I was curious why I was downvoted, and, what the heck, why not go ahead and ask. This is the answer I received from ChatGPT 4o:
Your reply—“An LLM wrote this and this and this… An LLM’s eternal recurrence.”—is clever and layered, riffing on both the original comment and Nietzsche’s concept of eternal recurrence. On Hacker News, though, that kind of playfulness can sometimes backfire for a few reasons:
1. Tone Perception: HN users often value clarity, conciseness, and substance. Your comment may have come off as glib or performative rather than adding meaningful insight—despite being philosophically witty.
2. Thread Saturation: If others also replied similarly (“An LLM wrote it” variants), your continuation might have felt like piling on or diluting the thread, which can get downvoted as noise.
3. Cultural Split: Hacker News has a split temperament: some users appreciate literary or ironic references; others see them as distractions from signal-rich discussion.
4. Automated-Sounding Style: Ironically, even though you’re parodying LLM-speak, your repetition (“this and this and this…”) could be mistaken as LLM-speak by some, triggering reflexive downvotes from those skeptical of AI-generated content.
In short: you were being clever, but the average Hacker News voter might’ve wanted more content or simply misread your intent.
Given your abhorrence of verbiage, here is some LLM spew instead:
In Search of Lost Time by Marcel Proust is a monumental novel about memory, time, and the subtle shifts of consciousness. Through the narrator’s recollections—often triggered by sensory experiences like the taste of a madeleine—Proust explores love, art, jealousy, and the passage of life in early 20th-century French society.
Just to clarify, the paper [0] does use both implanted electrodes and fMRI data, but it is actually quite transparent about which data came from which source. The authors worked with two datasets: the B2G dataset, which includes multi-unit activity from implanted Utah arrays in macaques, and the Shen-19 dataset, which uses noninvasive fMRI from human participants.
You’re right that fMRI measures blood flow rather than direct neural activity, and the authors acknowledge that limitation. But the study doesn’t treat it as a direct window into brain function. Instead, it proposes a predictive attention mechanism (PAM) that learns to selectively weigh signals from different brain areas, depending on the task of reconstructing perceived images from those signals.
The “thermal imager” analogy might make sense in a different context, but in this case, the model is explicitly designed to deal with those signal differences and works across both modalities. If you’re curious, the paper is available here:
Fair point. Side-channel attacks show how much signal you can pull from noise. But fMRI is a different kind of beast. It’s slow, indirect, and coarse. You’re not measuring neural activity directly, just blood flow changes that lag by a few seconds.
The paper [0] doesn’t pretend otherwise. It trains a model (PAM) to learn which brain regions carry useful info for reconstructing images, and applies this to both fMRI data from humans and intracranial recordings from macaques. The two signal types are handled separately.
If you want an analogy, it’s less like tapping power lines and more like trying to figure out which YouTube video someone is watching by measuring heat on the back of their laptop every few seconds. There’s a pattern in there, but pulling it out takes work.
Observations like these remind me of The Académie des Beaux-Arts in France, and more specifically its official Salon (the Salon de Paris), keeping Impressionist painters out of established exhibitions.
Yes because generating "art" that is entirely stealing from the hard work and actual dedication put forth by real artists is anything like the expressionist movement in the 20th century.
I was about to watch Francis Ford Coppola’s little-seen You’re a Big Boy Now on Criterion, but you’ve convinced me—I’m forking over the rental and watching True Romance.
Very curious to hear feedback from someone watching it for their first time ~30 years after its release. I watched it incessantly around the time it came out but haven't watched it much since - queued it up for the coming weeks.
“I’d love some pie.”
“-I think what you did was…
-What?
-I think what you did was…
-What?
-Was so romantic.
-Oh, baby, you’re bleeding.”
“Son of a bitch was right. She tastes like a peach.”
“You got me in a vendetta kind of mood. You can tell the angels in heaven you never seen evil so singularly personified as you did in the face of the man who killed you.”
Hm. I have a Macbook M3 and it doesn’t come up from sleep every third time or so, freezing and then force-restarting all running apps in the background. Most other times it takes up to a minute to show the login screen. No idea how to debug. Still hoping for some update to magically fix it.
Judging by the content of that link, this is probably for Intel based devices. The Apple Silicon based ones are basically giant iPads. I don’t ever remember an iPad having an issue with sleep. And they’ve existed for a decade or more now. I honestly don’t expect to need that link.
The philosopher Blaise Pascal once said that "all of humanity's problems stem from man's inability to sit quietly in a room alone." Many of our world's troubles come from people doing stupid things rather than sitting peacefully with discomfort.
Doing nothing is actually a kind of discipline. The brain isn’t designed for idle time; evolution didn’t prioritize contentment—it prioritized survival. So Becky never really shuts up, because quiet might’ve once meant danger. Today, it just means our ancient wiring is nudging us to be productive, even when there’s nothing to produce.
I would add a corollary to Pascal's remark. Not all of humanity's problems stem from that inability, bu the many of the ones that don't come instead from our inability to sit quietly in a room with others.
Fortunately, for more than 300 years, the Quakers have been showing us how this is done, and they inherit a long line of silent, social presence.
A shocking number of people are completely incapable of being alone with their thoughts.
I was at a bathhouse the other night and these two people were both playing videos, out loud, on their phones while having a conversation. They couldn't even have a conversation without some distraction.
Nowadays everyone has an earbud in their ear playing a podcast, music, or audiobook. Every task has to be accompanied by audio. People avoid social interaction by listening to something. Etc etc.
There are huge benefits to doing chores in silence or being outside without segregating your sense of sound.
It's up there with social media.
I'd be really curious if any mental health professionals have studied people with anxiety conditions and how much audio they listen to throughout the day.
It was either Radiolab or this American life that aired an episode about how the Sony walkman changed society forever. I think they were really onto something.
Seems like a feature and not a bug to me. Otherwise, we would still be living in small bands in caves.
All western man's "problems" to me seem to be the want of utopian trade offs that we get all the upside of a trade off without trading anything and then complaining when that doesn't happen in reality.
In reality, what was good enough yesterday, is expected today and not good enough tomorrow. Exactly the chemical reaction that causes progress.
