<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: queueueue</title><link>https://news.ycombinator.com/user?id=queueueue</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Tue, 15 Sep 2026 15:59:23 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=queueueue" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by queueueue in "Hyundai buys Boston Dynamics"]]></title><description><![CDATA[
<p>But for now, humanoids are still relatively incompetent. So if you're rich enough and you want things done like cleaning and cooking, it's more convenient to hire a human and give them specific instructions instead of buying a robot that can currently do only half the things they want to get done. Or they just want a nice gadget.</p>
]]></description><pubDate>Fri, 19 Jun 2026 20:15:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=48602768</link><dc:creator>queueueue</dc:creator><comments>https://news.ycombinator.com/item?id=48602768</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48602768</guid></item><item><title><![CDATA[New comment by queueueue in "AI coding assistants are getting worse?"]]></title><description><![CDATA[
<p>Ironic that I’m going to give another anecdotal experience here, but I’ve noticed this myself too. I catch myself trying to keep on prompting after an llm has not been able to solve some problem in a specific way. While I can probably do it faster at that point if I switch to doing it fully myself. Maybe because the llm output feels like its ‘almost there’, or some sunken cost fallacy.</p>
]]></description><pubDate>Fri, 09 Jan 2026 13:26:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=46553572</link><dc:creator>queueueue</dc:creator><comments>https://news.ycombinator.com/item?id=46553572</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=46553572</guid></item><item><title><![CDATA[New comment by queueueue in "I just want to code (2023)"]]></title><description><![CDATA[
<p>For me, this has somehow gotten to a point where I keep questioning myself if I’m actually doing something out of curiosity or because of the idea I could share something with other people or some other motive. So I’m not even sure what I’m curious about anymore, which might sound ridiculous.</p>
]]></description><pubDate>Mon, 28 Apr 2025 06:22:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=43818195</link><dc:creator>queueueue</dc:creator><comments>https://news.ycombinator.com/item?id=43818195</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43818195</guid></item><item><title><![CDATA[New comment by queueueue in "Tarpit ideas: What they are and how to avoid them (2023) [video]"]]></title><description><![CDATA[
<p>Not sure about AI specific but:
Todo apps, habit trackers, lots of social media, job boards, recommendation apps, fun things to do with friends, travel planners, trackers (movies/books).
I think it’s more common for B2C because these are things that a lot of people come across.<p>Some of these ideas could maybe be done better now that we have genAI but the question might would it work as a standalone app or is it just a feature?</p>
]]></description><pubDate>Fri, 25 Apr 2025 08:17:10 +0000</pubDate><link>https://news.ycombinator.com/item?id=43791397</link><dc:creator>queueueue</dc:creator><comments>https://news.ycombinator.com/item?id=43791397</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43791397</guid></item><item><title><![CDATA[New comment by queueueue in "Show HN: I built an app to stop me doomscrolling by touching grass"]]></title><description><![CDATA[
<p>Apple has a screentime API which allows the app/dev to block an app after the user chooses it</p>
]]></description><pubDate>Mon, 24 Feb 2025 23:30:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=43166199</link><dc:creator>queueueue</dc:creator><comments>https://news.ycombinator.com/item?id=43166199</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=43166199</guid></item><item><title><![CDATA[New comment by queueueue in "Every HTML Element"]]></title><description><![CDATA[
<p>I've counted 18! The next one was blank.</p>
]]></description><pubDate>Sat, 25 Jan 2025 22:47:31 +0000</pubDate><link>https://news.ycombinator.com/item?id=42825714</link><dc:creator>queueueue</dc:creator><comments>https://news.ycombinator.com/item?id=42825714</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42825714</guid></item><item><title><![CDATA[New comment by queueueue in "Show HN: FastGraphRAG – Better RAG using good old PageRank"]]></title><description><![CDATA[
<p>I don't see how this is not possible using knowledge graphs? You retrieve the entity, Sharon, and the additional context you get will be the nodes and edges close to Sharon. After this it becomes the LLM's job because if it is not mentioned in the given context, it should let the prompter know "In the given context the occupation of Sharon could not be found".</p>
]]></description><pubDate>Tue, 19 Nov 2024 20:36:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=42187832</link><dc:creator>queueueue</dc:creator><comments>https://news.ycombinator.com/item?id=42187832</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42187832</guid></item><item><title><![CDATA[New comment by queueueue in "The Beginner's Guide to Visual Prompt Injections (2023)"]]></title><description><![CDATA[
<p>I had to double check the date the article was posted because all 4 examples, while using ChatGPT 4o, did not give the output mentioned in the article. It seems the examples are old, which becomes obvious when you look at the chat interface of the screenshots in the article. They do not match the current ChatGPT interface. I'm sure there are new ways to do visual prompt injection though!</p>
]]></description><pubDate>Wed, 13 Nov 2024 21:52:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=42130454</link><dc:creator>queueueue</dc:creator><comments>https://news.ycombinator.com/item?id=42130454</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42130454</guid></item><item><title><![CDATA[New comment by queueueue in "ChatGPT for Teams"]]></title><description><![CDATA[
<p>The API is not used for training purposes either. <a href="https://openai.com/enterprise-privacy" rel="nofollow">https://openai.com/enterprise-privacy</a></p>
]]></description><pubDate>Thu, 11 Jan 2024 14:59:37 +0000</pubDate><link>https://news.ycombinator.com/item?id=38953015</link><dc:creator>queueueue</dc:creator><comments>https://news.ycombinator.com/item?id=38953015</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=38953015</guid></item></channel></rss>