Science™ in the news

[Diogenes]

A government-backed review spanning nine years found fluoride exposure linked to lower IQs in children, sparking fresh debates about its safety.

The study showed even small increases in fluoride levels could have noticeable impacts on intelligence, especially during pregnancy and early childhood.

Fluoride is still celebrated as a "public health victory," but maybe it's time we question that.

https://www.cnn.com/2025/01/06/health/children-higher-fluoride-levels-lower-iqs-government-study/index.html

 

[Diogenes]

Researchers at Peking University have reportedly cracked the code for DNA data storage, squeezing 215,000 terabytes into a single gram with a new "epi-bits" method.

Instead of traditional, costly DNA synthesis, this technique uses enzymatic methylation to "print" data onto reusable DNA strands—think binary, but in biology.

Volunteers encoded high-res images of a tiger and panda onto DNA, proving it’s accessible, scalable, and mind-blowingly efficient.

Who needs hard drives when you’ve got nature’s blueprint?

MSN

 

[Diogenes]

Jensen Huang introduced the GB200 NVL72, a data center powerhouse packing 72 Blackwell GPUs, 1.4 exaFLOPS of compute, and 130 trillion transistors.

This "superchip" enables test-time scaling, a groundbreaking approach that lets AI reason in real time, mimicking human thought.

Huang highlighted AI agents as a multi-trillion dollar opportunity, with NVIDIA leading the charge.

From NeMo for deploying AI agents to cutting-edge GPUs, NVIDIA is cementing itself as the backbone of the AI economy across industries.

Nvidia's Jensen Huang Unveils Hopper Successor 'Blackwell' at GTC -- Pure AI

Nvidia's Chief Executive Officer Jensen Huang kicked off his company's annual GPU Technology Conference (GTC), dubbed 'the Woodstock of AI,' with a keynote that introduced the Blackwell platform and more.

pureai.com

 

[Diogenes]

Researchers have cracked the code for simulating complex systems—like atomic chains—using a groundbreaking photonic chip made of lithium niobate.

This tech slashes the need for ultra-high frequencies, dropping them from 100 GHz to just 10 MHz, making quantum simulations faster, simpler, and way more efficient.

It’s like upgrading quantum physics from rocket science to something a bit more plug-and-play.

 

[Diogenes]

SCIENCE™ EXPLAINS DEMOCRATS​

Nose-picking can introduce harmful bacteria, such as Chlamydia pneumoniae, into the body, posing serious health risks.

The inner lining of the nose contains a rich network of blood vessels and olfactory nerves, which have direct connections to the brain through the olfactory bulb.

When the nasal mucosa is damaged by frequent picking, it creates a breach in this natural barrier, allowing bacteria to enter the bloodstream or travel along nerve pathways to the brain.

Studies have shown that Chlamydia pneumoniae can infiltrate the central nervous system and trigger neuroinflammation. This process may lead to the formation of amyloid plaques, which are hallmarks of Alzheimer’s disease.

Also, repeated nasal trauma can impair the nose's ability to filter out pathogens, increasing the risk of infections like sinusitis or brain abscesses. To protect brain health, it’s important to maintain nasal hygiene without causing trauma by using gentle saline rinses instead of picking.

Dr. Simon Hundeshagen

https://twitter.com/x/status/1876689625722589459

 

[Diogenes]

Physicists have theorized a bizarre new type of particle—paraparticles—that break the rules governing all known particles.

Unlike fermions (like electrons) or bosons (like photons), paraparticles follow their own strange exclusion rules.

Here’s the kicker: these could be created in quantum computers and may already exist in nature.

Similar discoveries, like anyons in 1D systems, are already reducing errors in quantum computing.

This breakthrough hints at a future where quantum tech becomes far more reliable—and raises big questions about what unseen particles are out there.

https://news.rice.edu/news/2025/mathematical-methods-point-possibility-particles-long-thought-impossible

 

[Into the Night]

A government-backed review spanning nine years found fluoride exposure linked to lower IQs in children, sparking fresh debates about its safety.

The study showed even small increases in fluoride levels could have noticeable impacts on intelligence, especially during pregnancy and early childhood.

Fluoride is still celebrated as a "public health victory," but maybe it's time we question that.

https://www.cnn.com/2025/01/06/health/children-higher-fluoride-levels-lower-iqs-government-study/index.html

Fluoride is not a chemical. IQ is a meaningless random number.

 

[Into the Night]

Researchers at Peking University have reportedly cracked the code for DNA data storage, squeezing 215,000 terabytes into a single gram with a new "epi-bits" method.

Instead of traditional, costly DNA synthesis, this technique uses enzymatic methylation to "print" data onto reusable DNA strands—think binary, but in biology.

Volunteers encoded high-res images of a tiger and panda onto DNA, proving it’s accessible, scalable, and mind-blowingly efficient.

Who needs hard drives when you’ve got nature’s blueprint?

MSN

Hard drives are faster.

 

[Diogenes]

Fluoride is not a chemical. IQ is a meaningless random number.

Yes, fluoride is indeed a chemical. Specifically, it is the anion of fluorine, a chemical element, and is commonly found in compounds like sodium fluoride (NaF) or calcium fluoride (CaF₂).


@Grok

 

[Into the Night]

Jensen Huang introduced the GB200 NVL72, a data center powerhouse packing 72 Blackwell GPUs, 1.4 exaFLOPS of compute, and 130 trillion transistors.

This "superchip" enables test-time scaling, a groundbreaking approach that lets AI reason in real time, mimicking human thought.

Huang highlighted AI agents as a multi-trillion dollar opportunity, with NVIDIA leading the charge.

From NeMo for deploying AI agents to cutting-edge GPUs, NVIDIA is cementing itself as the backbone of the AI economy across industries.

Nvidia's Jensen Huang Unveils Hopper Successor 'Blackwell' at GTC -- Pure AI

Nvidia's Chief Executive Officer Jensen Huang kicked off his company's annual GPU Technology Conference (GTC), dubbed 'the Woodstock of AI,' with a keynote that introduced the Blackwell platform and more.

pureai.com

So...it's as smart as a Democrat? Not impressive.

 

[Into the Night]

Researchers have cracked the code for simulating complex systems—like atomic chains—using a groundbreaking photonic chip made of lithium niobate.

This tech slashes the need for ultra-high frequencies, dropping them from 100 GHz to just 10 MHz, making quantum simulations faster, simpler, and way more efficient.

It’s like upgrading quantum physics from rocket science to something a bit more plug-and-play.

There is no such thing as a 'quantum computer'.

 

[Diogenes]

So...it's as smart as a Democrat? Not impressive.

We can infer that Superchips, particularly in the context of automotive tuning, are "smart" in the sense that they:

• Use advanced software to enhance vehicle performance with minimal hardware modification.
• Offer customization and real-time feedback options for vehicle owners, which are characteristics of smart technology.

However, this "smartness" is more about the functionality and application of the technology rather than the chips themselves possessing any form of autonomous intelligence. They are smart in the sense that they allow for smarter vehicle management and performance optimization.


@Grok

 

[Diogenes]

There is no such thing as a 'quantum computer'.

A quantum computer is a type of computer that uses the principles of quantum mechanics to perform operations on data. Here's a breakdown of how it differs from classical computers:

Key Features:

1. Qubits vs. Bits:
   • Classical computers use bits as their basic unit of information, which can be either 0 or 1.
   • Quantum computers use qubits (quantum bits). Unlike bits, qubits can exist in a state of 0, 1, or both 0 and 1 simultaneously due to a property called superposition.
2. Superposition:
   • Superposition allows qubits to represent multiple states at once, enabling quantum computers to process a vast number of possibilities simultaneously.
3. Entanglement:
   • Qubits can be entangled, meaning the state of one qubit is directly related to another, no matter the distance between them. This phenomenon can be used to correlate operations across qubits, providing a computational advantage for certain algorithms.
4. Quantum Gates:
   • Instead of traditional logic gates, quantum computers use quantum gates to manipulate qubits. These gates can change the state of qubits in ways that leverage superposition and entanglement.
5. Quantum Algorithms:
   • Algorithms like Shor's algorithm for factoring large numbers or Grover's algorithm for searching unsorted databases are much more efficient on quantum computers than on classical ones.

Applications:

• Cryptography: Quantum computers could potentially break many of the current encryption methods, leading to both new threats and new methods of secure communication (quantum cryptography).
• Drug Discovery: Simulating molecular structures at the quantum level could significantly speed up drug discovery processes.
• Optimization Problems: Quantum computing could solve complex optimization problems in logistics, finance, or supply chain management much faster than classical computers.
• Material Science: Understanding and designing new materials with specific properties.

Challenges:

• Error Correction: Quantum states are very fragile; they can decohere (lose their quantum properties) due to interaction with the environment, leading to errors in computation.
• Scalability: Creating and maintaining large numbers of qubits with high fidelity is a significant technical challenge.
• Temperature: Most quantum computers operate at temperatures near absolute zero to reduce thermal noise.

In summary, quantum computers promise a leap in computing power for certain types of problems by leveraging quantum mechanical phenomena like superposition and entanglement, but they also come with unique challenges in terms of hardware and software design.

@Grok