Friday, December 13, 2024

Tuesday, December 10, 2024

Google's new quantum chip cuts key error rate

In case that doesn’t sound exciting:

Their 105-qubit quantum processor, Willow, performed in less than five minutes a computation that would take one of today's fastest supercomputers 10 septillion years — about a quadrillion times longer than the universe has been around.”

https://www.axios.com/2024/12/09/google-quantum-computer-errors

Tesla STUNS With Optimus Robot Update

Optimus can avoid falling better than we can!

https://www.youtube.com/watch?v=KNsgUaiNCxQ

Tuesday, November 19, 2024

Wednesday, October 30, 2024

Game-Changing Tech Turns Dry Desert Air Into Lifesaving Water

Pretty amazing:

If I have one square meter, which is around three feet by three feet, we can generate about a gallon of water per day in Las Vegas, and up to three times more in humid environments.

https://scitechdaily.com/game-changing-tech-turns-dry-desert-air-into-lifesaving-water/

Atlas Goes Hands On

The new Atlas is definitely impressive, looking and working like a proper science fiction robot...but the way it moves is a bit creepy:

https://www.youtube.com/watch?v=F_7IPm7f1vI

Sunday, October 20, 2024

Saturday, October 12, 2024

Recent Alzheimer’s studies

Restoring hippocampal glucose metabolism rescues cognition across Alzheimer’s disease pathologies: https://www.science.org/doi/10.1126/science.abm6131

APOE-Genotype and Insulin Modulate Estimated Effect of Dietary Macronutrients on Cognitive Performance: Panel Analyses in Nondiabetic Older Adults at Risk of Dementia: https://pubmed.ncbi.nlm.nih.gov/37778510/

Precision Nutrition for Alzheimer's Prevention in ApoE4 Carriers: https://pubmed.ncbi.nlm.nih.gov/33921683/

Wednesday, September 18, 2024

Sam Altman Teases Orion (GPT-5) 🍓 o1 tests at 120 IQ 🍓 1 year of PHD work done in 1 hour...

This is stunning: It appears AI took an hour to write a program based on a scientific paper that took the PhD author a year to do the same thing! 

https://youtu.be/nZHGYGUjo9Q?si=-rA0DqiYrM-SBpsF

Revolutionary Catalyst Uses Sunlight To Turn Greenhouse Gases Into Valuable Chemicals

https://scitechdaily.com/revolutionary-catalyst-uses-sunlight-to-turn-greenhouse-gases-into-valuable-chemicals/

Harnessing the Helix: First-of-Its-Kind “Springy” Chiral Interface Boosts Solar Cell Efficiency

https://scitechdaily.com/harnessing-the-helix-first-of-its-kind-springy-chiral-interface-boosts-solar-cell-efficiency/

Goodbye Traditional Farming? German Scientists Harvest Protein From Air and Water

https://scitechdaily.com/goodbye-traditional-farming-german-scientists-harvest-protein-from-air-and-water/

Unlocking AI’s Future With a New Molecular Computing Breakthrough

https://scitechdaily.com/unlocking-ais-future-with-a-new-molecular-computing-breakthrough/

Monday, September 2, 2024

Tuesday, August 20, 2024

Fish oil supplements on heart and brain

An analysis of the studies on the risks and benefits of fish oil supplements:

Alzheimer’s: https://youtu.be/NScltXkIO44?si=BkDqBgO5q4j2a4VC

Heart health: https://youtu.be/T6HSAhG7p1M?si=V4QbVLVE86SsXbn3

The latter suggests 840 mg daily has no contraindications.

Reversing Alzheimer's: New Research Improves Cognition & Protects Brain Health | Dr.Heather Sandison

My woo meter is twitching, but this sounds encouraging:

https://www.youtube.com/watch?v=baQSf_9l-uk

Artificial Intelligence Predicts Earthquakes With Unprecedented Accuracy

This line woke me up:

Developed by researchers at The University of Texas at Austin, the AI algorithm correctly predicted 70% of earthquakes a week before they happened

https://scitechdaily.com/artificial-intelligence-predicts-earthquakes-with-unprecedented-accuracy/

Revolutionizing Lens Design: AI Cuts Months of Work Down to a Single Day

The topic isn’t interesting, but it’s an example of how AI is accelerating technological development:

https://scitechdaily.com/revolutionizing-lens-design-ai-cuts-months-of-work-down-to-a-single-day/

Thursday, August 15, 2024

Juicier, Glossier, Better: Superior Strawberries Unlocked Through Genetics

But it’s the FLAVOR that matters most, you numbskulls!

https://scitechdaily.com/juicier-glossier-better-superior-strawberries-unlocked-through-genetics/

Low Testosterone in Men Linked to Increased Risk for Death

The data showed that only men with low total testosterone concentrations had higher risks for all-cause mortality. A key finding was that men with a testosterone concentration below 7.4 nmol/L (<213 ng/dL) had a higher risk for all-cause mortality, regardless of LH concentration. Men with a testosterone concentration below 5.3 nmol/L (<153 mg/dL) had an increased risk of cardiovascular death.

https://scitechdaily.com/low-testosterone-in-men-linked-to-increased-risk-for-death/

Friday, August 2, 2024

Teens invent remarkable device while searching for way to save community: 'Can be implemented anywhere in the world'

Plasma fertilizer:

https://www.yahoo.com/tech/teens-invent-remarkable-device-while-180000437.html

This Ultra-Thin Lightsail Could Tow Tiny Spacecraft to the Nearest Stars

https://singularityhub.com/2024/07/31/this-ultra-thin-lightsail-could-tow-a-tiny-spacecraft-to-the-nearest-stars/

A Massively Strong Beetle Just Inspired a Lightweight Flying Robot

https://singularityhub.com/2024/08/01/a-massively-strong-beetle-just-inspired-a-lightweight-flying-robot/

Is AI About to Run Out of Data? The History of Oil Says No

A rather startling statistic:

An estimated 96% to 99.8% of all online data are inaccessible to search engines—for example, paywalled media, password-protected corporate databases, legal documents, and medical records, plus an exponentially growing volume of private cloud storage. In addition, the vast majority of printed material has still never been digitized—around 90% for high-value collections such as the Smithsonian and U.K. National Archives, and likely a much higher proportion across all archives worldwide.

https://time.com/7006382/ai-training-data-oil/

Revolutionary Organic Solar Cell Coating Boosts Efficiency and Cuts Costs

https://scitechdaily.com/revolutionary-organic-solar-cell-coating-boosts-efficiency-and-cuts-costs/

The AI boyfriend business is booming

I predicted this would happen, since an AI programmed to be your perfect mate will inevitably have an advantage. But I didn’t think it would happen so quickly for women. In hindsight, I should have, because AI doesn’t have a realistic human body yet (which is a bigger appeal for men), and communication and empathy are more important for women:

Thursday, August 1, 2024

Anti-Aging Treatment Breakthrough: Japanese Scientists’ Regenerative Gene Transfer Success

https://scitechdaily.com/anti-aging-treatment-breakthrough-japanese-scientists-regenerative-gene-transfer-success/

Artificial Investment?

It’s no secret: Investors and companies are pouring billions into AI. 

 

Venture capitalists have plowed $12 billion into generative AI startups so far this year. Elon Musk claims his company xAI will train new models on a staggering 100,000 of Nvidia’s latest H100 GPUs; Meta is reportedly buying some 350,000 more. (In perspective, the world’s fastest supercomputer, Frontier, boasts a mere 38,000 GPUs.) Alphabet, Microsoft, and Amazon are also building out enormous AI server farms. And this spending shows no signs of slowing.

 

Goldman Sachs says outlays on AI infrastructure could total $1 trillion over the next few years—a number on par with annual US military spending or the GDP of the NetherlandsBut there are strings attached: Big investment is tied to expectations of big revenue and profits. Eighteen months into the boom, investors are beginning to review the latter.

 

Some companies are clearly knocking it out of the park. Nvidia, which commands 80 percent of the AI chip market, is enjoying a historic run. The chipmaker has consistently posted revenue and profits beyond the market’s expectations, and in late June, it was (briefly) the most valuable company in the world, beating out Microsoft and Apple. (The stock has fallen off since then, but it’s still up some 140 percent year-to-date.)

 

But not everyone is raking it in like Nvidia. If Nvidia is selling “picks and shovels” for an AI gold rush, those using Nvidia’s equipment are still digging for gold. Exactly when they’ll strike it rich and how much they’ll unearth is a matter of speculation.

 

Though OpenAI is reportedly on pace to make $3.4 billion annually, an impressive number compared to last year, its costs are even greater. The Information recently reported the company is set to lose $5 billion this year and may need to seek new investment within the next 12 months. The publication also wrote that Anthropic will burn $2.7 billion in 2024.

 

The biggest players, like Alphabet and Microsoft, have deeper pockets. But driven by AI, their capital expenditures are growing fast. Alphabet’s capex spending is on pace to hit $49 billion this year, an increase of 84 percent compared to its average over the last half decade. Investors are increasingly scrutinizing the impact of these investments too. The companies’ cloud offerings—the huge server farms they rent to those building and running AI models and products—are the most obvious revenue-makers. But the sustainability of those revenues is dependent on the success of AI products.

 

And revenue from those products is lagging investment. This gap, which is widening, is what Sequoia Capital’s David Cahn calls the “$600 billion question.” That’s the difference between infrastructure investment and revenue in the industry. Barclays analysts put it like this: The industry is building enough infrastructure to support 12,000 ChatGPTs. While the technology is impressive, customer demand is unlikely to support that kind of supply anytime soon.

 

But the spending is also a bet on future performance improvements. This line of thinking suggests that if today’s capabilities aren’t enough to hook the world on AI, tomorrow’s will be. And to get to the next level—which will only be realized by bigger models trained on more (and better) data—companies need more computing power.

 

Anthropic CEO and cofounder, Dario Amodei, has said models being trained today already cost upwards of $1 billion. By next year, that number could be $10 billion, and in the years following, it could reach $100 billion—in line with the amount Microsoft is said to be spending on its 2028 AI supercomputer, Stargate. It's an eye-watering price tag. But Amodei thinks that if algorithms and chips continue to improve as they have in recent years, then there’s a chance those future AI models could be “better than most humans at most things.”

 

FOMO is another big driver. The CEOs of Alphabet and Microsoft have made that much clear. In a recent earnings call, Sundar Pichai said, “the risk of underinvesting is dramatically greater than the risk of overinvesting for us here.” And in a New York Times profile, Satya Nadella is described as being motivated by the desire to avoid missing the boat, as the company did with the internet in the early 2000s and smartphones several years later.

 

It seems clear the technology will have an impact—whether it’s through productivity boosting AI assistants or scientific discovery—and the impact’s size will scale with the capabilities of the models driving it. But exactly how big a splash it will make, how soon, and how this will compare to current investment isn’t clear, even to those at the helm.

 

“Of course, it’s possible…that all of this will be a bust. The models don’t turn out to be that powerful,” Amodei said recently. “That’s not my bet. That’s not what I think is gonna happen. What I think is gonna happen is that these models will produce a great deal of revenue. …That’s the bullish scenario that I’m betting on by leading this company.”

 

“But I’m not sure. It could go the other way. I don’t think anyone knows.”

Mayo Clinic AI Uncovers Hidden Brain Patterns to Spot Early Dementia

https://scitechdaily.com/mayo-clinic-ai-uncovers-hidden-brain-patterns-to-spot-early-dementia/

Game-Changing Advances in All-Solid-State Lithium Battery Technology

https://scitechdaily.com/game-changing-advances-in-all-solid-state-lithium-battery-technology/

Breakthrough in Anti-Aging: IL-11 Deactivation Boosts Lifespan by 25%

Now this is very interesting indeed:

https://scitechdaily.com/breakthrough-in-anti-aging-il-11-deactivation-boosts-lifespan-by-25/

Tuesday, July 30, 2024

Faster Than a Speeding Photon: How Tachyons Challenge Modern Physics

Oh, this is interesting:

https://scitechdaily.com/faster-than-a-speeding-photon-how-tachyons-challenge-modern-physics/

I asked Claude about the technological potential of harnessing tachyons, assuming they're actually real, and it said this:

While tachyons remain hypothetical and their existence would challenge our current understanding of physics, if they were to exist and we could harness them, they could potentially enable some fascinating technological applications. However, it's important to note that this is highly speculative and would require significant changes to our understanding of physics. Here are some potential applications:

  1. Faster-Than-Light (FTL) Communication:

    • Instantaneous communication across vast distances in space.
    • Could revolutionize space exploration and inter-planetary communication.
  2. Time Messaging:

    • Theoretical ability to send messages into the past, though this raises causality paradoxes.
  3. Advanced Computing:

    • Quantum computers using tachyons could potentially perform calculations at speeds far beyond current limitations.
  4. Energy Production:

    • Tachyons, having imaginary mass, might be a source of exotic energy with unique properties.
  5. Propulsion Systems:

    • FTL space travel, dramatically reducing travel time across the solar system or even to other stars.
  6. Precognitive Sensors:

    • Devices that could theoretically detect events before they occur, based on tachyons' supposed ability to move backwards in time.
  7. Exotic Matter Creation:

    • Tachyons could be used to create or manipulate forms of matter with properties we currently consider impossible.
  8. Advanced Imaging Technologies:

    • Potential to view objects or events distant in space or time.
  9. Causal Isolation Devices:

    • Theoretical shields against causality violations, protecting regions of spacetime.
  10. Temporal Phase Shifting:

    • Devices that could move objects slightly out of phase with normal time flow.
  11. Superluminal Data Storage:

    • Information storage systems with instant access regardless of physical distance.
  12. Tachyonic Materials Engineering:

    • Creation of materials with exotic properties for construction or manufacturing.

It's crucial to emphasize that these ideas are purely speculative and based on properties attributed to hypothetical tachyons. The existence of tachyons would fundamentally challenge our understanding of causality and the nature of time itself. Many of these concepts, especially those involving time travel or precognition, would introduce severe logical paradoxes.

Current mainstream physics does not support the existence of tachyons, and there is no experimental evidence for them. In most modern physical theories, the appearance of tachyons usually indicates an instability in the theory rather than the prediction of a real particle.

Then I asked it to read the above link, and asked if this would change its assessment. Claude replied:

Thank you for providing that article. Yes, this new research does change my assessment of tachyons in some significant ways. Here are the key updates based on this recent study:

  1. Resolving previous inconsistencies: The researchers have addressed several longstanding issues with tachyon theory by incorporating both past and future states into the boundary conditions. This approach resolves problems like the instability of the ground state, observer-dependent particle numbers, and negative energy values.

  2. Mathematical consistency: The new framework makes tachyon theory mathematically consistent within quantum mechanics, which was not the case before.

  3. New type of quantum entanglement: The expanded boundary conditions suggest a novel form of quantum entanglement that mixes past and future states, which isn't present in conventional particle theory.

  4. Role in matter formation: The researchers propose that tachyons may play a crucial role in the spontaneous symmetry breaking process responsible for matter formation. They suggest that Higgs field excitations might have traveled at superluminal speeds in the vacuum before symmetry was broken.

  5. Shift in scientific perspective: This work indicates that tachyons are not necessarily ruled out by special relativity, as was previously thought. Instead, they might help us better understand the causal structure of the theory.

  6. Future-influencing-past concept: The research reinforces the idea that future states can influence the present in quantum physics, which was previously considered an unorthodox interpretation.

While this research represents a significant theoretical advancement, it's important to note that tachyons remain hypothetical particles. There is still no experimental evidence for their existence. However, this work opens up new avenues for research and potentially changes how we might look for evidence of tachyons or related phenomena in the future.

This study demonstrates that our understanding of fundamental physics is still evolving, and concepts once thought impossible or inconsistent might find new life through innovative theoretical approaches.


Is AI Funnier Than Humans? Research Suggests Yes

They don't include the jokes, damn it, but this is another topic people thought would be among the last for AI to best humans in:

https://scitechdaily.com/is-ai-funnier-than-humans-research-suggests-yes/

This exciting NEW TECH will change the energy game FOREVER!

A number of intriguing developments:

https://youtu.be/kduR_4yYi9o?si=ARdYXBDx81kScr2G

Wednesday, June 12, 2024

Iron Power: Revolutionizing Batteries With Earth’s Most Abundant Metal

https://scitechdaily.com/iron-power-revolutionizing-batteries-with-earths-most-abundant-metal/

First-of-Its-Kind Test Can Predict Dementia up to Nine Years Before Diagnosis

The findings showed that the model had accurately predicted the onset of dementia up to nine years before an official diagnosis was made, and with greater than 80% accuracy. In the cases where the volunteers had gone on to develop dementia, it was also found that the model could predict within a two-year margin of error exactly how long it would take that diagnosis to be made.

fMRI is a non-invasive medical imaging tool, and it takes about 6 minutes to collect the necessary data on an MRI scanner, so it could be integrated into existing diagnostic pathways, particularly where MRI is already used.”

https://scitechdaily.com/first-of-its-kind-test-can-predict-dementia-up-to-nine-years-before-diagnosis/

How gravity batteries could change the world

https://youtu.be/kuVjkL9XYVI?si=qPLz2ldiLWz58GUa

Quantum Teleportation Becomes Reality on Active Internet Cables

https://scitechdaily.com/quantum-teleportation-becomes-reality-on-active-internet-cables/