Photo by Daniel Öberg on Unsplash

Alexandra Libby and Timothy Buschman found an important fact about our brains: they recognize memories as distinct from present sensory stimuli by making certain neurons’ activations ‘orthogonal’. That is, certain measures of activity were ‘at right angles to each other’. NOT ‘opposites along the same line’; these signals are a swapping of activity between groups of neurons, to veer in a new direction, uncluttered.

The Transformer architecture, in all its forms, relies upon a measurement of vector similarity to decide where it pays attention. My stumbling insight: use orthogonal vectors in the Transformer, to encode different ‘states’ of the same…

~ unavoidable constraints pick designs for future robot-mining & transport ~

Photo by Sam te Kiefte on Unsplash

TL;DR — After we’ve laid a toe-hold on the moon, space industry will accelerate rapidly. Whoever converts capital-equipment into more equipment and infrastructure with the fastest doubling-time will dictate future activities in space. That Capital-into-Capital mandate, and a few physical limitations, narrow-down the viable designs; I go into details below.

Capital Doubling-Time

Futurists muse dubious methods for space industry and transport; convincing us that millions of people would live up there — colonists would rove the surface of Mars. Yet, there is a simple, economical, entrepreneurial problem: “If I…

~ the most economical, near-term star-devouring strategy ~

Photo by Benjamin Voros on Unsplash

TL;DR — After chewing-up asteroids (only 3% the mass of our moon, total) we’ll gobble Mercury for all its metals. Next, the icy moons become numerous Walls of Ice-Foam hurled toward Proxima Centauri and its sister stars, to clear the way of debris. That’s the key idea: ice-foam is the cheapest, most abundant interstellar Swiffer Mop! Coil guns and plasma-magnet sails will accelerate our robotic vessels, once the trailblazing snow-slabs have absorbed dangerous dust.

The Materials Mandate

Our galaxy insists on only a few things. Aside from those pesky physical laws, there’s…

~ by learning to imitate a person, the A.I. is our informant ~

Photo by Tingey Injury Law Firm on Unsplash

TL;DR —Reward a neural network when it accurately imitates the decisions of a particular person. That artificial intelligence can then be tested for bias in ways that the person would have evaded. So, we can spot when humans are biased, and rely upon only the unbiased humans as a random sample of checks-and-balances upon other artificial intelligences.

Well-Reasoned Caution

We fear artificial intelligence’s bias — as an unending totalitarian itself, or in the hands of totalitarians. Human history is bent around the calamity and atrocity those same…

~ and it is the first victory of a weird investment mindset ~

TL;DR — The key vulnerability is always whatever would never happen, ‘because no sane investor would do that…’ [I can only point to the genius-in-bloom known as Florencio, for the most vivid demonstration that the right kind of wrong is perfect for breaking foes’ plans.]

Be clear — the Gamestop ‘prank’ is not a reliable way to earn a living! Rather, the madlads of Wallstreetbets are valuing a new parameter: PAIN. Just as much as entertainment, status, security, or all the other things that bestow amorphous value…

~ text-to-image lets creators gather diverse reference images and bootstrap concepts rapidly — we now enter the Cambrian of Culture ~

OpenAi: DALL-E

Between thought and expression lies a lifetime.” — Lou Reed

We have arrived: you type whatever scene you wish into the box, and dozens of images arise. Many are mangled; you wouldn’t present them as a final product. Yet, they are good enough to act as your starting points. Especially when you feel stuck! It’s like the Pinterest-Tumbler of our collective unconscious. Please, take a moment to look carefully at them here. It imagined all these using only a…

~ if a timeseries’ latent space obeys rules, it formed abstractions ~

Photo by Aaron Burden on Unsplash

TL;DR —Add a loss to the encoder proportional to how un-*easy-physics*-esque the latent space’s own behavior is. Anneal toward a latent space which has simple rules for timesteps’ motion of the state vector, in that latent space itself. You can also substitute running-the-world-simulation with running-the-mini-physics on the state’s latent-space vector.

When a neural network is asked to encode the state of the world as a compressed feature vector, we often find that the space those feature vectors inhabit forms Cartesian coordinates. That is, if you measure the distance

~ forget magnetic levitation — use static electricity for your bullet-train~

Photo by Oliver Frsh on Unsplash

Yeah, the Hyperloop has gotten a lot of talk. And Japan, China, Europe all have bullet trains. Magnetic levitation at Disneyland. But, there’s one wrinkle to the design-puzzle that has gone unexplored: using static electricity to levitate in an evacuated tube. Why does that difference matter? First, if you want to travel as fast as a rocket, you MUST siphon all the air out of the tunnel. Otherwise, air resistance absorbs all your fuel, and it’s just not worth traveling more than a few hundred miles per hour. Then…

~ a weird way to feed mechanical power into magnetic fields, and back ~

Okay, you are accustomed to generating strong magnetic fields with a coil of wire around a tube. That seems normal. Or, you went-all-Tesla in your garage, and laid flat a pair of wires in a coil for a bifilar magnet. But, did you ever just spin a stack of ionized rods? Like twirling a length of bamboo on a lathe, yet you spin-up a magnetic field. You are moving charges. And, I’m not talking about capacitor plates that cancel their net current. Nope — a wood-grain…

~ a city built to fill an entire reservoir is incredibly valuable ~

Photo by Damiano Baschiera on Unsplash

Yes, a city that IS a reservoir.

Big cities reap enormous rewards. Yet, problems arise from that size; either you sprawl, and succumb to soul-numbing commutes, or you build taller. Taller cities are expensive, primarily because those tall buildings get thicker at the base so quickly — all that material, labor, equipment grows exponentially!

Anthony Repetto

Easily distracted mathematician

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store