<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hacker News: phodo</title><link>https://news.ycombinator.com/user?id=phodo</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Tue, 07 Apr 2026 05:38:55 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=phodo" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by phodo in "Tell HN: Merry Christmas"]]></title><description><![CDATA[
<p>Prompt: create a christmas tree in ascii but that is a merkle tree<p>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”.)<p><pre><code>                   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

</code></pre>
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:<p><pre><code>                        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)
</code></pre>
Notes (so it’s actually Merkle-y)<p>D0–D3 = data blocks (your “presents” )<p>H(0) = hash(D0 || D0) (duplicated leaf for balance, common in Merkle trees)<p>H(0-1) = hash(H(0) || H(1))<p>H(ROOT) = hash(H(0-1) || H(2-3))<p>If you want, I can:<p>generate a bigger tree (8, 16, 32 leaves),<p>make the hashes look like real hash strings,<p>or format it like a perfect triangular Christmas tree silhouette while keeping the Merkle parent/child layout.<p>--
Prompt: format it like a perfect triangular Christmas tree silhouette while keeping the Merkle parent/child layout.<p>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).<p><pre><code>                                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
                                                
</code></pre>
If you want it even more like a Christmas tree (full silhouette + ornaments)<p>Here’s a slightly more “filled” version while keeping the structure valid:<p><pre><code>                                    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

</code></pre>
Edit: Note the emoji ornaments did not come through.</p>
]]></description><pubDate>Thu, 25 Dec 2025 01:23:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=46381246</link><dc:creator>phodo</dc:creator><comments>https://news.ycombinator.com/item?id=46381246</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46381246</guid></item><item><title><![CDATA[New comment by phodo in "Ask HN: What Are You Working On? (December 2025)"]]></title><description><![CDATA[
<p>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.</p>
]]></description><pubDate>Mon, 15 Dec 2025 03:18:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=46270071</link><dc:creator>phodo</dc:creator><comments>https://news.ycombinator.com/item?id=46270071</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46270071</guid></item><item><title><![CDATA[New comment by phodo in "Show HN: Gemini Pro 3 imagines the HN front page 10 years from now"]]></title><description><![CDATA[
<p>Will this be the new "pelican on a bicycle" test for frontier models?</p>
]]></description><pubDate>Tue, 09 Dec 2025 21:33:00 +0000</pubDate><link>https://news.ycombinator.com/item?id=46210981</link><dc:creator>phodo</dc:creator><comments>https://news.ycombinator.com/item?id=46210981</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46210981</guid></item><item><title><![CDATA[New comment by phodo in "Meta’s live demo fails; “AI” recording plays before the actor takes the steps"]]></title><description><![CDATA[
<p>a few moments earlier...
<a href="https://en.wikipedia.org/wiki/The_Mother_of_All_Demos" rel="nofollow">https://en.wikipedia.org/wiki/The_Mother_of_All_Demos</a></p>
]]></description><pubDate>Fri, 19 Sep 2025 03:34:14 +0000</pubDate><link>https://news.ycombinator.com/item?id=45297694</link><dc:creator>phodo</dc:creator><comments>https://news.ycombinator.com/item?id=45297694</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45297694</guid></item><item><title><![CDATA[John Carmack Reveals AGI Future: Robots, Videogames, and AI Agents]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.youtube.com/watch?v=4epAfU1FCuQ">https://www.youtube.com/watch?v=4epAfU1FCuQ</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=44477192">https://news.ycombinator.com/item?id=44477192</a></p>
<p>Points: 4</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 06 Jul 2025 02:06:08 +0000</pubDate><link>https://www.youtube.com/watch?v=4epAfU1FCuQ</link><dc:creator>phodo</dc:creator><comments>https://news.ycombinator.com/item?id=44477192</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44477192</guid></item><item><title><![CDATA[Ask HN: Futuristic and Sci-Fi Solutions to Fire Safety]]></title><description><![CDATA[
<p>Imagine you are tasked with a step function (10x, 100x, 1000x) improvements in fire safety, containment on a large scale basis. What would you dream up? Cost is not a factor in this case. Imagine fire becomes the existential threat. Imagine that climate change continues to be getting worse, and root causes for addressing climate change are being handled in another project.<p>Yes, there are political, economic, societal, forest management and current technological other factors that can be instituted today for fire safety, or that are preventing better fire management, but I'm looking for the dream scenarios, not the former.<p>Some examples I can think of:<p>* Preventing Ember Propagation:
 - large shields made of nano insulating materials deployed from drones, blimps, balloons, helicopters that attract and extinguish embers. They would form "walls" around fire hotspots, and provide containment of embers. They would be net attractors of embers. Can be deployed at mega scale.<p>* Wind prevention
- Wind control/ wind shaping - Ability to alter the direction of winds, even on temporary basis.<p>* Rain formation
- Ability to trigger rain (I think they experimented something like that in the UAE), even on a temporary basis.<p>* Terraforming of fire trenches
- Ability to "instantly" deploy or instantiate trenches and ravines around perimeter, and have material and technology within to extinguish. Imagine for example, ravines opening up on demand.<p>* Animal safety
- I would be remiss to ignore this safety of living things, including animals. Maybe there is an attractor that attracts living creatures, and funnels them into massive temporarily holding areas.<p>etc.<p>(disclaimer: I am far from an expert on this topic)</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=42677495">https://news.ycombinator.com/item?id=42677495</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 12 Jan 2025 22:12:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=42677495</link><dc:creator>phodo</dc:creator><comments>https://news.ycombinator.com/item?id=42677495</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42677495</guid></item><item><title><![CDATA[New comment by phodo in "OpenAI’s board, paraphrased: ‘All we need is unimaginable sums of money’"]]></title><description><![CDATA[
<p>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</p>
]]></description><pubDate>Tue, 31 Dec 2024 01:24:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=42555457</link><dc:creator>phodo</dc:creator><comments>https://news.ycombinator.com/item?id=42555457</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42555457</guid></item><item><title><![CDATA[New comment by phodo in "OpenAI’s board, paraphrased: ‘All we need is unimaginable sums of money’"]]></title><description><![CDATA[
<p>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.</p>
]]></description><pubDate>Mon, 30 Dec 2024 00:36:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=42545085</link><dc:creator>phodo</dc:creator><comments>https://news.ycombinator.com/item?id=42545085</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42545085</guid></item><item><title><![CDATA[New comment by phodo in "Traveling with Apple Vision Pro"]]></title><description><![CDATA[
<p>you can use the iPad kindle app and it works great.</p>
]]></description><pubDate>Wed, 16 Oct 2024 20:26:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=41863498</link><dc:creator>phodo</dc:creator><comments>https://news.ycombinator.com/item?id=41863498</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41863498</guid></item><item><title><![CDATA[New comment by phodo in "Ask HN: What macOS apps/programs do you use daily and recommend?"]]></title><description><![CDATA[
<p>Obsidian +1</p>
]]></description><pubDate>Mon, 10 Jun 2024 02:04:55 +0000</pubDate><link>https://news.ycombinator.com/item?id=40629441</link><dc:creator>phodo</dc:creator><comments>https://news.ycombinator.com/item?id=40629441</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=40629441</guid></item><item><title><![CDATA[New comment by phodo in "Ask HN: I have many PDFs – what is the best local way to leverage AI for search?"]]></title><description><![CDATA[
<p>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.</p>
]]></description><pubDate>Mon, 03 Jun 2024 06:00:00 +0000</pubDate><link>https://news.ycombinator.com/item?id=40559760</link><dc:creator>phodo</dc:creator><comments>https://news.ycombinator.com/item?id=40559760</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=40559760</guid></item><item><title><![CDATA[Ask HN: I have many PDFs – what is the best local way to leverage AI for search?]]></title><description><![CDATA[
<p>As the title says, I have many PDFs - mostly scans via Scansnap - but also non-scans. These are sensitive in nature, e.g. bills, documents, etc. I would like a local-first AI solution that allows me to say things like: "show me all tax documents for August 2023" or "show my home title". Ideally it is Mac software that can access iCloud too, since that where I store it all. I would prefer to not do any tagging. I would like to optimize on recall over precision, so False Positives in the search results are ok. What are modern approaches to do this, without hacking one up on my own?</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=40528192">https://news.ycombinator.com/item?id=40528192</a></p>
<p>Points: 257</p>
<p># Comments: 90</p>
]]></description><pubDate>Thu, 30 May 2024 20:24:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=40528192</link><dc:creator>phodo</dc:creator><comments>https://news.ycombinator.com/item?id=40528192</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=40528192</guid></item><item><title><![CDATA[The Timeless Beauty of Pre Rendered Graphics [video]]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.youtube.com/watch?v=e3SwbHIPnfo">https://www.youtube.com/watch?v=e3SwbHIPnfo</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=40177951">https://news.ycombinator.com/item?id=40177951</a></p>
<p>Points: 4</p>
<p># Comments: 0</p>
]]></description><pubDate>Sat, 27 Apr 2024 07:12:11 +0000</pubDate><link>https://www.youtube.com/watch?v=e3SwbHIPnfo</link><dc:creator>phodo</dc:creator><comments>https://news.ycombinator.com/item?id=40177951</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=40177951</guid></item><item><title><![CDATA[Diátaxis]]></title><description><![CDATA[
<p>Article URL: <a href="https://diataxis.fr">https://diataxis.fr</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=39636944">https://news.ycombinator.com/item?id=39636944</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 08 Mar 2024 01:53:45 +0000</pubDate><link>https://diataxis.fr</link><dc:creator>phodo</dc:creator><comments>https://news.ycombinator.com/item?id=39636944</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=39636944</guid></item><item><title><![CDATA[New comment by phodo in "Embracer Group Cancels 'Deus Ex' Video Game, Lays Off Workers"]]></title><description><![CDATA[
<p>What are some top indie games you would recommend?</p>
]]></description><pubDate>Mon, 29 Jan 2024 19:27:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=39181162</link><dc:creator>phodo</dc:creator><comments>https://news.ycombinator.com/item?id=39181162</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=39181162</guid></item><item><title><![CDATA[New comment by phodo in "Paperless-ngx – Open source document management system"]]></title><description><![CDATA[
<p>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.</p>
]]></description><pubDate>Sat, 07 Oct 2023 21:11:57 +0000</pubDate><link>https://news.ycombinator.com/item?id=37805610</link><dc:creator>phodo</dc:creator><comments>https://news.ycombinator.com/item?id=37805610</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=37805610</guid></item><item><title><![CDATA[New comment by phodo in "Nvidia on the Mountaintop"]]></title><description><![CDATA[
<p>What is a good book on how nvidia is run ?</p>
]]></description><pubDate>Tue, 29 Aug 2023 00:21:46 +0000</pubDate><link>https://news.ycombinator.com/item?id=37302007</link><dc:creator>phodo</dc:creator><comments>https://news.ycombinator.com/item?id=37302007</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=37302007</guid></item><item><title><![CDATA[New comment by phodo in "The odd appeal of absurdly long YouTube videos"]]></title><description><![CDATA[
<p>If on a mac you can always type ‘caffeinate’ in Terminal and it will keep your laptop on when you close the lid.</p>
]]></description><pubDate>Tue, 30 May 2023 09:00:05 +0000</pubDate><link>https://news.ycombinator.com/item?id=36122656</link><dc:creator>phodo</dc:creator><comments>https://news.ycombinator.com/item?id=36122656</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=36122656</guid></item><item><title><![CDATA[New comment by phodo in "YouTube, the jewel of the internet"]]></title><description><![CDATA[
<p>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.</p>
]]></description><pubDate>Mon, 24 Apr 2023 03:43:30 +0000</pubDate><link>https://news.ycombinator.com/item?id=35683434</link><dc:creator>phodo</dc:creator><comments>https://news.ycombinator.com/item?id=35683434</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=35683434</guid></item><item><title><![CDATA[New comment by phodo in "Using LLaMA with M1 Mac and Python 3.11"]]></title><description><![CDATA[
<p>What are some prompts that seem to be working on non-finetuned models? (beyond what is listed in example.py)</p>
]]></description><pubDate>Sun, 12 Mar 2023 19:56:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=35125383</link><dc:creator>phodo</dc:creator><comments>https://news.ycombinator.com/item?id=35125383</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=35125383</guid></item></channel></rss>