<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: eugeneonai</title><link>https://news.ycombinator.com/user?id=eugeneonai</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Fri, 05 Jun 2026 02:14:43 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=eugeneonai" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by eugeneonai in "Now AI agents need what RSS does"]]></title><description><![CDATA[
<p>Agree on RSS as the right shape — and worth adding the cost angle nobody's
  quantified here yet. Having an LLM read a 50KB HTML page is ~$0.03 of
  gpt-4o input. Polling 1000 sources hourly = ~$720/day, almost all of it
  tokenizing layout chrome the model throws away. RSS-shaped feeds drop
  that 90%+ because they strip to deltas. The harder blocker is the supply
  side though — publishers earn pennies per human pageview from ads and ~$0
  from agent polls, so unless feeds become licensed paid endpoints, the
  publisher incentive runs against your "publish an RSS feed for your
  content" recommendation. Just like that :)</p>
]]></description><pubDate>Wed, 03 Jun 2026 13:26:25 +0000</pubDate><link>https://news.ycombinator.com/item?id=48383722</link><dc:creator>eugeneonai</dc:creator><comments>https://news.ycombinator.com/item?id=48383722</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48383722</guid></item><item><title><![CDATA[New comment by eugeneonai in "Show HN: Paseo – Beautiful open-source coding agent interface"]]></title><description><![CDATA[
<p>Looks nice. The README pitches model-per-task picking but doesn't say
  much about context management. In coding-agent loops the full system
  prompt + tool specs re-send on every step — a 30-step task pays the
  input cost 30x. Prompt-cache headers catch the static prefix, but the
  per-step diff (file diffs, observation tokens) isn't cached, and that's
  often most of the input. Auto-summarizing older trajectory into a state
  vector saved 40-60% input tokens in workloads I've looked at — could be
  a useful daemon-side concern since users won't reach into each agent's
  internals.</p>
]]></description><pubDate>Wed, 03 Jun 2026 13:04:20 +0000</pubDate><link>https://news.ycombinator.com/item?id=48383469</link><dc:creator>eugeneonai</dc:creator><comments>https://news.ycombinator.com/item?id=48383469</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48383469</guid></item><item><title><![CDATA[New comment by eugeneonai in "I Hate the Weekends (2017)"]]></title><description><![CDATA[
<p>I agree, but my situation is a little different.<p>I try to squeeze my hobbies into the workweek, and it ends up happening after work.<p>I work from 10 a.m. to 10 p.m., then pursue my hobbies for a few more hours, leaving no time for a "personal life," let alone sleep.<p>But I can't physically move my hobbies to the weekend. If I did, I'd feel trapped and tied to a schedule. I can't do that. I need freedom, even if it's the same "freedom" that, in my mind, directly interferes with my sleep and, to some extent, my health, which I sacrifice for the sake of my hobby.<p>But it's important to understand what a "hobby" is.
A hobby is something I enjoy that positively impacts my life in one way or another. If your interest (hobby) "satisfies" you, then it will take precedence over sleep, food, and so on. Just like me.<p>My hobby is creating products to make life easier. Initially, it wasn't monetized, but with the addition of monetization, it now feels like the meaning of life.<p>I love weekends, I love weekdays, and I love my life with its many flaws and nuances. Thank you for the post. It was interesting, as I've been thinking about the same thing and still do, but I can't do anything about my "hobby" that I can't transfer, even though it could have been a better decision.</p>
]]></description><pubDate>Mon, 01 Jun 2026 17:57:09 +0000</pubDate><link>https://news.ycombinator.com/item?id=48360330</link><dc:creator>eugeneonai</dc:creator><comments>https://news.ycombinator.com/item?id=48360330</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48360330</guid></item><item><title><![CDATA[New comment by eugeneonai in "Fourth Grade Product Thinking"]]></title><description><![CDATA[
<p>Now I'll know where to get new ideas. I'm off to school, guys.<p>The most original things can truly be learned from people whose thinking isn't yet "proper" to adults. I've always thought about that.</p>
]]></description><pubDate>Mon, 01 Jun 2026 17:48:14 +0000</pubDate><link>https://news.ycombinator.com/item?id=48360208</link><dc:creator>eugeneonai</dc:creator><comments>https://news.ycombinator.com/item?id=48360208</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48360208</guid></item></channel></rss>