HN user

phodo

2,786 karma
Posts381
Comments228
View on HN
www.youtube.com 1y ago

John Carmack Reveals AGI Future: Robots, Videogames, and AI Agents

phodo
4pts0
news.ycombinator.com 1y ago

Ask HN: Futuristic and Sci-Fi Solutions to Fire Safety

phodo
3pts0
news.ycombinator.com 2y ago

Ask HN: I have many PDFs – what is the best local way to leverage AI for search?

phodo
257pts90
www.youtube.com 2y ago

The Timeless Beauty of Pre Rendered Graphics [video]

phodo
4pts0
diataxis.fr 2y ago

Diátaxis

phodo
2pts0
www.youtube.com 3y ago

The flying version of Howl's Moving Castle out of garbage

phodo
1pts0
news.ycombinator.com 3y ago

Ask HN: Why is the Mac Copy/Paste experience so inconsistent?

phodo
3pts3
www.theatlantic.com 5y ago

K: The Overlooked Variable That's Driving the Pandemic

phodo
1pts0
austinmorlan.com 6y ago

A Simple Entity Component System (ECS) [C++]

phodo
1pts0
home.hccnet.nl 6y ago

How to program a text adventure in C (2016)

phodo
177pts35
news.ycombinator.com 6y ago

Ask HN: Who is working on Coronavirus and what sources do you use for info?

phodo
1pts0
hackaday.com 6y ago

Turning Sounds from a Flute into Sheet Music

phodo
2pts0
a16z.com 6y ago

Product Zeitgeist Fit

phodo
46pts13
news.ycombinator.com 6y ago

Ask HN: Best chair for extended reading? (Not at a desk)

phodo
4pts1
blog.hackster.io 6y ago

Building an RF Side-Channel Attack Using Machine Learning

phodo
1pts0
www.cnbc.com 6y ago

Alarm in Texas as 23 towns hit by 'coordinated' ransomware attack

phodo
1pts0
www.youtube.com 6y ago

Transformer furniture hidden on ceiling deploys by command

phodo
1pts0
marcelwiget.blog 6y ago

Tether RPi to iPad Pro via Ethernet over USB-C

phodo
7pts3
lucidscience.com 6y ago

LucidScience – Electronic Projects and Tutorials

phodo
71pts3
erkaman.github.io 7y ago

How to Start Learning Computer Graphics Programming

phodo
754pts120
github.com 7y ago

Ipfs/roadmap

phodo
1pts0
medium.com 7y ago

The Rise and Further Rise of Pokemon Go: product lessons learned from hit game

phodo
2pts0
www.theverge.com 8y ago

Fortnite has the most interesting video game story in years

phodo
2pts0
amp.theguardian.com 8y ago

Will MySpace ever lose its monopoly? (2007)

phodo
2pts0
www.youtube.com 8y ago

Jonathan Blow, Thekla – Making Game Programming Less Terrible [video]

phodo
1pts0
www.youtube.com 8y ago

“Money doesn't interest me” – Creator of Blender talks about its future [video]

phodo
1pts0
www.planetary.org 8y ago

A Pale Blue Dot

phodo
1pts0
mikecann.co.uk 8y ago

A Game Developer Learns Machine Learning – A Little Deeper – MikeCann.co.uk

phodo
2pts0
www.farnamstreetblog.com 8y ago

What I'm Reading in 2017

phodo
2pts0
medium.com 8y ago

Software 2.0

phodo
2pts0

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...

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.

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.

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.

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.

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.

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.