<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: samuelzxu</title><link>https://news.ycombinator.com/user?id=samuelzxu</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Mon, 15 Jun 2026 17:17:03 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=samuelzxu" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[Show HN: Knowable, the AI tutor that follows your work on paper]]></title><description><![CDATA[
<p>I'm building the AI tutor that I wish I had when I was a kid. It's capable of following your thought process through the MacOS webcam as you do rough work and propose meaningful hints. You can download it on the Mac App Store for free, and use the free version without signing up for a free trial of a paid version.<p>Open sourced - note, readme's are out of date.<p><a href="https://github.com/samuelzxu/Knowable" rel="nofollow">https://github.com/samuelzxu/Knowable</a>
<a href="https://github.com/samuelzxu/knowable-be" rel="nofollow">https://github.com/samuelzxu/knowable-be</a><p>Ping me at `samuel at knowable dot ca` for suggestions and feedback!</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48405366">https://news.ycombinator.com/item?id=48405366</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 04 Jun 2026 22:15:43 +0000</pubDate><link>https://knowable.ca/</link><dc:creator>samuelzxu</dc:creator><comments>https://news.ycombinator.com/item?id=48405366</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48405366</guid></item><item><title><![CDATA[New comment by samuelzxu in "Mathematicians issue warning as AI rapidly gains ground"]]></title><description><![CDATA[
<p>I think we just haven’t spent enough time creating the systems to help people learn faster - so far, only the systems that teach AI to know more and for people to rely on AI to retrieve information.</p>
]]></description><pubDate>Thu, 04 Jun 2026 12:44:50 +0000</pubDate><link>https://news.ycombinator.com/item?id=48397860</link><dc:creator>samuelzxu</dc:creator><comments>https://news.ycombinator.com/item?id=48397860</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48397860</guid></item><item><title><![CDATA[New comment by samuelzxu in "Failing grades soar with AI usage, dwindling math skills in Berkeley CS classes"]]></title><description><![CDATA[
<p>AI + Education is really interesting but also pretty tough to get right. Working on something that is hopefully going in the right direction: <a href="https://knowable.ca" rel="nofollow">https://knowable.ca</a></p>
]]></description><pubDate>Thu, 04 Jun 2026 07:54:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=48395539</link><dc:creator>samuelzxu</dc:creator><comments>https://news.ycombinator.com/item?id=48395539</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48395539</guid></item><item><title><![CDATA[New comment by samuelzxu in "Knowable – Open-Source Personal AI Tutor on macOS"]]></title><description><![CDATA[
<p>I'm working full-time on a personal AI tutor that just requires a recent Macbook, available for free on the Mac App Store! You'll get a full ~60 minutes. Vision LLMs are awesome.<p>Happy to hear some feedback!<p>Supported so far:<p>Macbook Pro 2024+,
Macbook Air 2025+,
or
(a recent MacOS + iPhone continuity camera)<p>Code:<p><a href="https://github.com/samuelzxu/Knowable" rel="nofollow">https://github.com/samuelzxu/Knowable</a>
<a href="https://github.com/samuelzxu/knowable-be" rel="nofollow">https://github.com/samuelzxu/knowable-be</a><p>For feedback please email me at:
samuel at knowable dot ca</p>
]]></description><pubDate>Wed, 03 Jun 2026 17:07:27 +0000</pubDate><link>https://news.ycombinator.com/item?id=48386653</link><dc:creator>samuelzxu</dc:creator><comments>https://news.ycombinator.com/item?id=48386653</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48386653</guid></item><item><title><![CDATA[Knowable – Open-Source Personal AI Tutor on macOS]]></title><description><![CDATA[
<p>Article URL: <a href="https://knowable.ca/">https://knowable.ca/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48386652">https://news.ycombinator.com/item?id=48386652</a></p>
<p>Points: 3</p>
<p># Comments: 1</p>
]]></description><pubDate>Wed, 03 Jun 2026 17:07:27 +0000</pubDate><link>https://knowable.ca/</link><dc:creator>samuelzxu</dc:creator><comments>https://news.ycombinator.com/item?id=48386652</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48386652</guid></item><item><title><![CDATA[New comment by samuelzxu in "Claude Evolve: ShinkaEvolve code evolution on only Claude Code"]]></title><description><![CDATA[
<p>Been using Shinka Evolve for a while now, but sometimes I just want it to use claude code only (they require lots of API keys for a model ensemble). So, I made claude-evolve, a claude code plugin for doing the same thing. The model ensemble is less powerful (thinking effort x [opus, sonnet, haiku]) but I've been using it and it's been useful enough to share it with some folks!</p>
]]></description><pubDate>Tue, 21 Apr 2026 10:42:53 +0000</pubDate><link>https://news.ycombinator.com/item?id=47847016</link><dc:creator>samuelzxu</dc:creator><comments>https://news.ycombinator.com/item?id=47847016</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47847016</guid></item><item><title><![CDATA[Claude Evolve: ShinkaEvolve code evolution on only Claude Code]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/samuelzxu/claude-evolve">https://github.com/samuelzxu/claude-evolve</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47847015">https://news.ycombinator.com/item?id=47847015</a></p>
<p>Points: 2</p>
<p># Comments: 1</p>
]]></description><pubDate>Tue, 21 Apr 2026 10:42:53 +0000</pubDate><link>https://github.com/samuelzxu/claude-evolve</link><dc:creator>samuelzxu</dc:creator><comments>https://news.ycombinator.com/item?id=47847015</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47847015</guid></item><item><title><![CDATA[New comment by samuelzxu in "Space Elevator"]]></title><description><![CDATA[
<p>Sprites are AWESOME! They look so cool, does anyone know a good place apart from wikipedia to read about them?</p>
]]></description><pubDate>Thu, 20 Apr 2023 19:45:32 +0000</pubDate><link>https://news.ycombinator.com/item?id=35645259</link><dc:creator>samuelzxu</dc:creator><comments>https://news.ycombinator.com/item?id=35645259</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=35645259</guid></item><item><title><![CDATA[New comment by samuelzxu in "NaturalSpeech 2: Zero-shot speech and singing synthesizers"]]></title><description><![CDATA[
<p>Woah! How is this not more popular? I don't see it referenced in the naturalspeech2 paper anywhere.</p>
]]></description><pubDate>Wed, 19 Apr 2023 17:22:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=35630792</link><dc:creator>samuelzxu</dc:creator><comments>https://news.ycombinator.com/item?id=35630792</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=35630792</guid></item><item><title><![CDATA[New comment by samuelzxu in "NaturalSpeech 2: Zero-shot speech and singing synthesizers"]]></title><description><![CDATA[
<p>Does anyone know how many words would correspond to the diffusion model's batch size of 6000 frames?</p>
]]></description><pubDate>Wed, 19 Apr 2023 17:19:16 +0000</pubDate><link>https://news.ycombinator.com/item?id=35630755</link><dc:creator>samuelzxu</dc:creator><comments>https://news.ycombinator.com/item?id=35630755</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=35630755</guid></item><item><title><![CDATA[NaturalSpeech2: LDMs are Natural and Zero-Shot Speech and Singing Synthesizers]]></title><description><![CDATA[
<p>Article URL: <a href="https://speechresearch.github.io/naturalspeech2/">https://speechresearch.github.io/naturalspeech2/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=35619474">https://news.ycombinator.com/item?id=35619474</a></p>
<p>Points: 5</p>
<p># Comments: 0</p>
]]></description><pubDate>Tue, 18 Apr 2023 20:20:54 +0000</pubDate><link>https://speechresearch.github.io/naturalspeech2/</link><dc:creator>samuelzxu</dc:creator><comments>https://news.ycombinator.com/item?id=35619474</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=35619474</guid></item><item><title><![CDATA[New comment by samuelzxu in "The Infernal Desire Machines of Doctor Hoffman"]]></title><description><![CDATA[
<p>Curious to know whether anyone else here have read this, and their thoughts on it. I've just finished my first reading and found it entirely impossible to stop until I had read the whole thing. I've left a comment to kick off a discussion:<p>- There's an obvious symmetry with our own times, where stories and facts are smeared together. It's touching how clear it rings of "we see what we want to see" in the modern world of an infinitude of hot takes and narratives. Of course, even more recently, generative AI puts an even more literal spin in this direction.<p>- Desire and Will. In this book these two are differentiated in that desire cannot be changed, whereas you can will a desire into existence. I'm not sure about the philosophical basis of this - I've not read The World As Will and Representation - but I have a feeling it might strike some similar notes.<p>- In the interest of not spoiling the book, I'll say the carnal stuff is very in-your-face and deliberately so. The author was definitely shocking when she tried to be.</p>
]]></description><pubDate>Mon, 27 Mar 2023 01:12:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=35321697</link><dc:creator>samuelzxu</dc:creator><comments>https://news.ycombinator.com/item?id=35321697</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=35321697</guid></item><item><title><![CDATA[The Infernal Desire Machines of Doctor Hoffman]]></title><description><![CDATA[
<p>Article URL: <a href="https://en.wikipedia.org/wiki/The_Infernal_Desire_Machines_of_Doctor_Hoffman">https://en.wikipedia.org/wiki/The_Infernal_Desire_Machines_of_Doctor_Hoffman</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=35321696">https://news.ycombinator.com/item?id=35321696</a></p>
<p>Points: 3</p>
<p># Comments: 1</p>
]]></description><pubDate>Mon, 27 Mar 2023 01:12:06 +0000</pubDate><link>https://en.wikipedia.org/wiki/The_Infernal_Desire_Machines_of_Doctor_Hoffman</link><dc:creator>samuelzxu</dc:creator><comments>https://news.ycombinator.com/item?id=35321696</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=35321696</guid></item><item><title><![CDATA[New comment by samuelzxu in "Show HN: Unscribbler – Simple Handwriting Reader"]]></title><description><![CDATA[
<p>Thanks for the feedback! I tested the app out on my android tablet, and my S pen worked fine on my tablet. I'm not sure about Windows though ...</p>
]]></description><pubDate>Thu, 23 Mar 2023 14:27:59 +0000</pubDate><link>https://news.ycombinator.com/item?id=35275354</link><dc:creator>samuelzxu</dc:creator><comments>https://news.ycombinator.com/item?id=35275354</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=35275354</guid></item><item><title><![CDATA[New comment by samuelzxu in "Show HN: Unscribbler – Simple Handwriting Reader"]]></title><description><![CDATA[
<p>Thanks for the feedback! Yeah, it fails in some very simple cases, but does really well in others. I believe it does the best if your letters are tightly grouped, and can even recognize cursive pretty well, but space the letters out and it fails pretty easily ;)</p>
]]></description><pubDate>Thu, 23 Mar 2023 14:26:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=35275327</link><dc:creator>samuelzxu</dc:creator><comments>https://news.ycombinator.com/item?id=35275327</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=35275327</guid></item><item><title><![CDATA[New comment by samuelzxu in "Show HN: Unscribbler – Simple Handwriting Reader"]]></title><description><![CDATA[
<p>This is a handwriting-to-text converter! Just follow the instructions on the page and you're good to go :)<p>Background: I've been tutoring on the side for a while and it's apparent that the whole process can be smoothed out, with the end goal being an AI tutor buddy with a stylus interface. This is a little step in that direction.<p>As for implementation details, I forked excalidraw (at <a href="https://github.com/excalidraw">https://github.com/excalidraw</a>), got a gcp free tier instance running, and scraped together a Google K8s Engine cluster serving with torchserve. Luckily there's a great deal on the public preview of c3 cpus at the moment. For the model, I'm using trocr-base-handwritten ( <a href="https://huggingface.co/microsoft/trocr-base-handwritten" rel="nofollow">https://huggingface.co/microsoft/trocr-base-handwritten</a> ).<p>Let me know if anyone has any ideas, suggestions, and/or tips!</p>
]]></description><pubDate>Wed, 22 Mar 2023 21:45:32 +0000</pubDate><link>https://news.ycombinator.com/item?id=35267486</link><dc:creator>samuelzxu</dc:creator><comments>https://news.ycombinator.com/item?id=35267486</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=35267486</guid></item><item><title><![CDATA[Show HN: Unscribbler – Simple Handwriting Reader]]></title><description><![CDATA[
<p>This is a handwriting-to-text converter! Just follow the instructions on the page and you're good to go :)<p>Background: I've been tutoring on the side for a while and it's apparent that the whole process can be smoothed out, with the end goal being an AI tutor buddy with a stylus interface. This is a little step in that direction.<p>As for implementation details, I forked excalidraw (at <a href="https://github.com/excalidraw">https://github.com/excalidraw</a>), got a gcp free tier instance running, and scraped together a Google K8s Engine cluster serving with  torchserve. Luckily there's a great deal on the public preview of c3 cpus at the moment. For the model, I'm using trocr-base-handwritten ( <a href="https://huggingface.co/microsoft/trocr-base-handwritten" rel="nofollow">https://huggingface.co/microsoft/trocr-base-handwritten</a> ).<p>Let me know if anyone has any ideas, suggestions, and/or tips!</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=35264204">https://news.ycombinator.com/item?id=35264204</a></p>
<p>Points: 17</p>
<p># Comments: 7</p>
]]></description><pubDate>Wed, 22 Mar 2023 17:21:14 +0000</pubDate><link>https://www.board.samuelxu.com/</link><dc:creator>samuelzxu</dc:creator><comments>https://news.ycombinator.com/item?id=35264204</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=35264204</guid></item><item><title><![CDATA[New comment by samuelzxu in "High-res image reconstruction with latent diffusion models from human brain"]]></title><description><![CDATA[
<p>There's also this paper with very similar methodology called Mind-Vis, and also accepted to CVPR 2023.
<a href="https://mind-vis.github.io/" rel="nofollow">https://mind-vis.github.io/</a></p>
]]></description><pubDate>Fri, 03 Mar 2023 22:53:14 +0000</pubDate><link>https://news.ycombinator.com/item?id=35016121</link><dc:creator>samuelzxu</dc:creator><comments>https://news.ycombinator.com/item?id=35016121</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=35016121</guid></item></channel></rss>