Sometimes what is on the page is ambiguous. Imagine a scan where the dot over the i is missing in a word like "this". What's on the page is "thls" but to transcribe it that way would be an error outside of forensic contexts.
I am reminded it's basically impossible to read cursive writing in a language you don't know even if it's the same alphabet.
I can't help but wonder if it's a bit of self-aware humour about "scientific looksmaxing". Symmetry is involved in attractiveness but symmetry alone can only carry you so far.
yeah i mean i kind of realised that you cant really rate faces based on a bunch of mathematical params and expect it to still be very accurate; but maybe my opinion of attractiveness is skewed
The issue was not with PIO. It was with the fact that both rp2040 and rp2350 only support usb1.1, which doesn't have enough bandwidth to do uncompressed ~320x240x16bpp@60Hz.
On 24 January 1926, the British ship SS Antinoe was damaged by a hurricane and was at risk of sinking. The American ship SS President Roosevelt assisted in rescue and docked in Plymouth, England. A photograph of the rescue was published in both London and New York the next day. The quickness with which this photo reached New York apparently caused such a sensation that Science and Invention magazine published the linked infographic on how it was accomplished; briefly: the image was sent as a digital bitmap by transatlantic telegraph cable.
There's a synchronous and instantaneous nature you don't find in modern designs.
The image is not stored at any point. The receiver and the transmitter are part of the same electric circuit in a certain sense. It's a virtual circuit but the entire thing - transmitter and receiving unit alike - are oscillating in unison driven by a single clock.
The image is never entirely realized as a complete thing, either. While slow phosphor tubes do display a static image, most CRT systems used extremely fast phosphors; they release the majority of the light within a millisecond of the beam hitting them. If you take a really fast exposure of a CRT display (say 1/100,000th of a second) you don't see the whole image on the photograph - only the most recently few drawn lines glow. The image as a whole never exists at the same time. It exists only in the persistence of vision.
Just wanted to add one thing, not as a correction but just because I learned it recently and find it fascinating. PAL televisions (the color TV standard in Europe) actually do store one full horizontal scanline at a time, before any of it is drawn on the screen. This is due to a clever encoding used in this format where the TV actually needs to average two successive scan lines (phase-shifted compared to each other) to draw them. Supposedly this cancels out some forms of distortion. It is quite fascinating this was even possible with analogue technology. The line is stored in a delay line for 64 microseconds.
See e.g.: https://www.youtube.com/watch?v=bsk4WWtRx6M
At some point, most NTSC TVs had delay lines, too. A comb filter was commonly used for separating the chroma from the luma, taking advantage of the chroma phase being flipped each line. Sophisticated comb filters would have multiple delay lines and logic to adaptively decide which to use. Some even delayed a whole field or frame, so you could say that in this case one or more frames were stored in the TV.
If a motion adaptive 3d comb filter (which requires comparing successive frames) was present on a TV, you can bet that it would be plastered all over the marketing material for the TV.
You can decode a PAL signal without any memory, the memory is only needed to correct for phase errors. In SECAM though, it's a hard requirement because the two color components, Db and Dr, are transmitted on alternating lines, and you need both on each line.
It doesn’t begin at the transmitter either, in the earliest days even the camera was essentially part of the same circuit. Yes, the concept of filming a show and showing the film over the air existed eventually, but before that (and even after that, for live programming) the camera would scan the subject image (actors, etc) line-by-line and down a wire to the transmitter which would send it straight to your TV and into the electron beam.
In fact in order to show a feed of only text/logos/etc in the earlier days, they would literally just point the camera at a physical object (like letters on a paper, etc) and broadcast from the camera directly. There wasn’t really any other way to do it.
Our station had an art department that used a hot press to create text boards that were set on an easel that had a camera pointed at it. By using a black background with white text you could merge the text camera with a camera in the studio and "super-imposed the text into the video feed.
"And if you tell the kids that today, they won't believe it!"
The very first computers (Manchester baby) used CRTs as memory - the ones and zeros were bright spots on a “mesh” and the electric charge on the mesh was read and resent back to the crt to keep the ram fresh (a sorta self refreshing ram)
Yes, but those were not the standard kind of CRTs that are used in TV sets and monitors.
The CRTs with memory for early computers were actually derived from the special CRTs used in video cameras. There the image formed by the projected light was converted in a distribution of charge stored on an electrode, which was then sensed by scanning with an electron beam.
Using CRTs as memory has been proposed by von Neumann and in his proposal he used the appropriate name for that kind of CRT: "iconoscope".
DRAM memories made with special CRTs with memory have been used for a few years, until 1954. For instance the first generation of commercial electronic computers made by IBM (scientific IBM 701 and business-oriented IBM 702) have used such CRTs.
Then the CRT memories have become obsolete almost instantaneously, due to the development of magnetic core memories, which did not require periodic refreshing and which were significantly faster. The fact that they were also non-volatile was convenient at that early time, though not essential.
Today, due to security concerns, you would actually not want for your main memory to be non-volatile, unless you also always encrypt it completely, which creates problems of secret key management.
So CRT memories have become obsolete several years before the replacement of vacuum tubes in computers with transistors, which happened around 1959/1960.
Besides CRT memories and delay line memories, another kind of early computer memory that has quickly become obsolete was the memory with magnetic drums.
In the cheapest early computers (like IBM 650), the main memory was not a RAM (i.e. neither a CRT nor with magnetic cores), but a magnetic drum memory (i.e. with sequential periodic access to data).
Yeah it super weird that while we struggle with latency in the digital world, storing anything for any amount of time is an almost impossible challenge in the analog world.
ambitions of encyclopedic scope, something like "hoping to cover all the domains of knowledge"; in the context of a photographer, to photograph everything worth photographing
I get where you're coming from, but "encyclopedic" has a pretty specific definition, and it doesn't twin with "ambition" in any sensible way. It seems like it should, but it doesn't. I'm commenting on the poor writing. Maybe "grand ambitions", or "colossal ambitions"? "encyclopedic ambitions" just doesn't work, unless we're going with vibe-writing :-)
4 MB of SRAM in the '80s would have been the main RAM of a supercomputer.
We still use SRAM today. It's what level-1 cache and registers are implemented with - actual flip-flops, can be toggled with one cycle delay. Supercomputers used to make their entire main memory out of SRAM, effectively the whole thing was L1 cache.
The 486 has an on-chip cache - 8 or 16 KB of SRAM. Very large for the time.
Off-chip access to the DRAM involves wait states. The read or write is stalled until the DRAM enters the appropriate state. The 486 would also do block reads of 16 bytes at a time to fill an entire cache line. This is around the time main memory and the CPU became increasingly decoupled.
Avoiding all the complexity of managing DRAM is why hobbyists use SRAM these days. Basically: to avoid cost. Ironic!
I've done similar loose experiments using a 19th century French novel I have read (L'Agonie by Jean Lombard), and which is quite obscure. There is no English translation of the novel published.
Using Gemini Notebooks I've found it passable at summarizing chapters, listing characters, major theme and so on, and it can do this in English.
"What is the symbolism of the Black Stone?"
> In the sources, the Black Stone (referred to as the Pierre-Noire) serves as the central religious icon of the Syrian Sun cult brought to Rome by the Emperor Elagabalus. Its symbolism is multifaceted, ranging from fertility and virility to a mystical pursuit of universal unity.
> It represents the perennity of the Sun, which fertilizes the world, causing "germs to rise" and spreading them through the atmosphere. It is viewed as the "definitive form" of divinity, intended to absorb and replace the "transitory forms" of all other Roman, Greek, Egyptian, and Persian gods, including the Christian "Kreistos".
> Virility and Phallic Symbolism
>
> The sources explicitly characterize the Black Stone as a gigantic sacred phallus. It is described as:
• An icon of virility and the "organ of generation" • A "unisexual icon" that materializes the generative force of nature • A representation of "virility in activity," which is why it is often paraded and elevated in an "orgasmic" or "colossal adoration"
> The Androgyne and Universal Unity - Beyond simple fertility, the philosopher Atillius explains a more complex, "mad" metaphysical project associated with the stone. It symbolizes "Life One" (Vie Une) and the return to a unisexual state of perfection. • The Androgyne: Atillius believes that by pursuing "the male sex by the male sex," the cult "inutilizes" the female sex to eventually create the Androgyne—a self-sufficient being containing both sexes • Unity: The stone signifies the fusion of all generative forces into a single Unity, reversing the "separation of the sexes" which is viewed as a state of unhappiness and impotence. • Marriage of Moon and Sun: The ritual marriage of the goddess Astaroth (representing the Moon and the female principle) to the Black Stone (representing the Sun and the male principle) symbolizes the merging of the Orient and Occident into this unified life principle
>
> Destruction of the Symbol - The Black Stone ultimately becomes a symbol of Oriental pollution and decadence to the Roman populace. During the final rebellion against Elagabalus, the stone is torn from its temple on the Palatine, defiled with filth, and broken into pieces to ensure that its "signification of Life" would never again dominate Rome.
This is all accurate to the book, even teasing out a couple themes that were only subconsciously present to me.
The NotebookLM version gives citations with links to the original text to support all these assertions, which largely are coherent with that purpose.
The input is raw images of a book scan! Imperfect as it is it still blows my mind. Not that long ago any kind of semantic search or analysis was a very hard AI problem.
Not quite the same analysis. The human is better, no surprise. But the NotebookLM output links back to the original book in a very useful way. If you think about it as fuzzy semantic search it's amazing. If you want an essay or even just creativity, yes it's lacking.
It doesn't have to be the same analysis to put it in a partially overlapping vector space. Not saying it wasn't a useful perspective shuffling in the vector space, but it definitely wasn't original.
LLMs haven't solved any of the 2029 predictions as they were posited. But I expect some will be reached by 2029. The AI hype acts like all this is easy. Not by 2029 doesn't mean impossible or even most of the way there.
LLMs will never achieve anything as long as any victory can be hand waved away with "in the training set". Somehow these models have condensed the entire internet down to a few TB's, yet people aren't backing up their terabytes of personal data down to a couple MB using this same tech...wonder why
It wasn't a hand wave. I gave an exact source, which OP admitted was better.
They certainly haven't "condensed the entire internet into a few TBs". People aren't backing up their personal data to a few MB because your assumption is false.
Maybe when people stop hand waving abilities that aren't there we will better understand their use as a tool and not magic.
I am reminded it's basically impossible to read cursive writing in a language you don't know even if it's the same alphabet.
reply