? Or get another cat to give birth to a genetically identical animal? No, I would not. RIP to the one and only Peppy.

Pig kidneys that were cooled to -150 °C and stored in a freezer for months have been successfully rewarmed and shown to work again for the first time, say scientists. They hope to replicate the findings with human organs. The kidneys—which are similar in size to human ones—were left in a glass-like state, in one case for over a year. Once they had been rewarmed, tested in machines, and transplanted into pigs, the kidneys regained their color and made urine—key signs they were working. “Ten years ago … I wouldn’t say I had high hopes it was actually going to work,” says Erik Finger, a transplant surgeon at the University of Minnesota who co-led the work. “After we did the last transplant, I walked out of the room and said, ‘This is a big deal.’” The research was shared at the preprint server bioRxiv and has not yet been peer-reviewed. The kidneys aren’t perfect, and the researchers have yet to demonstrate that they can sustain life over the long term. But the results represent a milestone achievement, say others in the field. “Thank God that someone’s actually managed to do it in one organ and prove that it works,” says Peter Kilbride, a cryobiologist and cofounder of Kyros Kairos, a company focused on improving funding for cryopreservation research, who was not involved in the research. “For years, people have been trying and failing to get to this step. Finally, we’ve got this breakthrough.” “Their work is amazing and will enable us to truly, indefinitely bank organs,” says Korkut Uygun, a biomedical engineer and professor of surgery at Harvard Medical School, who was also not involved in the research. “It is a revolutionary time for transplantation.” Buying time Every year, tens of thousands of organ transplants take place in the US alone. These procedures are thought to have saved 2 million years of life in the last 25 years. But there’s plenty of room for improvement. One major challenge is the lack of available organs. Even when an organ becomes available, it can be difficult to get it to the right recipient within 24 to 36 hours, which is the current limit for preserving human organs. People who receive organ transplants must also take drugs that suppress their immune systems for the rest of their lives. These drugs are meant to stop their bodies from rejecting the new organs. But they come with side effects and increase the risk of infections and cancer. The ability to bank organs for long periods of time holds the promise to address all these challenges. Doctors would have more time to match organs to recipients. They’d be able to limit the risk of organ rejection, too—potentially by preparing recipients, and their immune systems, beforehand. “With real organ banking … instead of the patients waiting for the organ, it’s the organs that are waiting for the patients,” says Finger. Scientists have been able to cool cells to ultra-low temperatures through a process called vitrification, which essentially turns them to something like glass. This procedure is already used to store eggs, sperm, and embryos. Vitrifying whole organs is much harder. Some problems can be avoided with cryoprotectants—chemicals that work like antifreeze and prevent damaging ice crystals from forming. But these chemicals tend to be incredibly toxic. It’s also difficult to rapidly and uniformly cool large tissues, and just as hard to evenly rewarm an organ all the way through. Working with John Bischof, a bioengineer at the University of Minnesota, Finger and colleagues have come up with a solution. Once an organ has been loaded with a cryoprotectant, they infuse it with iron oxide nanoparticles. These nanoparticles don’t do anything to the cells. But when it’s time to rewarm the organ, they can be activated with an electromagnetic field.  When the radiofrequency of that field switches between two states, the particles also flip, realigning themselves with the field. That causes them to release heat throughout the organ. Adjusting the power of the field allows the team to control the rate of heating so that it gets faster once the organ reaches -120°C.  The researchers successfully vitrified rat kidneys using this approach in work published in 2023. Back then, they were able to rewarm kidneys that had been kept in a freezer for up to 100 days before transplanting them into rats. Since then, the team has been trying to achieve the same success with bigger organs. Pig kidneys are thought to be a good model for human ones—they’re about the same size and look similar. Rat kidneys weigh around one gram; pig kidneys are around 100. It hasn’t been easy. The cryoprotectant used for vitrifying rat kidneys didn’t work as well in the pig organs. “We had to rediscover and modify the cocktail,” says Bischof. “That’s why it’s taken us three years.” Deep-freezing kidneys The first step in the procedure is to remove a kidney from a donor pig. Once it’s out, the kidney is flushed with a commonly used organ preservation solution to remove the blood, bagged, and temporarily laid on a bed of ice in a cooler so it can be taken over to the engineering lab. There, team members unpack the kidney and hook it up to a device they’ve designed to control the organ’s temperature and pressure. Then they start to load it up with the cocktail of cryoprotectants, slowly enough to ensure an even spread through the organ but quickly enough to minimize any toxic effects. It takes around two hours. The next step is to infuse the organ with the iron oxide nanoparticles, which are pumped through the organ for around seven to eight minutes, says Finger. Then it’s time to cool the organ by pumping cold nitrogen vapor into a chamber housing it. It’s a delicate process, and the team must ensure that the organ is cooling all the way through. At the same time, they must lower the kidney’s temperature as quickly as possible to prevent ice from

In this age of rising electricity demand, people are trying to squeeze every last bit of power out of every power plant possible. Over the past few weeks, there’s been big news about nuclear power plants trying to do just that. Constellation, the largest nuclear operator in the US, announced plans to add nearly a gigawatt of new capacity across 11 existing nuclear reactors at six plants. And on October 5, the Department of Energy awarded a $4.2 billion loan to Vistra for previously announced upgrades at three plants. Pushing existing reactors to produce more could help provide more clean power for data centers, quickly. But just how much additional power can we count on?   Upgrading equipment at existing nuclear power plants can allow them to reach a higher capacity; the process is called a power uprate. Operators have been doing this since the 1970s in the US, but it’s been less common in recent years as demand for electricity plateaued and cheap natural gas put financial pressure on nuclear power plants. Some plants closed, and putting in more money to produce more electricity didn’t make much sense at others. Between 2001 and 2010, the US Nuclear Regulatory Commission approved over 80 uprates. Between 2011 and 2020, the number was 33. But with the rise of AI and the related boom in electricity demand, there’s been a shift. We’re seeing shuttered plants like Palisades and Three Mile Island race to reopen. And existing plants are looking to uprate again. Some uprates are minor, involving changes to instrument setpoints or calculations at the plant. But more major overhauls, which can boost reactor power by as much as 20%, require replacing plant equipment. Generally, uprates involve using fuel that’s more highly enriched, or a higher volume of fresh fuel, in the nuclear reactor. That helps produce more steam, which is used to turn a turbine and generate electricity. To handle that additional energy, the main turbines and equipment such as pumps, motors, generators, and transformers are upgraded. The most recent major uprate approved in the US was for three reactors at the Browns Ferry nuclear power plant in Alabama. A $475 million project saw that plant expand its power capacity by 14% between 2018 and 2019. Things could pick up soon, though. Constellation announced plans this week to spend more than $4.3 billion on uprates to 11 reactors. The additional electricity will be enough to power roughly 700,000 US homes. Behind it all? Big Tech money. Google agreed to buy electricity from these plants, and the 20-year agreement was a major factor in making the uprates happen. As Joe Dominguez, Constellation’s CEO, told the New York Times: “These are capital intensive, labor intensive projects that require a different price point than the market trades at, frankly.” Also in the last few weeks, the US Department of Energy shared that it will commit over $4 billion to help finance upgrades and modernization for Vistra nuclear power plants across Pennsylvania and Ohio. Those projects will add 433 megawatts of power capacity, and Meta has already signed on to buy electricity from the plants in a long-term deal. A note about cost: On a per-kilowatt basis, that Constellation project is less expensive than building a new reactor, but it’s still more expensive than building a new utility-scale solar farm with energy storage or a combined-cycle natural-gas plant. Even at this high cost, uprates are in high demand. Today, the US nuclear fleet has roughly 98 gigawatts of total power capacity. Depending on who you ask, there’s somewhere between three and eight additional gigawatts on the table from uprates. A pretty significant chunk of the potential uprates in the US are already accounted for—the NRC already expects applications to add 2.4 gigawatts of power to reactors through 2032. It’s crucial to put these plans (and the total potential for uprates in the US) in perspective, though. PJM, the grid operator that covers much of the East Coast, expects about 30 gigawatts of additional peak demand because of AI by 2030. All the possible nationwide nuclear uprates would cover just a fraction of that. Making the most of existing nuclear reactors is a relatively easy win at a time when we need all the zero-emissions power we can get. But there’s still a lot of demand, and if we want more nuclear power to meet it, eventually that will require actually building new reactors. This article is from The Spark, MIT Technology Review’s weekly climate newsletter. To receive it in your inbox every Wednesday, sign up here.