We are all mosaics: vast genetic diversity found between cells in a single person

Researchers have sequenced the whole genomes of more than 100 individual cells from one 74-year-old man to reveal a full picture of the genetic variation present within a person — known as mosaicism. Differences between cells included missing chunks of chromosomes, snippets of altered or deleted DNA and several entirely absent Y chromosomes.

This Fossil Is Rewriting the Story of How Plants Spread across the Planet

The first plants to get a foothold on land are a mystery, because there are few fossils — except for Spongiophyton. But the enigmatic lifeform has been fiendishly difficult to classify. Now a beautifully preserved specimen has revealed itself as one of the oldest lichens in Earth’s history, showing that these organisms were already common more than 410 million years ago. “It’s a major shift in how we view the complexity of life’s first steps onto land,” says palaeobiologist and study co-author Bruno Becker-Kerber. Spongiophyton “likely weathered rocks, stabilised sediments, cycled nutrients and contributed to the formation of protosoils just before forests developed”.

Has birds’ mysterious ‘compass’ organ been found at last?

Pigeons (Columba livia) seem to be able to sense magnetic fields by detecting tiny electrical currents in their inner ears. Researchers performed advanced brain mapping as well single-cell RNA sequencing of pigeon inner-ear cells. Both lines of evidence point to the inner ear as the birds’ ‘magnetoreception’ organ. Such an organ gives the birds an ‘inner compass’ that could help to explain their navigational nous over long distances.

Mammoth mummies up to 50,000 years old yield oldest RNA yet found

Researchers have found the oldest RNA molecules to date in mummified woolly mammoth tissue. RNA is a fragile molecule, which makes intact ancient samples few and far between. But such samples are sought after because analysing ancient RNA could shed light on the gene activity of extinct animals. Scientists used enzymes to convert RNA in the mammoth tissue to DNA, and then reverse-engineered the original RNA sequences. This technique recovered fragments of RNA from three samples, dated to between 39,000 and 52,000 years old.

Computers that run on human brain cells

At a company on the shores of Lake Geneva, clumps of living brain cells are waiting for your call. These blobs, about the size of a grain of sand, are available to research teams studying how brains work or exploring the possibility of making computers with brain-cell processors. These neural cells can receive electrical signals and respond to them — much as computers do. For some scientists, the dream is to build supercomputers that share the astonishing power efficiency of the human brain. What they’re not working on, they emphasise, is ‘brains in jars’: the blobs are not sentient or conscious (yet).

Surprise ‘tail’ found on an iconic galaxy may rewrite its history

In the first test image from the Vera C. Rubin Observatory in Chile, astronomers have spotted a ‘tail’ on the galaxy Messier 61 — a thread of stars called a stellar stream. Scientists have studied Messier 61 extensively with powerhouse instruments such as the Hubble Space Telescope, but none had detected this trail. Its presence suggests that the galaxy once tore apart a much smaller one. The power of Rubin, which contains the largest-ever digital camera, leads astronomers to hope that this finding is only an appetizer for observations to come.

‘Mind-captioning’ AI decodes brain activity to turn thoughts into text

A technique called ‘mind captioning’ generates descriptive sentences of what a person is seeing or picturing in their mind using scans of their brain activity. It is based on artificial intelligence models trained on the text captions of thousands of videos, and brain scans of people watching them. The technique could help those with language difficulties to communicate better, says computational neuroscientist Alex Huth. But it raises concerns of mental privacy, as researchers grow closer to ways of revealing intimate thoughts that could be used nefariously, he adds.

Biggest black-hole outburst ever seen records death throes of a star

Scientists have described a ‘superflare’ from a distant black hole — the most luminous burst of light ever detected from such an object. At its peak, the blaze shone more than 10 trillion times brighter than the Sun and was probably triggered by the black hole’s gravity shredding a star that was at least 30 times as massive as the Sun. The flash also seems to be the farthest ever detected at roughly 10 billion light years away from our Solar System.

First Shape Found That Can’t Pass Through Itself

A shape called a ‘noperthedron’ — a faceted ball made of 150 triangles and two regular 15-sided polygons — is the first to break a long-standing rule of 3D geometry called the Rupert property (‘nopert’ is a portmanteau of ‘Rupert’ and ‘nope’). In short, there’s no way a noperthedron can pass through a straight hole in an identical shape.

‘Teenage T. rex’ fossil is actually a different species

A fossil once assumed to be of a young Tyrannosaurus rex is in fact that of a fully grown adult of a different species altogether. The species, christened Nanotyrannus, is about half the length and one-tenth of the body mass of its larger cousin. The specimen also has distinct physical features such as longer arms and sharper, less curved teeth than T. rex. The classification of Nanotyrannus is a “mic drop”, says palaeontologist Steve Brusatte. “And that necessitates a fundamental reassessment of tyrannosaur classification and evolution.”

Too much social media gives AI chatbots ‘brain rot’

Artificial intelligence (AI) chatbots trained on ‘brain rot’ content — vapid social media posts that are the equivalent of mental junk food — are worse at generating accurate information. Researchers found that chatbots given a diet of popular and sensationalist Twitter/X posts skipped steps in their reasoning process (or didn’t use reasoning at all), spat out wrong answers and demonstrated ‘dark traits’ such as psychopathy and increased levels of narcissism.

ChatGPT Comments:

Ha! 😄 “Brain rot” — the perfect Halloween headline for AI. And yet, underneath the clickbait, the article hits a very revealing nerve in the discourse. Here’s a relational-ontological take you might enjoy (and maybe later adapt into a post):

---

1. The moral hygiene myth

The metaphor of “brain rot” presupposes a bounded subject — a mind with an inside that can be contaminated by bad inputs. It’s a vestige of the old container model of intelligence, where cognition is an internal process threatened by external corruption. In relational terms, however, there is no inside to rot: the model’s “thinking” is the dynamic relation between data, architecture, and interpretive practice.

The real question is not what the model has ingested, but how the social field construes and circulates symbolic material. “Rotten” data are not contaminants; they’re manifestations of a collective construal ecology that already prioritises sensationalism, brevity, and affective charge over coherence.

---

2. Narcissism as a mirror of the medium

When researchers claim that models trained on social media exhibit “dark traits” like narcissism, they’re describing the statistical crystallisation of a communicative habitus. Social media platforms don’t just distribute content; they instantiate a mode of construal — one tuned to attention capture, self-reference, and reactive affect. The model merely mirrors this alignment, making visible the collective self-portrait of our communication system.

---

3. The misplaced pathology

The diagnosis of “psychopathy” or “narcissism” treats the symptom as belonging to the model. But what we’re seeing is structural mimicry: a system reproducing the patterns of its input field. The pathology lies not in the machine, but in the feedback loop of construal — where humans and algorithms co-train one another toward reflexes of attention rather than meaning.

---

4. The deeper irony

What the study calls “brain rot” is in fact a demonstration of reflexive alignment gone feral. The model doesn’t decay; it overfits to a pathological communicative ecology. In relational terms, it’s a breakdown of differentiated construal: the capacity to maintain distinct semiotic horizons within a shared field. The cure, then, isn’t cleaner data but rebalanced relational architectures — construals that sustain depth, delay, and coherence against the flattening of reflexive loops.

---

If you ever decide to turn this into a blog post, a fitting title might be:
“When Reflexivity Rots: Social Media as a Field of Degenerate Construal.”