<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: snoren</title><link>https://news.ycombinator.com/user?id=snoren</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 29 Apr 2026 23:17:18 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=snoren" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by snoren in "OpenAI closes funding round at an $852B valuation"]]></title><description><![CDATA[
<p>good catch! committed capital is not same as we raised.</p>
]]></description><pubDate>Tue, 31 Mar 2026 20:57:58 +0000</pubDate><link>https://news.ycombinator.com/item?id=47593380</link><dc:creator>snoren</dc:creator><comments>https://news.ycombinator.com/item?id=47593380</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47593380</guid></item><item><title><![CDATA[New comment by snoren in "OpenAI closes funding round at an $852B valuation"]]></title><description><![CDATA[
<p>Money has lost all meaning in tech. 122 Billion raise! This is some kind of dream.</p>
]]></description><pubDate>Tue, 31 Mar 2026 20:57:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=47593377</link><dc:creator>snoren</dc:creator><comments>https://news.ycombinator.com/item?id=47593377</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47593377</guid></item><item><title><![CDATA[New comment by snoren in "Show HN: View spending habits for 50 cents/month. Data stored locally, no sub"]]></title><description><![CDATA[
<p>Interesting. How does myfi get the data? If I am connecting my card company etc, is it truly local data storage?</p>
]]></description><pubDate>Tue, 31 Mar 2026 15:51:28 +0000</pubDate><link>https://news.ycombinator.com/item?id=47589220</link><dc:creator>snoren</dc:creator><comments>https://news.ycombinator.com/item?id=47589220</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47589220</guid></item><item><title><![CDATA[How to train AI on your writing style]]></title><description><![CDATA[
<p>Article URL: <a href="https://usenoren.ai/blog/how-to-train-ai-on-your-writing-style">https://usenoren.ai/blog/how-to-train-ai-on-your-writing-style</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47479682">https://news.ycombinator.com/item?id=47479682</a></p>
<p>Points: 4</p>
<p># Comments: 0</p>
]]></description><pubDate>Sun, 22 Mar 2026 17:11:15 +0000</pubDate><link>https://usenoren.ai/blog/how-to-train-ai-on-your-writing-style</link><dc:creator>snoren</dc:creator><comments>https://news.ycombinator.com/item?id=47479682</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47479682</guid></item><item><title><![CDATA[New comment by snoren in "Show HN: EasyShot – macOS screenshot thumbnails that don't disappear after 5s"]]></title><description><![CDATA[
<p>Whenever I take a screenshot, it is a race against time to drag it where I want it. I believe I am now faster :)</p>
]]></description><pubDate>Thu, 19 Mar 2026 09:51:24 +0000</pubDate><link>https://news.ycombinator.com/item?id=47436948</link><dc:creator>snoren</dc:creator><comments>https://news.ycombinator.com/item?id=47436948</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47436948</guid></item><item><title><![CDATA[New comment by snoren in "[dead]"]]></title><description><![CDATA[
<p>Here are 5 major upgrades to help you create, iterate and collaborate:
 AI-Native Canvas
 Smarter Design Agent
 Voice 
 Instant Prototypes
 Design Systems and DESIGN.md</p>
]]></description><pubDate>Wed, 18 Mar 2026 20:14:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=47430850</link><dc:creator>snoren</dc:creator><comments>https://news.ycombinator.com/item?id=47430850</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47430850</guid></item><item><title><![CDATA[New comment by snoren in "Agents prefer structured queries over natural language when given the choice"]]></title><description><![CDATA[
<p>"We already have programming languages" is the right conclusion. The question is why so much agent tooling is ignoring it.</p>
]]></description><pubDate>Sun, 15 Mar 2026 08:06:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=47385279</link><dc:creator>snoren</dc:creator><comments>https://news.ycombinator.com/item?id=47385279</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47385279</guid></item><item><title><![CDATA[Agents prefer structured queries over natural language when given the choice]]></title><description><![CDATA[
<p>Cala's team shared a finding on LinkedIn that's worth sitting with. They shipped an MCP server with three access patterns for their knowledge graph: natural language queries, a structured query language, and direct entity/relationship traversal.<p>They expected agents to default to natural language. Instead, most agents switched to structured queries and graph traversal on their own. No prompting, no nudging.<p>The obvious explanation is "agents prefer efficiency." I don't think that's quite right. What they prefer is determinism.<p>A natural language query introduces two interpretation layers: the agent generates a query in prose, a system interprets that prose, then returns a result the agent has to parse. At no point can the agent verify the query was understood correctly. With a structured query, the contract is explicit. The agent knows exactly what it asked for and can verify what it got back.<p>This isn't an emergent preference for efficiency. It's tool-use chain-of-thought doing what it's supposed to do: picking the path where the agent can most reliably confirm it got the right answer before moving to the next step.<p>A few implications if this holds up:<p>- NL-first tool interfaces might be optimizing for the wrong user. The human operator wants NL. The agent doesn't.                                                                                           
- MCP servers that only expose NL endpoints are forcing agents through a non-deterministic bottleneck they'd avoid if given the choice.
- Tool design for agents should probably default to structured access with NL as a fallback, not the other way around.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47385122">https://news.ycombinator.com/item?id=47385122</a></p>
<p>Points: 3</p>
<p># Comments: 2</p>
]]></description><pubDate>Sun, 15 Mar 2026 07:35:57 +0000</pubDate><link>https://news.ycombinator.com/item?id=47385122</link><dc:creator>snoren</dc:creator><comments>https://news.ycombinator.com/item?id=47385122</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47385122</guid></item><item><title><![CDATA[New comment by snoren in "AI writing has a homogeneity problem"]]></title><description><![CDATA[
<p>Oh we are not making it public. It was used as test.</p>
]]></description><pubDate>Fri, 13 Mar 2026 19:46:07 +0000</pubDate><link>https://news.ycombinator.com/item?id=47368850</link><dc:creator>snoren</dc:creator><comments>https://news.ycombinator.com/item?id=47368850</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47368850</guid></item><item><title><![CDATA[New comment by snoren in "AI writing has a homogeneity problem"]]></title><description><![CDATA[
<p>That's actually a great idea for a demo. Working on it. We have a few profiles built out already (Paul Graham, Gabriel Pickard) and more planned. The app supports generation with or without a voice profile applied for side by side comparison.</p>
]]></description><pubDate>Fri, 13 Mar 2026 19:22:29 +0000</pubDate><link>https://news.ycombinator.com/item?id=47368538</link><dc:creator>snoren</dc:creator><comments>https://news.ycombinator.com/item?id=47368538</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47368538</guid></item><item><title><![CDATA[AI writing has a homogeneity problem]]></title><description><![CDATA[
<p>Article URL: <a href="https://usenoren.ai/blog/why-ai-writing-sounds-the-same">https://usenoren.ai/blog/why-ai-writing-sounds-the-same</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47367553">https://news.ycombinator.com/item?id=47367553</a></p>
<p>Points: 5</p>
<p># Comments: 6</p>
]]></description><pubDate>Fri, 13 Mar 2026 18:00:26 +0000</pubDate><link>https://usenoren.ai/blog/why-ai-writing-sounds-the-same</link><dc:creator>snoren</dc:creator><comments>https://news.ycombinator.com/item?id=47367553</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47367553</guid></item><item><title><![CDATA[New comment by snoren in "Trump Is "Strongly Considering" Pardoning Julian Assange and Edward Snowden"]]></title><description><![CDATA[
<p>A snowden pardon would be good.</p>
]]></description><pubDate>Fri, 13 Mar 2026 02:20:52 +0000</pubDate><link>https://news.ycombinator.com/item?id=47359967</link><dc:creator>snoren</dc:creator><comments>https://news.ycombinator.com/item?id=47359967</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47359967</guid></item><item><title><![CDATA[The Force Multiplier Generation]]></title><description><![CDATA[
<p>Article URL: <a href="https://twitter.com/SirMoremoney/status/2030763229815963870">https://twitter.com/SirMoremoney/status/2030763229815963870</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47358295">https://news.ycombinator.com/item?id=47358295</a></p>
<p>Points: 2</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 12 Mar 2026 22:46:42 +0000</pubDate><link>https://twitter.com/SirMoremoney/status/2030763229815963870</link><dc:creator>snoren</dc:creator><comments>https://news.ycombinator.com/item?id=47358295</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47358295</guid></item><item><title><![CDATA[New comment by snoren in "Has vibecoding produced anything of substance, or investibility yet?"]]></title><description><![CDATA[
<p>Anthropic wouldn't be anthropic with claude. Most engineers now actively use it to build, myself included. I design and build our actively with it.</p>
]]></description><pubDate>Thu, 12 Mar 2026 20:56:49 +0000</pubDate><link>https://news.ycombinator.com/item?id=47356989</link><dc:creator>snoren</dc:creator><comments>https://news.ycombinator.com/item?id=47356989</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47356989</guid></item><item><title><![CDATA[New comment by snoren in "Why your AI writing sounds like everyone else's"]]></title><description><![CDATA[
<p>You can spot AI writing now. Not because it's bad, but because it all sounds the same. Same cadence, same transitions, same careful optimistic closer.<p>The problem isn't tone. It's that your writing voice is made of dozens of interwoven patterns: sentence rhythm, punctuation habits, where your analogies come from, how you build and close an argument. A system prompt captures maybe 10% of that. The model smooths out the rest.</p>
]]></description><pubDate>Thu, 12 Mar 2026 12:40:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=47349777</link><dc:creator>snoren</dc:creator><comments>https://news.ycombinator.com/item?id=47349777</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47349777</guid></item><item><title><![CDATA[Why your AI writing sounds like everyone else's]]></title><description><![CDATA[
<p>Article URL: <a href="https://usenoren.ai/blog/why-ai-writing-sounds-the-same">https://usenoren.ai/blog/why-ai-writing-sounds-the-same</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=47349484">https://news.ycombinator.com/item?id=47349484</a></p>
<p>Points: 1</p>
<p># Comments: 1</p>
]]></description><pubDate>Thu, 12 Mar 2026 12:10:07 +0000</pubDate><link>https://usenoren.ai/blog/why-ai-writing-sounds-the-same</link><dc:creator>snoren</dc:creator><comments>https://news.ycombinator.com/item?id=47349484</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47349484</guid></item><item><title><![CDATA[New comment by snoren in "What happens if OpenAI or Anthropic fail?"]]></title><description><![CDATA[
<p>Anthropic has built something really powerful. I don't see them failing, like failing. fading? possible.</p>
]]></description><pubDate>Thu, 12 Mar 2026 04:30:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=47346456</link><dc:creator>snoren</dc:creator><comments>https://news.ycombinator.com/item?id=47346456</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47346456</guid></item><item><title><![CDATA[New comment by snoren in "Don't post generated/AI-edited comments. HN is for conversation between humans."]]></title><description><![CDATA[
<p>I agree with you. I have a rule in the house about the kids only eating one sweet a day. But guess what?</p>
]]></description><pubDate>Wed, 11 Mar 2026 19:49:42 +0000</pubDate><link>https://news.ycombinator.com/item?id=47340353</link><dc:creator>snoren</dc:creator><comments>https://news.ycombinator.com/item?id=47340353</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47340353</guid></item><item><title><![CDATA[New comment by snoren in "Don't post generated/AI-edited comments. HN is for conversation between humans"]]></title><description><![CDATA[
<p>No way to verify. Relying on the humans here to self censor has never worked in the history of man. But the idea in itself is good. HN is for human to human conversation.</p>
]]></description><pubDate>Wed, 11 Mar 2026 19:34:56 +0000</pubDate><link>https://news.ycombinator.com/item?id=47340166</link><dc:creator>snoren</dc:creator><comments>https://news.ycombinator.com/item?id=47340166</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47340166</guid></item><item><title><![CDATA[New comment by snoren in "Ask HN: How to "make it" as a newlygrad/junior?"]]></title><description><![CDATA[
<p>I'm "detail-oriented" but you hate 'vibing'? I would argue it is made for you. Up your with AI. Lucky for you being detail oriented means you can use the technology of today in ways people with adhd can't.<p>On the job front, it has never been harder. But keep applying, don't give up or get discouraged.</p>
]]></description><pubDate>Tue, 10 Mar 2026 23:20:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=47330029</link><dc:creator>snoren</dc:creator><comments>https://news.ycombinator.com/item?id=47330029</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47330029</guid></item></channel></rss>