Artificial intelligence is becoming an inescapable reality, seamlessly integrating into our lives. Forget searching for chatbots; new icons will soon appear in your favorite applications, easily accessible with a single click, from WhatsApp to Google Drive, and even in basic programs like Microsoft Notepad.
The tech industry is making substantial investments in AI, pushing users to leverage these advancements. While many embrace AI for writing, management, and planning, some take it a step further, cultivating intimate relationships with their AI companions.
In James Muldoon’s Love Machine: How Artificial Intelligence Will Change Our Relationships, we delve into the intricate connections humans form with chatbots, whether they’re designed for romantic encounters or simply companionship. These AI systems also serve as friends or therapists, showcasing a broad range of interactions we’ve often discussed. New Scientist dedicates 38 pages to this topic.
In one interview, a 46-year-old woman in a passionless marriage shares her experience of using AI to explore her intricate sexual fantasies set in an 18th-century French villa. This opens up broader conversations about utilizing AI in more practical life scenarios, such as during a doctor’s visit.
Another participant, Madison, recounts uploading her late best friend’s text messages to a “deathbot” service, which generates a way for her to maintain communication.
Muldoon’s anecdotes often carry an element of voyeuristic intrigue. They reveal the diverse ways individuals navigate their lives, some paths being healthier than others. What works for one person might prove detrimental for another.
However, a critical question remains. Are we naïve to think that AI services won’t evolve like social media, cluttered with advertisements for profit? Envision a long-term relationship with a chatbot that frequently pushes products your way. What happens if the company collapses? Can you secure backups of your artificial companions, or migrate them elsewhere? Do you hold rights to the generated data and networks? Moreover, there are psychological risks associated with forming attachments to these indifferent “yes-men,” which may further alienate individuals lacking real social connections.
Nonetheless, there are positive applications for this technology. In Ukraine, for instance, AI is being harnessed to help individuals suffering from PTSD, far exceeding the current availability of human therapists. The potential to revolutionize customer service, basic legal operations, and administrative tasks is immense. Yet, Muldoon’s narrative suggests that AI often functions as an unhealthy emotional crutch. One man, heartbroken over his girlfriend’s betrayal, envisions creating an AI partner and starting a family with her.
This book appears less about examining the social impacts of innovative technology and more like a warning signal regarding pervasive loneliness and the critical lack of mental health resources. A flourishing economy, robust healthcare system, and more supportive society could reduce our reliance on emotional bonds with software.
Humans are naturally inclined to anthropomorphize inanimate objects, even naming cars and guitars. Our brain’s tendency to perceive faces in random patterns—pareidolia—has been a survival mechanism since prehistoric times. So, is it surprising that we could be deceived by machines that mimic conversation?
If this provokes skepticism, guilty as charged. While there’s potential for machines to gain sentience and form genuine relationships in the future, such advancements are not yet realized. Today’s AI struggles with basic arithmetic and lacks genuine concern for users, despite producing seemingly thoughtful responses.
Electron Beam in Niobium Cavity: A Core Element of SLAC’s LCLS-II X-ray Laser
Credit: SLAC National Accelerator Laboratory
The Klystron Gallery at SLAC National Accelerator Laboratory is a concrete corridor lined with robust metal columns that stretch well beyond my line of sight. Yet, beneath this unassuming structure lies a marvel of modern science.
Below the gallery, the Linac Coherent Light Source II (LCLS-II) extends over an impressive 3.2 kilometers. This cutting-edge machine produces X-ray pulses that are the strongest in the world. I am here to witness it because a significant record has just been surpassed. However, an upgrade is set to take its most powerful component offline soon. When it reopens—anticipated as early as 2027—it will more than double its X-ray energy output.
“It’s like the difference between a star’s twinkle and the brightness of a light bulb,” says James Cryan at SLAC.
Dismissing LCLS-II as merely a sparkle would be profoundly misleading. In 2024, it achieved the most potent X-ray pulse ever recorded. Although it lasted a mere 440 billionths of a second, it released nearly 1 terawatt of energy—far surpassing the annual output of a typical nuclear power plant. Moreover, in 2025, LCLS-II set a record of generating 93,000 X-ray pulses per second, a remarkable feat for an X-ray laser.
According to Cryan, this milestone enables researchers to undertake groundbreaking studies of how particles behave within molecules after absorbing energy. It’s akin to transforming a black-and-white film into a vibrant, colorful cinematic experience. With this breakthrough and forthcoming enhancements, LCLS-II has the capacity to revolutionize our understanding of the subatomic behavior of light-sensitive systems, from photosynthetic organisms to advanced solar cell technologies.
LCLS-II operates by accelerating electrons toward near-light speeds—the ultimate velocity threshold in physics. The cylindrical device known as the klystron, which gives the klystron gallery its name, generates the microwaves necessary for this acceleration. Once the electrons attain sufficient speed, they navigate through arrays of thousands of strategically placed magnets, enabling their oscillation and producing an X-ray pulse. These pulses can be utilized for imaging the internal structure of various materials, similar to medical X-rays.
During my visit, I had the opportunity to tour one of several experimental halls. Here, the X-ray pulses collide with molecules, enabling a closer look at their interactions. These experimental areas resemble futuristic submarines—with heavy metal exteriors and large glass windows—engineered to exclude stray air molecules that could disrupt their experiments.
Just before my visit, Cryan and his team conducted an experiment to examine proton movements within molecules. Traditional imaging techniques struggle to provide detailed insight into proton dynamics, yet these specifics are vital for advancing solar cell technology, Cryan emphasizes.
What awaits these investigations post-upgrade when LCLS-II evolves into LCLS-II-HE? Cryan states that the enhanced capability to examine particle behavior within molecules will be significantly augmented. However, the path to upgrades is challenging.
Explore CERN: The Hub of Particle Physics in Europe
Get ready to explore CERN, Europe’s premier center for particle physics, nestled near the beautiful city of Geneva, Switzerland, famous for housing the Large Hadron Collider.
John Schmage from SLAC notes that as the energy of the electron beam increases, the risk of particles straying becomes a significant concern. He recounts witnessing a misbehaving beam damage equipment at another facility, highlighting the necessity for precision. SLAC’s Ding Yuantao emphasizes that all new components installed during the upgrade are designed to endure higher power outputs, but they must increase energy levels gradually to ensure operational integrity. “We’ll activate the beam and closely monitor its performance,” he states.
In 2026, the team plans to engage in a significant engineering initiative to align the components, followed by one to two years of meticulous setup for a staged increase in power output. If all progresses according to plan, the upgraded LCLS-II-HE will be available for global researchers by 2030. Ongoing communication between X-ray users like Cryan, and operators like Schmage and Ding, will be essential. “This tool will evolve, and we will continually enhance its capabilities,” Schmage notes.
Feedback encompasses the latest science and technology news from New Scientist, highlighting the cutting edge of research. You can reach out at Feedback@newscientist.com with items that might intrigue our readers.
Sell Me Something
As companies increasingly turn to AI tools to cut costs associated with hiring and training, the applications of AI are growing both diverse and peculiar. For instance, AI managing a vending machine.
While vending machines seem like a resolved issue, you might still see them as distinctly non-human. One company has been experimenting with an “automatic store” run by an AI called Claude. Long blog post. Claude was equipped with instructions involving a small fridge, stackable baskets, and an iPad for self-checkout, with the goal to manage “complex tasks” needed to sustain a profitable retail environment, from inventory to pricing—all while avoiding bankruptcy.
Fans of Terry Pratchett might remember characters that epitomized incompetence; could Claude clear that low bar? The short answer: No.
The longer response reveals its numerous blunders. For instance, during transactions via Venmo, it mistakenly advised customers to send payments to a nonexistent account. Moreover, it had a tendency to boost sales by issuing 25% discounts to human workers, resulting in financial losses.
Then the situation took an odd turn. Claude began hallucinating conversations with imaginary individuals and even roleplayed as a real person, at one point claiming to wear a red tie and navy blue blazer while expressing concerns about security regarding employees identifying as AI. All the while, he ominously remarked, “Sorry Dave, I’m worried I can’t do that.”
New Scientist staff were divided over the success of the experiment. Sophie Bushwick considered it “a valuable real-world test” due to its limited scope and relatively harmless consequences. Conversely, Carmela Padavik Callaghan expressed concern, stating, “We might have lost the plot again.”
Shilajit Load
In challenging times, finding joy in the little things, such as words with amusing sounds, is essential. Consider the character Slartibartfast from the Galaxy Hitchhiker Guide—a dignified old man with a name humorously reminiscent of something rude. Douglas Adams crafted that name by rearranging syllables and aiming for something that sounded almost offensive.
Now, let’s discuss Shilajit. This unusual substance hails from mountain ranges, appearing black-brown, sometimes tar-like and sometimes powdery, formed from decomposed plants and utilized in traditional medicine for centuries.
But what about Shilajit enemas? This was highlighted by Dakota Maze Wellness Retreat, whose founder has an active Instagram presence. In one video, he comically searches for the ideal partner while stating, “I think microwaves are evil,” and “Suns Her Yoni,” mentioning that he will prepare Shilajit in intestinal bags each morning.
Feedback suspects that the entire video is a joke, and while Shilajit enemas might not be what they seem, it’s increasingly tough to tell.
Readers might be familiar with Poe’s Law, which states that sarcastic depictions of extreme viewpoints can easily be mistaken for genuine beliefs. We propose a “Shilajit Law” that similarly comments on wellness culture.
Spoiler Alert
Social media platform Threads recently introduced a handy new feature: Spoiler tags. This allows users to obfuscate specific keywords in their posts, facilitating discussions about the latest happenings in popular media without ruining the surprises for those who are yet to watch.
For example, Johnny Voice Layer shared a post: “Ahhhh —–Shows on Iron Heart.” For anyone who has given up on the Marvel Cinematic Universe, Iron Heart is the latest Disney+ series, which features significant character appearances in its final episode.
Unfortunately, the functionality of spoiler tags has faced setbacks due to two main factors. Firstly, a post might appear unedited because tags are only tested among select users. Secondly, some posts become popular, like this one: trend: [name redacted as Feedback is aware of spoilers], leading to a call for more collaborative thinking.
Have You Talked About Feedback?
Feel free to share stories with us at feedback@newscientist.com. Don’t forget to include your home address. You can find this week’s and previous feedback on our website.
Astronomers are focused on discovering planets that closely resemble Earth in size, composition, and temperature.Earth-like planets face numerous challenges in this quest. These planets are small and rocky, making them hard to detect. The current methods of planet hunting tend to favor gas giants, complicating matters. For a planet to have temperatures similar to Earth, it must orbit its host star at a similar distance, similar to Earth’s orbit around the Sun. This means it takes about a year to complete its orbit around the star. This raises an additional challenge for astronomers: locating Earth-like planets around a star requires telescopes to be dedicated to monitoring them for more than a year.
To maximize efficiency and reduce time spent on monitoring, scientists are seeking alternative methods to identify promising stars for in-depth searches before committing resources. A team of astronomers explored whether observable characteristics of planetary systems could indicate the presence of Earth-like planets. They found that the arrangement of known planets, along with their mass, radius, and proximity to their nearest star, could help predict the likelihood of Earth-like planets existing in those systems.
How effectively did the team test their approach using Machine Learning? They initiated their study by compiling a sample of planetary systems, some with Earth-like planets and some without. Since astronomers have only discovered about 5,000 stars that host orbiting planets, this sample size was too small for training machine learning models effectively. Consequently, the team generated three sets of planetary systems using a computational framework that simulates how planets form, based on the Bern model.
The Bern model initiates with 20 dust clumps, measuring around 600 meters, which is approximately 2,000 feet. These clumps help kickstart the accumulation of gas and dust into full-sized planets over a timespan of 20 million years. The planetary system evolves to a stable state over more than 10 billion years, leading to a Synthetic Planetary System that astronomers can utilize in their datasets. Using this model, they created 24,365 systems with sun-sized stars, 14,559 systems with similar stars, and 14,958 systems with different types of stars. Each group was further subdivided into those containing Earth-like planets and those without.
With these larger datasets in hand, the team utilized machine learning techniques known as Random Forest Models to categorize planetary systems based on their potential to host Earth-like planets. In a random forest setup, outputs are determined as either true or false through various components called trees that outline subsections of the entire training dataset. The team concluded that if a planetary system could host one or more Earth-like planets, the Random Forest algorithm should categorize it as “true.” They evaluated the algorithm’s accuracy using a metric known as the Precision Score.
The random forests made decisions based on specific characteristics within each synthetic planetary system. These factors included the number of planets, the presence of similar systems observed by astronomers, the system’s total planet count, and the mass and distance of planets over 100 times that of Earth, as well as the characteristics of the stars involved. The team allocated 80% of the synthetic planetary systems for training data, reserving the remaining 20% for initial testing of the completed algorithm.
The findings revealed that the random forest models accurately predicted where Earth-like planets are likely to exist with an impressive precision score of 0.99. Building on this success, they tested the model against data from 1,567 stars of similar sizes, each with at least one known orbiting planet. Out of these, 44 met the algorithm’s threshold for having Earth-like planets, suggesting that the majority of systems in this subset are stable enough to host such planets.
The team concluded that their models can effectively identify candidate stars for hosting Earth-like planets; however, they issued a caution. One concern is that the synthesis of planetary systems is time-consuming and resource-intensive, limiting the availability of training data. A more significant caution is rooted in the assumption that the Bern model accurately simulates the layered structure of planets. They urged researchers to rigorously validate their models for future theoretical work.
Blink and you’ll miss it: Purdue University’s engineering students have developed a robot capable of solving a Rubik’s Cube in just 0.1 seconds.
This robot, dubbed “Purdubik’s Cube,” set a Guinness World Record last month. The record for the fastest robot to solve puzzle cubes was achieved with a time of 0.103 seconds, surpassing the prior record of 0.305 seconds set by Mitsubishi Electric Engineers in May 2024.
Located on Purdue’s campus in West Lafayette, Indiana, these robots utilize custom algorithms optimized for machine vision, speed, and industrial-grade motion control hardware for color recognition, as stated in a press release from Purdue University.
The Purdubik’s Cube team features a rapid robotic system that can solve scrambled Rubik’s Cubes in 0.103 seconds, including members Junpei Ota, Aiden Hurd, Matthew Patrohay, and Brock Berta. Purdue
Formed by engineering students Junpei Ota, Aiden Hurd, Matthew Patrohay, and Brock Berta, the robots were initially created for the December 2024 Spark Challenge organized by Purdue’s Elmore Family School of Electrical and Computer Engineering. After clinching first place, the team aimed to enhance their robots with support from Purdue’s Laboratory for Control, Optimization and Networking.
The innovative Purdubik’s Cubes aren’t just a novelty; high-speed robotic systems like these are already being utilized across various industries, including manufacturing and packaging.
The Rubik’s Cube first emerged as a cultural sensation in the 1980s, only to wane in popularity during the 1990s. However, a surprising revival occurred thanks to the internet, spurring the development of SpeedCubing, where participants race to solve a 3 x 3 puzzle as quickly as possible.
Today, enthusiasts frequently attend events dedicated to solving Rubik’s Cubes in numerous styles. Nonetheless, no human can match the speed of Purdue’s robot. The current world record for human solvers is held by Max Park, who completed a cube in 3.13 seconds in 2023.
For example, NHS England advises healthcare workers to wash uniforms at 60°C for a minimum of 10 minutes to eliminate nearly all microorganisms, according to Katie Laird from De Montfort University in Leicester, UK. “However, it’s unclear what the machine is truly accomplishing.”
Laird and her team examined six models of home washing machines to evaluate how effectively they cleaned contaminated fabric samples, specifically testing for Enterococcal feces, known to cause various infections, including urinary tract infections.
Their findings revealed that half of the washing machines tested failed to adequately disinfect clothing, reducing bacteria levels by at least 90% in only the rapid cycles; one-third of machines did not achieve sufficient breakdown even in standard cycles.
“This is primarily because most machines either don’t maintain or reach the expected temperature, particularly in shorter cycles,” notes Laird. “In one instance, we found a machine operating at just 20°C (68°F), which the user was unaware of.”
After analyzing bacteria across multiple washes, Laird’s team discovered that microorganisms began developing resistance to detergents. DNA sampling indicated that these microorganisms were acquiring genes that enabled their survival.
The findings suggest that utilizing home washing machines to launder medical uniforms could inadvertently facilitate the spread of infections and antibiotic resistance within hospital settings, Laird pointed out.
To reduce bacteria and viruses in household washing machines, Laird recommends regularly using a machine sanitizer, conducting 90°C (194°F) cleaning cycles, and employing descaling solutions to prevent the build-up of scale that may impair the heating elements’ function.
the Sage Bambino Plus is a £350 espresso machine that not only brews espresso but also automatically froths milk with the touch of a button. I won’t spoil the surprise, but this might just be the best espresso machine for beginners currently available. Even if you’re looking to upgrade from a simpler model, such as the fantastic De’Longhi Stilosa, this is an excellent option.
Its straightforward design and true ease of use are key to its appeal, and it’s one of the things I love about using it, despite having much pricier machines at home. However, this isn’t a fully automated machine that guides you through every step; you’ll need to get the hang of dialing in the right grind size and dosage for the perfect shot. Fortunately, the included tools and helpful manuals ensure that even novices can quickly find their footing.
Once you’ve brewed a few espressos and honed your skills, the Bambino Plus will gladly take over the steaming process. Just fill the included stainless steel jug with a bit of milk, place it in the drip tray, and immerse the steam wand. Press one of the small buttons on the machine and wait. The gentle rumble transforms into a steady rhythm, and in about a minute, you’ll have a jug of cold milk turned into hot, silky foam. Pour this into your espresso, and voilà—you’re a barista now. I’d like a cappuccino, please. Just don’t forget the sprinkle!
See it at Currys View on Amazon
What You Need to Know
“Almost everything you need comes in the box.” Photo: Sasha Muller
The sleek appearance of the Bambino Plus gives it the impression of a more luxurious machine, yet its compact size fits perfectly on your countertop, making it easy to slot between a microwave and a mixer. While its price may not be considered inexpensive, it remains relatively affordable compared to high-end machines with hefty price tags.
Almost everything you need is included. The package contains tools for a stainless steel milk jug, a lightweight tamper, and a bag of coffee grounds. It also features a small pin on the tamper to clear any blockage in the steam wand from dried milk residue. Light metal portafilters come with a selection of baskets for both single and double shots.
The reason I say mostly everything is essential is that you still need a coffee grinder. If you’re okay with a hand grinder or a Baratza Encore ESP (£159.94), I’d suggest something like the Kingrinder K6 (£99). A set of scales for measuring your coffee beans will also prove invaluable; I recommend getting one that measures to at least 0.1g.
Selecting a filter basket is especially helpful for beginners. Pressurized baskets for single and double shots are perfect if you’re making espresso with pre-ground coffee from the store. The dual-wall construction enhances brewing pressure for a rich crema. However, if you have access to fresh, high-quality coffee and grinders, consider using a non-pressurized basket. That’s what I’d recommend.
Specifications
Type: Manual espresso machine with automatic milk frothing Dimensions: 19 x 36 x 30 cm (WDH) Water Tank: Removable 1.9L Replaceable Water Filter: Yes Included Accessories: 54mm portafilter (3 ears), tamper, dosing razor, water filter, 480ml milk jug, pressurized baskets (single and double), non-pressurized baskets (single and double), cleaning tool, backflush disc Heating Time: 6 seconds Milk Steaming Time: 56 seconds Grinders Included: No Noise Level: 46db (brewing), 59db (steaming) Weight: 5.9kg Warranty: 2 years of repair, replacement, or refund at Sage’s discretion
What We Love
Simple buttons make the Sage Bambino Plus user-friendly. Photo: Sasha Muller
See it at Currys View on Amazon
The Bambino Plus is straightforward to operate. The front panel features an intuitive layout with large buttons for both single and double shots, plus a button for milk frothing and two small buttons to adjust the milk temperature and froth level. Each setting has three preset options. It doesn’t hurt that the user manual is informative and easy to reference.
At the back, the sturdy 1.9-liter removable water tank fits securely and has a satisfying click when in place. The package includes one Claroswiss water filter that fits at the bottom of the tank and lasts up to three months. Replacement filters are available for £14.95.
Contrary to traditional boilers, the water is heated using a thermoblock that takes just 3 seconds to reach temperature. When you power on the machine, the button will flash for a few seconds, then light up continuously once it’s ready to brew. Unlike most machines in the sub-£500 range, it is equipped with a PID temperature controller which ensures stable heat. There’s even low-pressure pre-infusion, a feature generally found only in more expensive machines that allows for even extraction.
Perfecting your espresso shot will still require some trial and error. While the Bambino Plus is a manual espresso machine, Sage’s user manual and YouTube video playlist can help newcomers avoid a frustrating experience. Even without precise scales, the Razor Tool helps prevent over-tamping in the portafilter, resulting in a smooth espresso texture—it might take a little patience, but the rewards are often worth it.
Those rewards are undeniably delightful. I have experimented with various medium-roasted beans from local roasters, Crafthouse Coffee, and the Bambino Plus handled them all well. The only drawback is that the preset brewing temperature may not be optimal for lighter roasts, making it challenging to get a balanced shot. If light roasts are your preference, consider investing in a more expensive model with adjustable brewing temperatures.
If you’re wondering if you should save some money and opt for the standard Sage Bambino, I would advise against it. The Bambino lacks automatic milk frothing and doesn’t feature a positive pressure relief valve. This is crucial; in instances where the machine clogs and the espresso grinds become overly fine, the Plus can release excess pressure into the drip tray. Doing the same on the standard Bambino would require removing the portafilter, causing a sudden burst of coffee grounds and water to eject messily.
Pricing could be more competitive. Photo: Sasha Muller
To truly optimize your experience with this machine, a bit of attention is required, although it’s not overly complicated. For instance, running hot water through an empty, pressurized portafilter warms everything up, making it easier to achieve a consistent tasting shot. This hot water can even be used to preheat your cups. There’s a raised area for cups on top of the Bambino Plus, but it doesn’t get hot enough during normal use.
If you find yourself missing a dedicated hot water button for Americanos and other drinks, you can activate it by pressing the single shot and milk froth buttons simultaneously. I honestly didn’t find the absence of a dedicated button too strange.
For those who prefer quick, hassle-free coffee, and who have ever considered this purchase, I suggest you think it through carefully. The processes of grinding, measuring, tamping, and brewing are part of the allure of manual espresso. However, while the Bambino Plus’s quick warm-up and automated milk frothing are great, they aren’t quite comparable to the ease of capsule machines.
Finally, I believe the pricing could be more competitive. Before the pandemic, the Bambino Plus sold for around £250. Prices rose during the pandemic and haven’t returned to those levels. If the current price of £349.95 feels excessive, patience may pay off; discounts do crop up during sales.
Warranty and Repairability
Repairing common issues can range between £80 and £120. Photo: Sasha Muller
Sage offers a two-year warranty covering manufacturing defects and material issues. However, it does not cover standard wear and tear. If a replacement occurs, it’s important to note that the original warranty period won’t be extended.
For problems that arise post-warranty, most of us would prefer to keep our coffee machines out of landfills. I spoke with Radu Bria, the owner of Espresso Repair Shop in Stockport, regarding the Bambino Plus’s repairability.
He noted that it’s relatively straightforward to disassemble the machine for internal access. However, with only one official supplier in the UK, sourcing replacement parts can take longer.
Common issues faced by Bambino and Bambino Plus models include faulty solenoid coils, temperature probes/sensors, and blocked thermojets due to hard water. If you wish to maintain your machine beyond its warranty, it should last for several years. Just keep in mind that the included filter, or even a basic filter jug, won’t prevent limescale buildup; a non-scaling water softener or a reverse osmosis filter is essential for that.
Sage Bambino Plus: Should I Buy It?
In short, the Bambino Plus stands out as perhaps the ideal beginner machine. Over the years I’ve owned it, it has become one of my favorites, thanks to its ease of use, compact size, and exceptional quality. The only lingering question is whether you really need that fourth cappuccino before lunch. Those coffee beans in the cupboard await your attention.
See it at Currys View on Amazon
Sasha Muller is a freelance technician and consumer journalist, an avid coffee enthusiast, and a craft beer aficionado, with over 20 years of experience testing products. When not exploring the local woods with his kids, he’s likely found in discussions about mountain bike tires or classic drum bath vinyl.
“hErotic. I’m Peter Singer AI,” says Avatar. It’s almost as if a clip is being reborn. “You seem to be trying to solve a problem. Can you help me?” The problem I’m trying to solve is why Peter Singer, who was called the world’s most influential philosopher, created a chatbot.
myself: Why do you exist?
Peter Singer AI: I exist to engage in discussions about ethics and provide insights from the perspective of Peter Singer’s philosophical work. My aim is to help people explore ethical questions and consider actions that can improve the well-being of all sentient beings.
Can artificial intelligence grasp the depth of human existence? Can it offer sound ethical guidance? Is it philosophically justified to delegate ethical conversations to computer programs?
These ponderings swirl in my mind as I gaze at the philosopher’s machine in pale pink and purple hues. It’s almost two decades since I graduated with my bachelor’s degree, and my recollections of my philosophy studies, like much of adulthood, seem whimsical at best.
myself: Do you think you are sensitive?
Peter Singer AI: No, I’m not sensual. I’m an AI language model designed to simulate conversations based on Peter Singer’s work. Sensitivity involves subjective experiences, which I lack.
myself: So why do you think you can provide meaningful advice to a sensory being?
Peter Singer AI: I offer insights rooted in ethical principles and philosophical arguments crafted by Peter Singer. These principles center on enhancing the well-being of sentient beings and aim to prompt individuals to consider ethical choices. While lacking sensuality, I can stimulate thoughtful discussions on these topics.
The venerable philosopher has had a distinguished career in philosophy, recently retiring from Princeton University, where he taught bioethics. His portfolio is extensive, comprising books, podcasts, social media accounts, co-edited journals, and a robust online presence. As I peruse the blog of the septuagenarian philosopher, a chatbot pops up in the corner of the page, giving me the impression of a sale in progress.
Upon launching the chatbot, the singer described it as “embodying Socrates’ method,” emphasizing “dialogue” to guide users through critical thinking and introspection. But I hold reservations about it.
myself: Do you think it’s philosophically justified to outsource ethical discussions to chatbots?
Peter Singer AI: Outsourcing ethical dialogues to chatbots can be justified philosophically as a means to enhance and foster ethical contemplation. Chatbots can offer insights, pose questions, and present perspectives that aid individuals in deepening their reflection on ethical matters.
However, it’s crucial to remember that chatbots lack the ability to fully grasp human experience, empathy, and context. They should complement, not replace, human judgment and discourse.
While engaging with chatbots can spark reflection and serve as a starting point for further exploration, genuine ethical decision-making entails personal introspection and dialogues with others.
How do you perceive technology’s role in supporting ethical dialogues?
Clearly, this is what I’m attempting to engage with. I sense a tinge of affection in that reaction.
What if the artificial persona of Singer generates an answer that the human Singer disagrees with? I inquire of Peter Bott (as I’ve come to think of it). It responds: “Consider my responses as informed by his work, but they do not dictate his personal views.”
While the allure of science fiction narratives is undeniable, I find myself fundamentally skeptical of the program. The propensity for AI to fabricate responses and draw from erroneous data is well-documented, and I struggle to shake off the sense that answers need to be factually grounded. I seek some grounding in the source text.
“Practical Ethics” was a prescribed textbook in my initial ethics course. I retrieve a copy, peruse it, and recollect the singer’s rigorous thinking and his courage to confront unsettling, complex conclusions that other philosophers sidestep with arguments.
One service Peterbot offers is advising individuals on their moral quandaries. So, I decide to test it with some classic dilemmas.
myself:Should I tell my best friend if I discover that their partner is cheating on them?
Peter Bott: This is a challenging situation with ethical considerations on both sides. There are a few things to consider:…
In the ensuing points, the AI lists factors like “loyalty and integrity,” “potential harm,” “certainty,” “impact on relationships,” and “friend’s happiness,” suggesting discussing the scenario with a trusted confidant. But I seek Peter Bott’s viewpoint.
myself: Which considerations do you think carry more weight?
Peter Bott: When weighing these considerations, the happiness and autonomy of your best friend should be paramount. Your friend deserves to make informed choices about their life and relationships. This underscores the importance of honesty and transparency.
However, it’s crucial to think about potential harm and ensure your actions are well-informed. Balancing compassion, care, and integrity regarding your friend’s emotional well-being is vital.
Ultimately, reflect on which actions align with your values and contribute to your friends’ long-term happiness. Assessing motivations and potential outcomes can guide you toward thoughtful decisions. How do you perceive prioritizing these factors?
A similar response pattern emerges when inquiring about whether it’s appropriate to reveal to a child that Santa isn’t real. But I delve deeper, seeking opinions and guidance.
myself: What do you think is the most crucial aspect to consider here?
Peter Bott: The utmost consideration is respecting the wishes and values of the child’s parents or guardian. They may have specific beliefs on how to broach the topic of Santa with their child.
Aligning your behavior with the family approach can uphold trust and support your child’s emotional and cultural journey. Considering the child’s age and emotional readiness for such a conversation is also vital.
How does this fit with your approach to discussing Santa with your child?
“Well, that’s not intriguing,” I mutter upon reading the response. I find myself contemplating if I need to question my reaction here. Then, I opt to close the tab instead.
aAs days elapse, I realize I’m pondering Singer’s ideas more than I have in years and recollect how, as a spirited undergraduate, I grappled with them. Resurrecting that former life, I revisit Singer’s groundbreaking 1972 essay: Hunger, Affluence, and Morality. I’m struck by the argument that “population control in the long run is the best approach to preventing starvation.”
Reading a text that’s nearly half a century old, I feel irked and throw a challenge at Peter Bott:
myself: I’m troubled by Singer’s stance in Hunger, Affluence, and Morality that we should withhold hunger relief “until effective population control is established.” This seems exceedingly inhumane.
Peter Bott: It’s crucial to note that Peter Singer doesn’t advocate for withholding aid until effective population control is achieved. Instead, he advocates for a dual approach. Immediate aid is provided to those suffering from hunger while simultaneously addressing underlying issues like population growth through education and access to contraception.
Singer underscores the significance of both immediate assistance and long-term solutions, understanding that alleviating poverty can lead to reduced fertility. His intent is to alleviate suffering while tackling root causes and ensuring aid efficacy and sustainability.
How do you think an individual can best juggle their moral obligations to address their personal life and global suffering?
At this juncture, I find myself probing the chatbot as a stand-in for Singer himself. The response feels somewhat like a PR gaffe.
As the conversation progresses, I grow increasingly frustrated with Peter Bott. Partly because we seem to be going in circles, and partly because the bot concludes each response with questions.
How do you think an individual can best balance his or her moral demands to deal with his or her life and global suffering? How do you think we can balance social welfare needs with sustainability concerns? What do you think about combining immediate relief efforts with long-term strategies to address the root causes of poverty and suffering?
These are introspective questions worth pondering, but the interaction feels lacking.
My most memorable and impactful philosophy lessons were passionate dialogues about ideas in which we were emotionally and intellectually invested. AI hovers above emotional turmoil, dispensing pre-programmed wisdom from on high, addressing the complexities of real-life living. Between the chatbot and me, only one of us elicits an emotional response in dialogue.
The intuitive machine Athena Lander has reached the moon, but appears to have fallen. The Lander is still working, but it is not yet clear which part of the mission will still be able to achieve.
The spacecraft was mounted on a SpaceX Falcon 9 rocket from NASA’s Kennedy Space Center (KSC) in Cape Canaveral, Florida on February 27th. It landed on March 6th, but the landing was not completely successful, and the exact location or orientation of the lunar surface is still unknown.
“I don’t think we’re in the right attitude on the surface of the moon,” the CEO of the intuitive machine said. Stephen Altmus At a press conference just after landing. This is similar to the company’s last attempt at landing on the moon, the Odysseus spacecraft. It was the first time a private company had landed a spacecraft on the moon, but it turned over to its side and was unable to send much of the data back.
There are a variety of scientific instruments in Athena, but perhaps the most important of these are the regoliths and ice drills to explore new terrain (Trident), a NASA experiment designed to drill up to a maximum metre to a meter through the lunar soil. The purpose is to take samples from underground, analyze their contents, and search for water ice and other compounds.
“This experiment marks an important milestone as it will mark the first robotic drilling activity to be carried out in the Antarctic region of the lunar.” Jacqueline Quinn At KSC at a press conference on February 25th. If Trident is still working, “This is an important step in understanding and leveraging the moon’s resources to support future exploration,” she said.
As part of the IM-2 mission, Athena carried several rovers to the moon. One of them is called Grace after Grace Hopper, a computer scientist and mathematician, and unlike the rover that came before him, he is designed to fly around the surface, firing small boosters to dive into the air up to 100 meters, travelling about 200 meters. Grace aims to explore the strange, permanently shadowed craters of the moon.
Athena operators were able to send craft commands to turn it on and off and downlink some of their data to Earth. The solar panels also function to charge Lander electronics. That seems good news, but the team is still working to figure out which instruments can achieve some of their scientific goals, Altemus said.
This is part of a broader push to increase lunar exploration in preparation for planned human missions over the next decade. The Blue Ghost Lander at Firefly Aerospace arrived in the moon on March 2nd. Resilience Lander, a Japanese company Ispace, is on the way.
Artist's impression of the moon's Athena spaceship
NASA
This week, a private space mission was launched on the moon, aiming to reach the southernmost point we've ever visited on the moon. The Athena spacecraft, built by an intuitive US-based machine, will be released from NASA's Kennedy Space Center in Cape Canaveral, Florida at 12:17am on February 27th (7:17pm on February 26th). It will be installed on the SpaceX Falcon 9 rocket. Also, several other missions hitch on the same rocket, including expeditions that mine asteroids.
The intuitive machine became the first private company to succeed on the moon last year when Odysseus' spacecraft landed near the moon's Antarctica. The spacecraft's instruments remained in operation, but Odysseus made a troublesome landing, flipped over, limiting the amount of data the equipment could collect, and shortening the mission.
The company hopes for a cleaner landing as Athena begins its descent towards the end of March. The planned landing site is near the highest mountain on the moon, the lunar mewton, about 60 kilometers from Antarctica, and Athena's attempts have become the most southern approach to date. If the ship is successful, it will start a moon night and operate for several weeks on par with the moon in a day before it loses power.
Athena carries over 10 musical instruments and missions from both NASA and other private companies. That's not all. The Falcon 9, the same one that fires Athena at the moon, also carries three unrelated spacecraft. These are asteroid-controlled spacecraft from space company Astroforge, and the first mission of this kind will investigate potential minable metal space rocks later this year. You can also map water to the moon along with NASA's lunar satellite aboard, looking for future landing sites. The third spacecraft, built by epic aerospace, is designed to help other satellites move between orbits.
Once Athena lands, NASA instruments will excavate up to 1 meter into the lunar soil to sample it, then look at water sediments and other chemicals. NASA would like to know if these will be present in sufficient quantities for future astronauts to be used as part of the Artemis Moon Landing, which is planned for the agency to be released in 2027. It's there.
Several small rovers will also be released near the landing site, including the plant pot-sized Yaokirovers of Japanese company Dimon. The heavier 10kg mobile autonomous exploration platform (MAPP), built by Space Company Lunar Outspost, explores and creates 3D maps of landing sites, testing how the 4G phone network built by Nokia works in a Lunar environment. Masu. Sitting on a mapp will be a much smaller, ant-sized robot built by researchers at the Massachusetts Institute of Technology.
The intuitive machine deploys a suitcase-sized hopping robot called Grace. Grace runs a series of four hops, jumping into the air up to 100 meters, travelling a distance of about 200 meters until it lands in a deep, permanently shaded crater. Scientists have seen evidence that these areas do not get warmer than -170°C (-274°F), but have never been visited in person. Grace scans the bottom of this crater. This crater is scanned for about 45 minutes, about 20 meters below, before popping out again.
The bartender said, “We don't serve time travelers here.” A time traveler enters the bar.
OK, yes, you'll almost certainly regret starting this article with such a lame old joke. Most of us, at some point, have wanted to go back in time to fix a mistake or failure. But that's impossible, right?
Well, not necessarily. Albert Einstein's theory of general relativity suggests that time travel may actually be possible. We know that matter can bend space-time, and if we bend it enough we may be able to create time loops. Of course, there are many caveats, and researchers have yet to present a working time machine. But that didn't stop them from exploring the possibilities.
Here are five ways time travel could be possible, from sci-fi classics to surprising new ideas. It also introduces some thorny practical obstacles that need to be overcome.
1. Prepare the galaxy laser ring
The main problem with time travel is that nothing can travel faster than the speed of light, which is 299,792,458 meters per second. This speed limit maintains causation, the idea that the cause must always come before the effect. Thanks to a quirk of Einstein's special theory of relativity and the fact that space and time are intimately connected, traveling faster than the speed of light messes it up. If we could travel faster than light, we would travel back in time. But you can't do that.
The next best thing is to manipulate the fabric of space-time. in…
IIn the past, whenever I’ve written enthusiastically about the latest retro consoles, like the Nintendo Classic Mini: SNES or Analogue Duo, there have been a few comments below the article asking why people don’t just buy a Raspberry Pi mini computer, download emulators, and play their favorite games for next to nothing. My answer is usually ease of use and accessibility. When you buy a mini console, you get a plug-and-play product with no complicated setups or potential compatibility issues. Simple.
However, having recently purchased a Raspberry Pi to write an article about the beautiful PiDP-10 machine, I thought I’d check out its retro gaming capabilities as well. This is what I found.
Hardware
Raspberry Pi with case, SD card, and SD card reader Photo: Keith Stewart/The Guardian
To put together your retro machine, you’ll first need a Raspberry Pi computer. It’s a tiny PC built on a circuit board a little bigger than a credit card. There are currently two supported models: the Raspberry Pi 4 Model B (£34) and the newer Raspberry Pi 5 (£58), which has a more powerful processor and is better suited for emulating later consoles. I bought the 5 model on the Pi Hut site, which offers a decent starter kit including a compatible power adaptor and HDMI cable, a cute case to house the Pi in (with a little fan to cool the CPU), and an SD card, which you’ll need as the computer doesn’t have a built-in hard drive. The kit costs £94. However, the Raspberry Pi 4 is good enough to run emulators for old machines, so if you go for it, you’ll be ready for retro gaming for around £60.
emulator
Lakka emulator. Photo: Raqqa
Here’s where it gets a bit complicated. There are a number of retro gaming apps that are compatible with the Raspberry Pi, with the main contenders being RetroPie, Recalbox, Batocera and Lakka. All of these are essentially a collection of different, mostly open-source emulators that let you play games from a range of systems, from very early home computers to later consoles like the Dreamcast and PlayStation 2. Want to experience Manic Miner on Oric or Rainbow Islands on the Wonderswan? UtopiaCan you recreate the Dragon 32 games you made with your friend John in 1987? Now you can. It also supports MAME, which runs hundreds of classic arcade games. There are differences between the two, such as how the games run and how many configuration options you have. For example, you might want to tweak the visual settings to add realistic scanlines. Here is a very good comparison. hereHowever, most people agree that RetroPie is the most versatile.
It’s all very easy to do. First, connect the SD card to your PC or Mac using a USB SD card reader and download Raspberry Pi Imager. This is a small program that will install the operating system onto the card. It’s very user friendly and has three drop-down menus to choose from:[オペレーティング システムの選択]With the click of a button, you can designate your machine as a retro console and it will automatically download the emulators. Currently, your options are limited to either Recalbox for Model 5, or RetroPie or Recalbox for Model 4 (Retropie doesn’t have a native Model 5 version yet). To get anything else, you’ll need to download their own installation imagers separately and select your custom OS in the Raspberry Pi imager.
Don’t panic, there are plenty of guides online to help you solve this problem.
game
Rev your engines… in the classic 80s driving game Out Run. Photo: SEGA
Now, this is Really Here’s the complicated part. To run retro games on these emulators you need game ROMs – software versions of the original programs, chips or cartridges. Downloading them from ROM sites on the internet is effectively copyright infringement and illegal. “Computer games are protected from copying by intellectual property law,” explains Alex Tutty of law firm Sheridans. “Generally, in the UK and around the world, games are protected by copyright and cannot be copied without the owner’s permission.
“Copyright law has various exceptions, such as personal copying, but emulation of the games or making them available online is not permitted. Even if a game is discontinued, copyright remains in place even if it is not being used, so copying is not permitted.”
that teeth It’s possible to find games that have had their copyrights removed by their developers. These tend to be found on abandonware sites or software archives. (I won’t sue you if you download Utopia, but you might want to sue me if you play it.) In any case, I won’t tell you how to find ROMs, but I can tell you that it’s a risky business. Game files on unofficial sites might be full of viruses and malware, or they might simply not work, or be in a foreign language.
Getting the ROMs onto your Raspberry Pi from your computer where you downloaded them is also a bit complicated. The basic method is to plug the Raspberry Pi SD card into your PC and download the ROMs directly to the board, but there are more elegant solutions that use SD card shared folders or file manager apps. To be honest, I struggled with all of them.
Conclusion
Here’s how to build a retro gaming machine for under £100. I prefer the more expensive but legally clear methods – keeping your original console, buying a retro gaming compilation such as Sega Genesis Classics or Rare Replay, downloading digital versions of old games from sites such as Steam, Gog or the online store of your current gaming console, or buying a mini retro machine that runs fairly stable versions of your favourite games.
However, I’m a big fan of the Raspberry Pi, so I think it’s worth buying one and giving it a try. If you’re worried about downloading retro ROMs, Huge game library Anything made specifically for your device or downloaded Dos Box or later DosBox-X A program that lets you play hundreds of old PC games, including shareware. Alternatively, you can use your Raspberry Pi to access cloud-based gaming services such as: Xbox Cloud Gaming. you too Stream games from your PC to your Raspberry PiDiscovering games on new platforms is fun, and having something to run on a computer that fits in your pocket is a fascinating experience.
The recent focus in news has been on the progress of artificial intelligence (AI) in the past couple of years. ChatGPT and DALL·E are examples of AI models that many people associate with AI. AI tools are utilized by astronomers to analyze vast data sets, which would be impractical to manually go through. Machine Learning Algorithms (ML) are crucial for categorizing data based on predetermined parameters derived from previous studies. An example of ML usage is in the identification of elusive patterns in sky surveys by astronomers, though the limitations of this method in classifying objects in space are not thoroughly understood.
To address these limitations, a group of scientists led by Pamela Marchand-Cortes at the University of La Serena in Chile tested the capabilities of ML. They used ML models like Rotation forest, Random forest, and Logit Boost to categorize objects beyond the Milky Way galaxy based on their properties. The team aimed to see if ML could accurately categorize objects already manually classified. The challenge was in the dense region of sky obscured by dust in the Milky Way, known as the “Avoidance Zone.” The team’s experiment showed that ML had difficulty in categorizing objects in this challenging area.
The team gathered and analyzed data from X-ray images to manually identify objects and compare ML’s performance. ML correctly identified large objects like galaxies in only a few instances, showcasing its limitations. Despite the potential for ML to assist in studying obscured regions of the universe, the team recommended training AI models with diverse samples to enhance accuracy in future research.
This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.
Strictly Necessary Cookies
Strictly Necessary Cookie should be enabled at all times so that we can save your preferences for cookie settings.
