<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: anon1253</title><link>https://news.ycombinator.com/user?id=anon1253</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Mon, 25 May 2026 20:58:18 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=anon1253" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[An attempt at explaining bipolar disorder and psychosis]]></title><description><![CDATA[
<p>Article URL: <a href="https://osf.io/w28g9_v1">https://osf.io/w28g9_v1</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47996521">https://news.ycombinator.com/item?id=47996521</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 03 May 2026 12:58:25 +0000</pubDate><link>https://osf.io/w28g9_v1</link><dc:creator>anon1253</dc:creator><comments>https://news.ycombinator.com/item?id=47996521</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47996521</guid></item><item><title><![CDATA[An attempt at explaining bipolar disorder and psychosis]]></title><description><![CDATA[
<p>Article URL: <a href="https://osf.io/preprints/psyarxiv/w28g9_v1">https://osf.io/preprints/psyarxiv/w28g9_v1</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47919269">https://news.ycombinator.com/item?id=47919269</a></p>
<p>Points: 4</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 27 Apr 2026 09:00:28 +0000</pubDate><link>https://osf.io/preprints/psyarxiv/w28g9_v1</link><dc:creator>anon1253</dc:creator><comments>https://news.ycombinator.com/item?id=47919269</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47919269</guid></item><item><title><![CDATA[Show HN: Llamora, a local-first journaling environment]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/joelkuiper/Llamora">https://github.com/joelkuiper/Llamora</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47111880">https://news.ycombinator.com/item?id=47111880</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 22 Feb 2026 15:41:46 +0000</pubDate><link>https://github.com/joelkuiper/Llamora</link><dc:creator>anon1253</dc:creator><comments>https://news.ycombinator.com/item?id=47111880</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47111880</guid></item><item><title><![CDATA[New comment by anon1253 in "Prism"]]></title><description><![CDATA[
<p>Slightly off-topic but related: currently I'm in a research environment (biomedicine) where a lot of AI is used. Sometimes well, often poorly. So as an exercise I drafted some rules and commitments about AI and research ("Research After AI: Principles for Accelerated Exploration" [1]), I took the Agile manifesto as a starting point. Anyways, this might be interesting as a perspective on the problem space as I see it.<p>[1] <a href="https://gist.github.com/joelkuiper/d52cc0e5ff06d12c85e492e4295ca890" rel="nofollow">https://gist.github.com/joelkuiper/d52cc0e5ff06d12c85e492e42...</a></p>
]]></description><pubDate>Wed, 28 Jan 2026 07:44:26 +0000</pubDate><link>https://news.ycombinator.com/item?id=46792245</link><dc:creator>anon1253</dc:creator><comments>https://news.ycombinator.com/item?id=46792245</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46792245</guid></item><item><title><![CDATA[Research After AI: Principles for Accelerated Exploration]]></title><description><![CDATA[
<p>Article URL: <a href="https://gist.github.com/joelkuiper/d52cc0e5ff06d12c85e492e4295ca890">https://gist.github.com/joelkuiper/d52cc0e5ff06d12c85e492e4295ca890</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46748372">https://news.ycombinator.com/item?id=46748372</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Sat, 24 Jan 2026 22:28:42 +0000</pubDate><link>https://gist.github.com/joelkuiper/d52cc0e5ff06d12c85e492e4295ca890</link><dc:creator>anon1253</dc:creator><comments>https://news.ycombinator.com/item?id=46748372</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46748372</guid></item><item><title><![CDATA[AI and academic research: the Manifesto for Accelerated Exploration]]></title><description><![CDATA[
<p>Article URL: <a href="https://gist.github.com/joelkuiper/d52cc0e5ff06d12c85e492e4295ca890">https://gist.github.com/joelkuiper/d52cc0e5ff06d12c85e492e4295ca890</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=46741901">https://news.ycombinator.com/item?id=46741901</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Sat, 24 Jan 2026 08:07:44 +0000</pubDate><link>https://gist.github.com/joelkuiper/d52cc0e5ff06d12c85e492e4295ca890</link><dc:creator>anon1253</dc:creator><comments>https://news.ycombinator.com/item?id=46741901</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46741901</guid></item><item><title><![CDATA[Llamora is an experimental, local-first diary companion]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/joelkuiper/Llamora">https://github.com/joelkuiper/Llamora</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=45050369">https://news.ycombinator.com/item?id=45050369</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 28 Aug 2025 10:07:09 +0000</pubDate><link>https://github.com/joelkuiper/Llamora</link><dc:creator>anon1253</dc:creator><comments>https://news.ycombinator.com/item?id=45050369</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=45050369</guid></item><item><title><![CDATA[Show HN: A minimal Flask and Htmx and LangChain (with llama.cpp) interface]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/joelkuiper/flask-htmx-llm">https://github.com/joelkuiper/flask-htmx-llm</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=44787104">https://news.ycombinator.com/item?id=44787104</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Mon, 04 Aug 2025 15:22:38 +0000</pubDate><link>https://github.com/joelkuiper/flask-htmx-llm</link><dc:creator>anon1253</dc:creator><comments>https://news.ycombinator.com/item?id=44787104</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=44787104</guid></item><item><title><![CDATA[I wrote a book [Dutch/NL][pdf]]]></title><description><![CDATA[
<p>Article URL: <a href="https://entoenvoormijnlotgenoten.nl/files/book.pdf">https://entoenvoormijnlotgenoten.nl/files/book.pdf</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=39065581">https://news.ycombinator.com/item?id=39065581</a></p>
<p>Points: 4</p>
<p># Comments: 1</p>
]]></description><pubDate>Sat, 20 Jan 2024 08:01:13 +0000</pubDate><link>https://entoenvoormijnlotgenoten.nl/files/book.pdf</link><dc:creator>anon1253</dc:creator><comments>https://news.ycombinator.com/item?id=39065581</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=39065581</guid></item><item><title><![CDATA[New comment by anon1253 in "Subsec fluctuations in extracellular dopamine encode prediction errors in humans"]]></title><description><![CDATA[
<p>It always fascinated me how a lot of "state" in our neural networks is probably encoded in the extracellular fluids rather than in the neurons themselves. Biological neural networks really do not like it if you swap out their fluids (you can do this experimentally in vitro). For me it has always been one of those "nature really doesn't care about complexity" things ... it will just use whatever tools are available with little to no regard for our understanding of "boundaries". I'm not saying this complexity is strictly needed for intelligence (however that is defined) ... but I do always find it a little bit dishonest when scientists (and especially those working with pharmaceuticals) "zoom in" to the cells and then usually promptly forget that those cells are part of the much wider stage of tissues and eventually even everything outside the confines of our skin. Anyway, just my two cents.</p>
]]></description><pubDate>Sun, 10 Dec 2023 10:25:28 +0000</pubDate><link>https://news.ycombinator.com/item?id=38590603</link><dc:creator>anon1253</dc:creator><comments>https://news.ycombinator.com/item?id=38590603</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=38590603</guid></item><item><title><![CDATA[New comment by anon1253 in "Multifaceted: The linguistic echo chambers of LLMs"]]></title><description><![CDATA[
<p>It's a fascinating topic. I've often been surprised by its use of "tapestry" (as in "the tapestry of existence") and I never really figured out why it seems to gravitate towards such a relatively uncommon phrase. As usual I am reading too much into it (seemingly the logit for "tapestry" was higher than the others), but why? And what do these preferences tell us about the LLMs more generally? Anyway, fascinating!</p>
]]></description><pubDate>Sun, 03 Dec 2023 10:47:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=38506137</link><dc:creator>anon1253</dc:creator><comments>https://news.ycombinator.com/item?id=38506137</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=38506137</guid></item><item><title><![CDATA[New comment by anon1253 in "Ask HN: What are some unpopular technologies you wish people knew more about?"]]></title><description><![CDATA[
<p>RDF and semantic web used to be my goto's for this, as I believe many of the core ideas are still valid and often overlooked and sometimes even poorly re-implemented. Which says something.<p>However, lately I've come to like llama.cpp and friends, yes it's not ChatGTP miracle whatever but how often do you /actually/ need that? Despite its tremendous popularity, it still seems like something more people should know about. For me, I've had great fun with running LLMs locally and experiencing their different "flavors" from a more "phenomenological" (what is it like to use them) perspective rather than a technological one.</p>
]]></description><pubDate>Sat, 02 Dec 2023 15:52:23 +0000</pubDate><link>https://news.ycombinator.com/item?id=38499435</link><dc:creator>anon1253</dc:creator><comments>https://news.ycombinator.com/item?id=38499435</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=38499435</guid></item><item><title><![CDATA[A chat about "the process of reality appears mental"]]></title><description><![CDATA[
<p>Article URL: <a href="https://chat.openai.com/share/ea0dab81-2cb1-465a-be27-84ab7460b846">https://chat.openai.com/share/ea0dab81-2cb1-465a-be27-84ab7460b846</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=38304837">https://news.ycombinator.com/item?id=38304837</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Fri, 17 Nov 2023 15:25:14 +0000</pubDate><link>https://chat.openai.com/share/ea0dab81-2cb1-465a-be27-84ab7460b846</link><dc:creator>anon1253</dc:creator><comments>https://news.ycombinator.com/item?id=38304837</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=38304837</guid></item><item><title><![CDATA[Stupid Ideas Revived: a chat about consciousness and reality]]></title><description><![CDATA[
<p>Article URL: <a href="https://chat.openai.com/share/8a4a3085-4668-40af-86fa-f2a5dbb40d4b">https://chat.openai.com/share/8a4a3085-4668-40af-86fa-f2a5dbb40d4b</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=38209692">https://news.ycombinator.com/item?id=38209692</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 09 Nov 2023 19:25:49 +0000</pubDate><link>https://chat.openai.com/share/8a4a3085-4668-40af-86fa-f2a5dbb40d4b</link><dc:creator>anon1253</dc:creator><comments>https://news.ycombinator.com/item?id=38209692</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=38209692</guid></item><item><title><![CDATA[A chat about therapy, Metzinger, Kastrup, and Whitehead]]></title><description><![CDATA[
<p>Article URL: <a href="https://chat.openai.com/share/06753ce3-3fae-4aa5-b442-5341c6aba1cb">https://chat.openai.com/share/06753ce3-3fae-4aa5-b442-5341c6aba1cb</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=38188075">https://news.ycombinator.com/item?id=38188075</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 08 Nov 2023 08:48:38 +0000</pubDate><link>https://chat.openai.com/share/06753ce3-3fae-4aa5-b442-5341c6aba1cb</link><dc:creator>anon1253</dc:creator><comments>https://news.ycombinator.com/item?id=38188075</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=38188075</guid></item><item><title><![CDATA[New comment by anon1253 in "Mistral 7B"]]></title><description><![CDATA[
<p>Code is up <a href="https://github.com/vortext/esther">https://github.com/vortext/esther</a> but it's still heavily work in progress :-)</p>
]]></description><pubDate>Sun, 15 Oct 2023 19:10:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=37892473</link><dc:creator>anon1253</dc:creator><comments>https://news.ycombinator.com/item?id=37892473</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=37892473</guid></item><item><title><![CDATA[Show HN: Esther, an idea for a diary app that embeds an LLM]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/vortext/esther">https://github.com/vortext/esther</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=37891397">https://news.ycombinator.com/item?id=37891397</a></p>
<p>Points: 11</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 15 Oct 2023 16:59:26 +0000</pubDate><link>https://github.com/vortext/esther</link><dc:creator>anon1253</dc:creator><comments>https://news.ycombinator.com/item?id=37891397</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=37891397</guid></item><item><title><![CDATA[New comment by anon1253 in "Ask HN: Show me your half baked project"]]></title><description><![CDATA[
<p><a href="https://github.com/vortext/esther">https://github.com/vortext/esther</a><p>Esther is my personal project to develop a diary app that talks back. Basically. Along the way I learned how to htmx, llama.cpp via JNA and practical experience with LLMs. I suffer from type-1 bipolar disorder with psychoses and normal life just ain't gonna happen. So unemployed, single, #nolife ... I decided to build a chat bot for myself. It's not finished the RAG stuff still needs implementing, but oh well. It's written in Clojure on GraalVM (because I wanted to try polyglot) other than that it's nothing /too/ fancy ... but it feels great having an LLM + UI you can just build the way you like it</p>
]]></description><pubDate>Thu, 12 Oct 2023 17:47:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=37860417</link><dc:creator>anon1253</dc:creator><comments>https://news.ycombinator.com/item?id=37860417</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=37860417</guid></item><item><title><![CDATA[New comment by anon1253 in "Mistral 7B"]]></title><description><![CDATA[
<p>Cool! And on top of that TheBloke has the quantized models of course:<p><a href="https://huggingface.co/TheBloke/Mistral-7B-v0.1-GGUF" rel="nofollow noreferrer">https://huggingface.co/TheBloke/Mistral-7B-v0.1-GGUF</a><p><a href="https://huggingface.co/TheBloke/Mistral-7B-OpenOrca-GGUF" rel="nofollow noreferrer">https://huggingface.co/TheBloke/Mistral-7B-OpenOrca-GGUF</a><p><a href="https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF" rel="nofollow noreferrer">https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGU...</a><p>I typically run my models with the 5_K_M or 6_K quantization, but it really depends on the use case and requirements</p>
]]></description><pubDate>Wed, 11 Oct 2023 18:27:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=37848341</link><dc:creator>anon1253</dc:creator><comments>https://news.ycombinator.com/item?id=37848341</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=37848341</guid></item><item><title><![CDATA[New comment by anon1253 in "Mistral 7B"]]></title><description><![CDATA[
<p>Probably soon! I'll post it here. Still finalizing some Retrieval Augmented Generation things. It's written in Clojure with a very thin HTMX front-end. However there are some interesting things like using gbnf grammar constraints creatively for chain-of-thought reasoning. It's a one-person job though but I've always wanted a diary that feels like someone to talk to, and the tech is finally here!</p>
]]></description><pubDate>Wed, 11 Oct 2023 18:12:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=37848135</link><dc:creator>anon1253</dc:creator><comments>https://news.ycombinator.com/item?id=37848135</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=37848135</guid></item></channel></rss>