But that's a little too tidy to be a proper Christmas tree — so here’s a more “tree-like” version with ornaments, while still preserving the Merkle structure:
H(0) = hash(D0 || D0) (duplicated leaf for balance, common in Merkle trees)
H(0-1) = hash(H(0) || H(1))
H(ROOT) = hash(H(0-1) || H(2-3))
If you want, I can:
generate a bigger tree (8, 16, 32 leaves),
make the hashes look like real hash strings,
or format it like a perfect triangular Christmas tree silhouette while keeping the Merkle parent/child layout.
--
Prompt: format it like a perfect triangular Christmas tree silhouette while keeping the Merkle parent/child layout.
Answer: You got it — here’s a perfect triangular Christmas tree silhouette that still preserves the Merkle parent/child layout (parents directly above their two children, leaves at the base).
My sister and I are glued to it, and she continues to destroy me, with consistent zero reveals and half the time to complete, as yours truly. We love this game. thanks.
One view is that it’s not first mover, but first arriver advantage. Whoever gets to AgI (the fabled city of gold or silver?, Ag pun intended) will achieve exponential gains from that point forward, and that serves as the moat in the limit. So you can think of it as buying a delayed moat, with an option price equivalent to the investment required until you get to that point in time. Either you believe in that view or you don’t. It’s more of an emotional / philosophical investment thesis, with a low probability of occurrence, but with a massive expected value.Meanwhile, consumers and the world benefit.
What if the AGI takes an entire data center to process a few tokens per second. Is the still a first-arriver advantage? Seems like the first to make it cheaper than an equivalent-cost employee (fully loaded incl hiring and training) will begin to see advantage.
What if the next one to get there produces a similar service for 5% less? Race to the bottom.
And would AI that is tied to some interface that provides lock-in even be qualified to be called general? I have trouble pointing my finger on it, but AGI and lock-in causes a strong dissonance in my brain. Would AGI perhaps strictly imply commodity? (assuming that more than one supplier exists)
Depending on how powerful your model is, a few tokens per second per data center would still be extraordinarily valuable. It's not out of the realm of possibility that a next generation super intelligence could be trained with a couple hundred lines of pytorch. If that's the case, a couple tokens per second per data center is a steal.
Good point. It’s 2 conditions and both have to be true :
- Arrive first
- Use that first arrival to innovate with your new AGI pet / overlord to stay exponentially ahead
Exponential gains from AGI requires recursive self improvement and the compute headroom to realize them. It's unclear if current LLM architectures make either of those possible.
People need to stop talking about "exponential" gains; these models don't even have the ability to improve themselves, let alone at this or that rate. And who wants them to be able to train themselves while being connected to the Internet anyway? I sure don't. All it takes for major disruption is superhuman ability at subhuman prices.
What does AGI even mean in this case? If progress toward more capable and more cost-effective agents is incremental, I don't see a defensible moat. (You can maintain a moat given continued outpaced investment, but following remains more cost-effective)
Since we're talking about the economic impact here, AGI(X) could be defined as being able to do X% of white collar jobs independently with about as much oversight as a human worker would need.
The exponential gains would come from increasing penetration into existing labor forces and industrial applications. The first arriver would have an advantage in being the first to be profitably and practically applicable to whatever domain it's used in.
Why would the gains be exponential? Assume that X "first arrival" develops a model with a certain rnd investment, and Y arrives next year with investment that's an order of magnitude less costly by following, and there's a simple enough switchover for customers. That's what's meant by no defensible moat; a counterexample is Google up to 2022 where for more than a decade nothing else came close in value prop. Maybe X now has an even better model with more investment, but Y is good enough and can charge way less even if their models are less cost-effective.
> ... Google up to 2022 where for more than a decade nothing else came close in value prop. Maybe X now has an even better model with more investment ...
I was very confused at this point because I haven't really seen X as a competitor to Google's ad business, at least not in investment and value prop... Then I saw you were using X as a variable...
Yes, "first to arrive at AGI" could indeed become a moat, if OpenAI can get there before the clock runs out. In fact, that's what's driving all the spending.
Thank you all for the comments. Got a lot of good input and ways to think thru the tried and true tools (enjoying ripgrep-all + fzf) plus the standard ai/rag-style tools. I do think there is room for a bridge or an integrated way to pipe in similarity / embedding into the ripgreps of the world. Maybe something close to fzf’s piping model. Will explore if I have some time.
My top rec would be Factorio if you like sandbox building games (almost RTS, but not quite). Talos Principle 2 is the best puzzle game I've played (might not be indie, but I don't think it's a large studio). Last Epoch is a solid ARPG like Diablo, but more old-school in how it plays and feels. Outer Wilds is also an amazing exploration, narrative-driven game.
Talos Principle 2 was a masterpiece. The concepts explored in the story were really interesting to boot, I also did not anticipate it to be so stunning visually.
Does auto OCR work on iCloud files ? For example: I scansnap a huge collection of documents to a folder that is on iCloud (synced w desktop). It works great because it is so simple. However if I have, say, PDF document, will the Mac ocr functionality perform the OCR if the doc is on iCloud and will I then be able to search for the text in that doc via spotlight / finder ? I tested this a few years ago and the search on content inside scanned PDFs did not work. I had looked at Paperless but decided to stay on Mac os file system.
Are you talking about iCloud Drive? As far as I can tell, files in there are just normal files, so Live Text works. You can easily put a screenshot / pdf in there and see.
Answer: Here’s an ASCII Christmas tree that is also a Merkle tree (Each parent node is the hash of its two children; leaves are the “data blocks”.)
But that's a little too tidy to be a proper Christmas tree — so here’s a more “tree-like” version with ornaments, while still preserving the Merkle structure: Notes (so it’s actually Merkle-y)D0–D3 = data blocks (your “presents” )
H(0) = hash(D0 || D0) (duplicated leaf for balance, common in Merkle trees)
H(0-1) = hash(H(0) || H(1))
H(ROOT) = hash(H(0-1) || H(2-3))
If you want, I can:
generate a bigger tree (8, 16, 32 leaves),
make the hashes look like real hash strings,
or format it like a perfect triangular Christmas tree silhouette while keeping the Merkle parent/child layout.
-- Prompt: format it like a perfect triangular Christmas tree silhouette while keeping the Merkle parent/child layout.
Answer: You got it — here’s a perfect triangular Christmas tree silhouette that still preserves the Merkle parent/child layout (parents directly above their two children, leaves at the base).
If you want it even more like a Christmas tree (full silhouette + ornaments)Here’s a slightly more “filled” version while keeping the structure valid:
Edit: Note the emoji ornaments did not come through.