<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: rileyt</title><link>https://news.ycombinator.com/user?id=rileyt</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 09 Apr 2026 10:55:36 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=rileyt" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by rileyt in "Daemons that clean up the mess agents leave behind"]]></title><description><![CDATA[
<p>it's similar to triggers, but with a routing layer that combines semantic triggers and memory. the magic is defining them as files in the repo (like skills) and not worrying about the execution.</p>
]]></description><pubDate>Wed, 18 Mar 2026 16:31:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=47427828</link><dc:creator>rileyt</dc:creator><comments>https://news.ycombinator.com/item?id=47427828</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47427828</guid></item><item><title><![CDATA[New comment by rileyt in "Daemons that clean up the mess agents leave behind"]]></title><description><![CDATA[
<p>the working spec is files like `.agents/daemons/<name>/DAEMON.md` and they have access to skills and rules in the repo so you don't need to duplicate them.<p>you could even have a daemon that just says to run an existing skill.</p>
]]></description><pubDate>Wed, 18 Mar 2026 16:09:02 +0000</pubDate><link>https://news.ycombinator.com/item?id=47427533</link><dc:creator>rileyt</dc:creator><comments>https://news.ycombinator.com/item?id=47427533</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47427533</guid></item><item><title><![CDATA[New comment by rileyt in "Why the next agent interface is shared"]]></title><description><![CDATA[
<p>seems like and appropriate way to share.</p>
]]></description><pubDate>Fri, 06 Feb 2026 15:20:23 +0000</pubDate><link>https://news.ycombinator.com/item?id=46913902</link><dc:creator>rileyt</dc:creator><comments>https://news.ycombinator.com/item?id=46913902</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46913902</guid></item><item><title><![CDATA[Using GPT-4 to fix the Twitter Doge logo]]></title><description><![CDATA[
<p>Article URL: <a href="https://twitter.com/rileytomasek/status/1644022700073951235">https://twitter.com/rileytomasek/status/1644022700073951235</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=35471376">https://news.ycombinator.com/item?id=35471376</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 06 Apr 2023 17:12:14 +0000</pubDate><link>https://twitter.com/rileytomasek/status/1644022700073951235</link><dc:creator>rileyt</dc:creator><comments>https://news.ycombinator.com/item?id=35471376</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=35471376</guid></item><item><title><![CDATA[New comment by rileyt in "Show HN: Factual AI Q&A – Answers based on Huberman Lab transcripts"]]></title><description><![CDATA[
<p>It was less than $2 to embed all 100+ episodes with the new OpenAI embeddings and was as easy as just making a bunch of API calls. Pretty hard to beat that experience.</p>
]]></description><pubDate>Sun, 18 Dec 2022 18:40:43 +0000</pubDate><link>https://news.ycombinator.com/item?id=34041063</link><dc:creator>rileyt</dc:creator><comments>https://news.ycombinator.com/item?id=34041063</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=34041063</guid></item><item><title><![CDATA[New comment by rileyt in "Show HN: Factual AI Q&A – Answers based on Huberman Lab transcripts"]]></title><description><![CDATA[
<p>It's not fine tuned. You literally just add something like "if the answer to the question isn't in the context, say 'I don't know'" It's wild.</p>
]]></description><pubDate>Sat, 17 Dec 2022 23:52:50 +0000</pubDate><link>https://news.ycombinator.com/item?id=34033532</link><dc:creator>rileyt</dc:creator><comments>https://news.ycombinator.com/item?id=34033532</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=34033532</guid></item><item><title><![CDATA[New comment by rileyt in "Show HN: Factual AI Q&A – Answers based on Huberman Lab transcripts"]]></title><description><![CDATA[
<p>Thanks a lot. It's nice when people appreciate the stuff I build for fun.<p>The UI is my own design system that I will open source at some point. The app is Remix with a Redis cache to keep things snappy.</p>
]]></description><pubDate>Sat, 17 Dec 2022 23:51:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=34033525</link><dc:creator>rileyt</dc:creator><comments>https://news.ycombinator.com/item?id=34033525</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=34033525</guid></item><item><title><![CDATA[New comment by rileyt in "Show HN: Factual AI Q&A – Answers based on Huberman Lab transcripts"]]></title><description><![CDATA[
<p>Old version? Works on latest for me, but the CSS uses @layer which doesn't have great support with older browsers.</p>
]]></description><pubDate>Sat, 17 Dec 2022 23:47:55 +0000</pubDate><link>https://news.ycombinator.com/item?id=34033490</link><dc:creator>rileyt</dc:creator><comments>https://news.ycombinator.com/item?id=34033490</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=34033490</guid></item><item><title><![CDATA[New comment by rileyt in "Show HN: Factual AI Q&A – Answers based on Huberman Lab transcripts"]]></title><description><![CDATA[
<p>The embeddings cost less than $2 for all 100+ episodes. The cost for the answering calls to davinci are around $30 so far.</p>
]]></description><pubDate>Sat, 17 Dec 2022 23:01:21 +0000</pubDate><link>https://news.ycombinator.com/item?id=34033182</link><dc:creator>rileyt</dc:creator><comments>https://news.ycombinator.com/item?id=34033182</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=34033182</guid></item><item><title><![CDATA[New comment by rileyt in "Show HN: Factual AI Q&A – Answers based on Huberman Lab transcripts"]]></title><description><![CDATA[
<p>It uses Whisper for transcripts, which I believe are better than the YouTube generated ones.<p>My guess is that there are more relevant results from the semantic search than I'm including in the context (to reduce costs) and that exact snippet isn't being given to the answering model as context.</p>
]]></description><pubDate>Sat, 17 Dec 2022 22:59:50 +0000</pubDate><link>https://news.ycombinator.com/item?id=34033164</link><dc:creator>rileyt</dc:creator><comments>https://news.ycombinator.com/item?id=34033164</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=34033164</guid></item><item><title><![CDATA[New comment by rileyt in "Show HN: Factual AI Q&A – Answers based on Huberman Lab transcripts"]]></title><description><![CDATA[
<p>You're welcome :)</p>
]]></description><pubDate>Sat, 17 Dec 2022 20:58:17 +0000</pubDate><link>https://news.ycombinator.com/item?id=34032167</link><dc:creator>rileyt</dc:creator><comments>https://news.ycombinator.com/item?id=34032167</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=34032167</guid></item><item><title><![CDATA[Show HN: Factual AI Q&A – Answers based on Huberman Lab transcripts]]></title><description><![CDATA[
<p>This is a quick prototype I built for semantic search and factual question answering using embeddings and GPT-3.<p>It tries to solve the LLM hallucination issue by guiding it only to answer questions from the given context instead of making things up. If you ask something not covered in an episode, it should say that it doesn't know rather than providing a plausible, but potentially incorrect response.<p>It uses Whisper to transcribe, text-embedding-ada-002 to embed, Pinecone.io to search, and text-davinci-003 to generate the answer.<p>More examples and explanations here: <a href="https://twitter.com/rileytomasek/status/1603854647575384067" rel="nofollow">https://twitter.com/rileytomasek/status/1603854647575384067</a></p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=34030389">https://news.ycombinator.com/item?id=34030389</a></p>
<p>Points: 120</p>
<p># Comments: 43</p>
]]></description><pubDate>Sat, 17 Dec 2022 18:05:04 +0000</pubDate><link>https://huberman.rile.yt/</link><dc:creator>rileyt</dc:creator><comments>https://news.ycombinator.com/item?id=34030389</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=34030389</guid></item><item><title><![CDATA[New comment by rileyt in "Show HN: Scrollable ChatGPT Share URLs"]]></title><description><![CDATA[
<p>Ha, nice work getting ChatGPT to do it. I started down the same route, but wanted to get it done fast so I'm just grabbing the relevant HTML and then adding a few styles to clean up things like controls.</p>
]]></description><pubDate>Mon, 05 Dec 2022 21:05:42 +0000</pubDate><link>https://news.ycombinator.com/item?id=33871919</link><dc:creator>rileyt</dc:creator><comments>https://news.ycombinator.com/item?id=33871919</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=33871919</guid></item><item><title><![CDATA[Show HN: Scrollable ChatGPT Share URLs]]></title><description><![CDATA[
<p>I was getting really sick of taking and sharing multiple screenshots every time I wanted to share a ChatGPT thread, so I made <a href="https://gpt.best/" rel="nofollow">https://gpt.best/</a><p>It's a minimal tool that creates shareable links [1] from ChatGPT conversations. It also has dynamic share images so you get a screenshot of the beginning of the thread for free.<p>1: <a href="https://gpt.best/k5Q5F9Up" rel="nofollow">https://gpt.best/k5Q5F9Up</a></p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=33871427">https://news.ycombinator.com/item?id=33871427</a></p>
<p>Points: 2</p>
<p># Comments: 2</p>
]]></description><pubDate>Mon, 05 Dec 2022 20:29:38 +0000</pubDate><link>https://gpt.best/</link><dc:creator>rileyt</dc:creator><comments>https://news.ycombinator.com/item?id=33871427</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=33871427</guid></item><item><title><![CDATA[New comment by rileyt in "My newsletter is making $2k per month with 7k subscribers – AMA"]]></title><description><![CDATA[
<p>Ryan never asked me to clean anything. However, I find it hard to work in messy spaces, so my workspace rarely looks like a "real" one.</p>
]]></description><pubDate>Fri, 29 Jul 2022 11:20:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=32275551</link><dc:creator>rileyt</dc:creator><comments>https://news.ycombinator.com/item?id=32275551</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=32275551</guid></item><item><title><![CDATA[New comment by rileyt in "Ask HN: What details do you want in job postings?"]]></title><description><![CDATA[
<p>My list:<p>1. Salary range<p>2. Remote work policy<p>3. Tech stack<p>4. The product/team the role is for</p>
]]></description><pubDate>Wed, 23 Mar 2022 18:04:38 +0000</pubDate><link>https://news.ycombinator.com/item?id=30781403</link><dc:creator>rileyt</dc:creator><comments>https://news.ycombinator.com/item?id=30781403</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=30781403</guid></item><item><title><![CDATA[Ask HN: What details do you want in job postings?]]></title><description><![CDATA[

<p>Comments URL: <a href="https://news.ycombinator.com/item?id=30781397">https://news.ycombinator.com/item?id=30781397</a></p>
<p>Points: 5</p>
<p># Comments: 5</p>
]]></description><pubDate>Wed, 23 Mar 2022 18:03:57 +0000</pubDate><link>https://news.ycombinator.com/item?id=30781397</link><dc:creator>rileyt</dc:creator><comments>https://news.ycombinator.com/item?id=30781397</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=30781397</guid></item><item><title><![CDATA[Digital Pharmacy Capsule Tops $1B with New Capital Raise]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.bloomberg.com/news/articles/2021-04-28/digital-pharmacy-capsule-tops-1-billion-with-new-capital-raise">https://www.bloomberg.com/news/articles/2021-04-28/digital-pharmacy-capsule-tops-1-billion-with-new-capital-raise</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=26969429">https://news.ycombinator.com/item?id=26969429</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 28 Apr 2021 13:58:14 +0000</pubDate><link>https://www.bloomberg.com/news/articles/2021-04-28/digital-pharmacy-capsule-tops-1-billion-with-new-capital-raise</link><dc:creator>rileyt</dc:creator><comments>https://news.ycombinator.com/item?id=26969429</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=26969429</guid></item><item><title><![CDATA[New comment by rileyt in "Ask HN: What are you working on?"]]></title><description><![CDATA[
<p>Im building an easy way to convert your LinkedIn profile to a PDF and web resume: <a href="https://standardresume.co/linkedin-resume-builder" rel="nofollow">https://standardresume.co/linkedin-resume-builder</a><p>Making a resume sucks, but it doesn't have to. With Standard Resume you can import your LinkedIn in one click, pick from 12 templates, and share it as a PDF, or web resume (great for casual applications and referrals).<p>It's a lightweight tech stack that I maintain myself. It's Firebase+React+Next, combined with a custom written PDF layout engine.<p>Web example: <a href="https://rsm.io/sidney-template" rel="nofollow">https://rsm.io/sidney-template</a><p>PDF example: <a href="https://assets.standardresume.co/image/upload/v1607879981/resume-templates/pdfs/sidney-professional-resume-template-pdf.pdf" rel="nofollow">https://assets.standardresume.co/image/upload/v1607879981/re...</a></p>
]]></description><pubDate>Fri, 15 Jan 2021 02:22:12 +0000</pubDate><link>https://news.ycombinator.com/item?id=25786164</link><dc:creator>rileyt</dc:creator><comments>https://news.ycombinator.com/item?id=25786164</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=25786164</guid></item><item><title><![CDATA[New comment by rileyt in "Dropbox to cut 11% of its global workforce"]]></title><description><![CDATA[
<p>If anyone who lost their job at Dropbox (or anywhere else) is reading this and needs help making a resume, email me and I'll give you a free month of <a href="https://standardresume.co" rel="nofollow">https://standardresume.co</a>.<p>riley@standardresume.co</p>
]]></description><pubDate>Wed, 13 Jan 2021 15:39:29 +0000</pubDate><link>https://news.ycombinator.com/item?id=25763312</link><dc:creator>rileyt</dc:creator><comments>https://news.ycombinator.com/item?id=25763312</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=25763312</guid></item></channel></rss>