Unearned5161

relatively? they're both rather in-the-weeds things that would attract more technically minded folk

maybe not prudent technically minded folk, but nobody's born perfect

Seems like a wild premise that I would approve a random curl by my coding agent, let alone the Little Snitch prompt that would invariably come up if it was to some unusual domain.

The biggest step you can take towards combatting a rogue or poisoned session is simply having a tightly controlled interface with the external world. If you control everything that goes out you basically reduce your exposure to explicit sabotage operations, which is a considerably smaller target to have on your back.

I totally understand, thanks for sharing the repo, I'll do my best to pitch in. Always happy to support making history more accessible!

I'm getting

"You've requested a page on a website (radar.koakno.com) that is on the Cloudflare network. The host (radar.koakno.com) is configured as a Cloudflare Tunnel, and Cloudflare is currently unable to resolve it."

when I try and visit the demo

Lovely project, I've given it a skim and I quite like the presentation.

The only thing that I would work on would be to rewrite a lot of the website copy since it's a bit heavy with the llm-isms, which gives it an unfortunate sheen.

If theres a repo link, I'd be happy to contribute, since I realize it's no small task.

Thank you for making this, it's very nice. I love a good timeline, everything seems to make a bit more sense when it's laid out spatially.

This is very similar to last week with that mind reading startup thing. Please read the paper before commenting.

This is a tool to help researchers in figuring out what different parts of the brain are actually for with less experimenter bias contamination of “well we think maybe it’s about this so let’s show it video of x to see”.

The essence runs on having someone sit in a scanner for a couple hours watching all sorts of things, and then feeding that to a model that will then build its own representation of said data and try different things on it until it’s found what makes a certain part sing in the model.

The purpose is a generalized understanding of brain function, more or less the same way we’ve been doing it all these years. Expose brain to something, record it somehow, see if brains reaction in the recording helps you understand more about who we are and what cognition is.

I want to bring some attention to a spectacular sleight of hand that occurs at minute 4 of this podcast:

"The way that I formulate the argument, just to get us started here, is that acts, the things we do, have ends. We act for an end. They have a purpose. And that it is wrong to deliberately frustrate an act from attaining its end, from attaining its purpose."

I will draw your attention to the three instances of "end", first we have the noble, tautological, "have ends", actions have ends; then, following close behind we see "an end", we act for an end, those ends have been made into one now, singular end; and finally, "its end", the act, as an entity unto itself, has an end you mustn't interrupt.

The imaging stuff is cool but the homepage is making me wince.

There's a compelling argument to be made that the level of detail in "mind reading" they are gesturing at is plain unrecoverable with hemodynamics. There's an irreversible loss of dimensions that occurs the instant you start recording blood instead of spikes on the neural circuits themselves, and it's not at all clear that what a VC reading the words "telepathy" is imagining even survives that transformation.

What you have is food delivery data for a neighborhood, this can tell you a surprising amount, including when they might throw a party. What it can't tell you, however, is who wore the best outfit and what was talked about over dinner. The information simply does not survive across the interface.

There is a spectacular canyon between "informed interpretation" and "mind reading"

I think that’s part of the point. Execution at its core is mastering the art of projection onto a lower dimensional space.

Taking anything from up in the mind out into the real world, be it a physical action, a speech, an artwork, requires you to make decisions about what’s load bearing and what’s not.

So the more practice you get translating your thoughts into words (or another medium), the better you get at executing.

If you read the thinking you can quite literally see it say "I can't just agree with all they are saying, I should find something for a constructive response". I wager that the anti-sycophancy sections in the system prompt have gotten unbalanced with the "helpful agent" parts.

I imagine that the right balance will be hard to strike well given that at the end of the day we're asking the machine to have tact, and we don't quite know how to put that into an instruction yet. "Please push back when it feels right but in other cases read the room and be less rigorous" is something that plenty of humans struggle with as it is.

Articles like this should approach topics on consciousness with more humility than is displayed here.

We don’t even agree on a good definition of what’s going on inside our own heads yet, what gives you the confidence to say that what goes on inside an LLM can’t be conscious?

I have a pet peeve with the concept of "a genuinely novel discovery or invention", what do you imagine this to be? Can you point me towards a discovery or invention that was "genuinely novel", ever?

I don't think it makes sense conceptually unless you're literally referring to discovering new physical things like elements or something.

Humans are remixers of ideas. That's all we do all the time. Our thoughts and actions are dictated by our environment and memories; everything must necessarily be built up from pre-existing parts.

No matter how intricate and detailed an object is, it will appear similar to any other blurry mess if it's viewed through a shoddy lens.

I think your point stands for upper level work; however, at medium to lower levels, your counterfactual starts to weaken. The ideas have always been there, but it's the ability to express them--well enough to notice their presence--that is not.

The point has always been the act of writing itself. What you write about is almost irrelevant; it’s that you spent the time writing, that you had ideas in your head, and that you squeezed them onto the page.