ojo-rojo

This is actually a new skill I've been working on. Learning how to elicit concise and simple speech from models (and from people to!).

Whenever I come to a wall of complicated text I kick into gear and think through getting it to distill this into the high-level useful bits that I actually need to know.

I guess I could create an actual agent skill for this :) And next-gen models might eventually be trained to simplify their output themselves...

Right. Once we see AI start delivering on the creative & intuition side of things that's going to be awesome. Until then I guess we'll live with exhaustive exploration of problem spaces by orchestrating swarms of agents...?

I'm really impressed by mathematicians. It's cool that Fermat had the intuition to conjecture that "aⁿ + bⁿ = cⁿ" could not be satisfied for n > 2, and that other mathematicians can create proofs, and that others still can understand AI's formulation of those proofs. Really cool.

> My view is that these sorts of things are not possible for AI in general.

I wonder what it would take build an artificial system that has these qualities.

> Software deals with metaphors.

This is me wondering again: what's fundamentally different between software running on a machine compared to what's happening in our brains? In both cases you have energy flow following a pattern.

It's conceivable to create a system where energy flows in a particular way.

BTW, we navigate the world of an uncountable number of particles by creating models in our heads of what we think are large things out there. Approximations are made by both artificial and biological systems.

I'm in the same boat, I think some aspects can be engineered, like intention and desire. I'm really curious if it's possible to go the full distance and make AI have experience like we do.

> it can't jump to somewhere where it's not present its training data

That sounds like something that can be engineered, can't it? In other words, we can identify limitations in current transformer-based architectures, and we can also build new architectures over time.

You mention LLMs are dead and don't have the complexity or inner life that people do. Is your opinion that these kinds of things are not possible for AI in general, or that these things might be possible but we're just not there yet with modern LLMs?

You mentioned LLMs don't have souls, desire, or a will. I imagine those latter two can be engineered, no?

Ha, this is very true. When this happens I have to tell myself "Okay, time to wait out yet another story"

How about a subsequent review where a separate agent analyzes the original issue and resultant code and approves it if the code meets the intent of the issue. The principle being to keep an eye out for manual work that you can describe well enough to offload.

Depending on your success rate with agents, you can have one that validates multiple criteria or separate agents for different review criteria.

This is my first time hearing the British don't like saying Celtic. (I'm from the U.S.) There must be some history there?

It's humbling to think about all the things people have gone through over the past couple hundred thousand years. Somewhere around 117 billion humans have ever lived...? It makes it seem kind of small when we think only 50 or 100 years out when thinking of what the future would be.

I agree with you. I clicked into this hoping to hear what new things we could learn or discover with the new observatories. Commenting on the more positive and informative side would be a better use of time and energy I think :)

Ha, you made me think of casually referring to xkcd's by number just as we did with RFC's back in the day. "I don't know, the socket states seem to follow RFC 793, but remember it's a 1918 address on the southside of the NAT."

I gonna keep a look out for doing this with xkcd's now :)

Can you share some details? Do you disconnect while in your hometown going about your daily routine, or do you have this down time in a different environment? I'm kind of looking for inspiration. I have grown kids and friends that I text with so I'm also wondering how my relationship with them would fit into this. Has that played a role for you?

I notice when its left hand came down there was a squirt of water from probably crushing water bottle. That makes me wonder how much force these robots can exert, and if they can accidentally hurt people.

Probably from deconstructing the solar system's asteroids and planets. I imagine a Dyson sphere would be less structurally sound and harder to get right – due to gravitational forces on the material – than a Dyson swarm or matryoshka brain. The latter made of independent satellites orbiting the sun and collecting light from concentric orbits at various distances.

Early as in we may have developed before any other civilizations? That's interesting. We're speculating of course, but what would explain us being the first after so much time – 13.8 billion years?

This is new to me. Thank you!

I'm interested in what you changed in your diet that helped. Would you be open to sharing?

(I'm vegetarian, and eat a lot of salty and sugary foods I'm not too proud of, and would love to learn what works for other people.)

+1 To add to the experience of connecting to people, I can also imagine our family members taking a photograph together while in VR of the family living room – a memento we can take away. That would work if our VR avatars are realistic representations of ourselves, which I think Meta can do (?)

Yeah, I'm still confused.

I like this sharing of the joy of journaling, thanks for that. I don't quite like the formula described here, though. I would imagine that following a set of questions would make it feel like filling out a templated form – too structured. I really enjoy the flow and natural progression of journaling in a free-form format.

By the way, in addition to occasionally writing a personal journal entry, I also really enjoy keeping notes on my thoughts on the books I read, whether fiction or non-fiction. I love flipping back and seeing what I was going through while reading a really good story, and reminding myself who the characters were, and seeing the important points to remember of some technical material. All good stuff :)

I find your comment interesting, even though I'm not sure if I really get what you're saying. You built a perpetual motion machine? You then made improvements? Can you share details?

Can you say more? What are you using now?

Thanks for sharing this. I've often felt that the ease by which we can erase digital content makes our time period susceptible to a digital dark ages to archaeologists studying history a few thousand years from now.

Us preserving digital archives is a good step. I guess making hard copies would be the next step.

But that means we'd prefer whichever theory our species had landed on first. Basing our preference for a theory on that timing seems kind of arbitrary to me. If they're the same in other respects, I'd take a look at both sides to see if there are other compelling reasons to focus on one or the other, such as which is simpler. Of course if they make different predictions that'd be even better, time to get to testing :)

Ahh, The Last Question. This has a special place in my heart :)

>One day this February, I just got up at 2am and started writing code. I was tired of waiting. So I wrote and wrote and wrote.

That's cool. It makes me feel happy reading this, kind of inspiring :)

>I found myself making an API for making game maker tools and a game engine and a game. It turns out I’m an API designer at heart. I guess I always kinda knew this.

I like hearing when someone finds their passion and goes for it full throttle.

"I'll be your huckleberry" – a great line in a tense scene.

That's what I missed. Very very nice to see the detailed photos.