In 7th grade social studies, I did a report for a class project, and printed the Karateka opening screen on my apple image writer as the cover page. I got an A+ because of that cover!
HN user
phodo
> "who wants to own cutting vinyl?"
Well, Sega gamers for one: https://www.youtube.com/watch?v=c744iD0_fWU
RIP - last of the greats - hugely influential to me in his disciplined approach to perfecting his craft and overall grit - https://www.selmer.fr/en-int/blogs/infos/sonny-rollins-bridg...
what model do you use?
Great work. I wonder what the future "can it run doom ?" Will it be: Can it run AGI on a new quantum processor/ robot / bio-engineered cell. Or will it be Doom all the way down...
Neat! Any cool stories? What games did you work on?
Prompt: create a christmas tree in ascii but that is a merkle tree
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”.)
MERKLE TREE
H(ROOT)
/ \
H(0-1) H(2-3)
/ \ / \
H(0) H(1) H(2) H(3)
/ \ / \ / \ / \
D0 D0 D1 D1 D2 D2 D3 D3
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(ROOT)
/ \
H(0-1) H(2-3)
/ \ / \
H(0) H(1) H(2) H(3)
/ \ / \ / \ / \
D0 D0 D1 D1 D2 D2 D3 D3
(leaf)(leaf)(leaf) (leaf)(leaf)(leaf)
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).
H(ROOT)
/ \
┌────────H(0-3)────────┐
/ \
┌────H(0-1)────┐ ┌────H(2-3)────┐
/ \ / \
┌─H(0)─┐ ┌─H(1)─┐ ┌─H(2)─┐ ┌─H(3)─┐
/ \ / \ / \ / \
D0 D1 D2 D3 D4 D5 D6 D7
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:
H(ROOT)
/ \
──────H(0-3)──────
/ \
─────H(0-1)───── ─────H(2-3)─────
/ \ / \
───H(0)─── ───H(1)─── ───H(2)─── ───H(3)───
/ \ / \ / \ / \
D0 D1 D2 D3 D4 D5 D6 D7
Edit: Note the emoji ornaments did not come through.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.
Will this be the new "pelican on a bicycle" test for frontier models?
a few moments earlier... https://en.wikipedia.org/wiki/The_Mother_of_All_Demos
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
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.
you can use the iPad kindle app and it works great.
Obsidian +1
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.
What are some top indie games you would recommend?
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.
What is a good book on how nvidia is run ?
If on a mac you can always type ‘caffeinate’ in Terminal and it will keep your laptop on when you close the lid.
My biggest gripe is that I cannot search playlists by name - especially when I want to add a new piece of content to a previously created playlist. I end up having to scroll through many playlists or end up creating duplicate playlists.
What are some prompts that seem to be working on non-finetuned models? (beyond what is listed in example.py)
For whistper.cpp live transcription, there seems to be duplicates in the output filename. Is there a mix of parameters that eliminate this?
What are some of the best tools people are using these days to consumer research papers? (outside of clicking on the PDF)
But they have dark mode, so it will work. /s
What is the worst case scenario for security on your network, in the above self hosted setup ?
Is it running on a max or are you accessing iCloud from a non-Mac?
Related: Here is an interesting deconstruction on chords (jazz) and chatgpt https://www.youtube.com/watch?v=WmvzMeJdRTI
Would be interesting to get a list of those 40 papers mentioned
This is known as a programmer-denial-of-service attack (PDOS) and can be an effective way to bring down a society by distracting and engaging its top computing professionals in endless useless activity and an occasional bike shedding.
Thank you for this. Did you use any tool to publish the site and UI, or all static and vanilla? It's snappy, nice and clean.