<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: janilowski</title><link>https://news.ycombinator.com/user?id=janilowski</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Wed, 29 Jul 2026 12:20:40 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=janilowski" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by janilowski in "If coding has been solved, why does software keep getting worse?"]]></title><description><![CDATA[
<p>Lower barrier to entry = more crap flooding the market</p>
]]></description><pubDate>Sun, 26 Jul 2026 08:36:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=49055977</link><dc:creator>janilowski</dc:creator><comments>https://news.ycombinator.com/item?id=49055977</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=49055977</guid></item><item><title><![CDATA[Forgejo v16.0: Granular Watching, Better Reviews, Safer Integrations]]></title><description><![CDATA[
<p>Article URL: <a href="https://forgejo.org/2026-07-release-v16-0/">https://forgejo.org/2026-07-release-v16-0/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48933817">https://news.ycombinator.com/item?id=48933817</a></p>
<p>Points: 4</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 16 Jul 2026 12:55:04 +0000</pubDate><link>https://forgejo.org/2026-07-release-v16-0/</link><dc:creator>janilowski</dc:creator><comments>https://news.ycombinator.com/item?id=48933817</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48933817</guid></item><item><title><![CDATA[New comment by janilowski in "Price per 1M tokens is meaningless"]]></title><description><![CDATA[
<p><a href="https://news.ycombinator.com/item?id=48821204">https://news.ycombinator.com/item?id=48821204</a></p>
]]></description><pubDate>Tue, 07 Jul 2026 18:17:04 +0000</pubDate><link>https://news.ycombinator.com/item?id=48821478</link><dc:creator>janilowski</dc:creator><comments>https://news.ycombinator.com/item?id=48821478</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48821478</guid></item><item><title><![CDATA[New comment by janilowski in "Price per 1M tokens is meaningless"]]></title><description><![CDATA[
<p>I'd say it's more like going to a Ferrari dealership and they tell you they will build a car for you and bill you per gram of parts used. It might also not work. And they might also not build it ever, really — but they will bill you for any attempts to build it.</p>
]]></description><pubDate>Tue, 07 Jul 2026 18:15:19 +0000</pubDate><link>https://news.ycombinator.com/item?id=48821453</link><dc:creator>janilowski</dc:creator><comments>https://news.ycombinator.com/item?id=48821453</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48821453</guid></item><item><title><![CDATA[New comment by janilowski in "Price per 1M tokens is meaningless"]]></title><description><![CDATA[
<p>I am not sure if pricing actually reflects inference costs</p>
]]></description><pubDate>Tue, 07 Jul 2026 17:58:15 +0000</pubDate><link>https://news.ycombinator.com/item?id=48821252</link><dc:creator>janilowski</dc:creator><comments>https://news.ycombinator.com/item?id=48821252</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48821252</guid></item><item><title><![CDATA[New comment by janilowski in "Price per 1M tokens is meaningless"]]></title><description><![CDATA[
<p>Yes that's true, although calculating the exact discount you get using a subscription could be difficult, especially since the labs often don't state their actual limits and just tell you you get "more usage" or "even more usage" or "5x the usage" (but how much exactly is x?).<p>It is clear we are getting a very meaningful discount by using a subscription though. I once checked how much would I pay for Codex after about 3 months of non-daily use if I only bought "credits". Couldn't believe it when it came out to be north of $1000 (I paid them $20/month in that period).</p>
]]></description><pubDate>Tue, 07 Jul 2026 17:53:35 +0000</pubDate><link>https://news.ycombinator.com/item?id=48821204</link><dc:creator>janilowski</dc:creator><comments>https://news.ycombinator.com/item?id=48821204</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48821204</guid></item><item><title><![CDATA[New comment by janilowski in "Price per 1M tokens is meaningless"]]></title><description><![CDATA[
<p>Well yeah this benchmark I've quoted is quite large, I believe they use thousands of diverse tasks, so this average cost per task could be a more accurate representation of how expensive each model actually is to run.</p>
]]></description><pubDate>Tue, 07 Jul 2026 17:44:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=48821103</link><dc:creator>janilowski</dc:creator><comments>https://news.ycombinator.com/item?id=48821103</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48821103</guid></item><item><title><![CDATA[New comment by janilowski in "Price per 1M tokens is meaningless"]]></title><description><![CDATA[
<p>I also don't see much of a quality difference switching between thinking levels while using those models as agents.</p>
]]></description><pubDate>Tue, 07 Jul 2026 17:42:26 +0000</pubDate><link>https://news.ycombinator.com/item?id=48821079</link><dc:creator>janilowski</dc:creator><comments>https://news.ycombinator.com/item?id=48821079</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48821079</guid></item><item><title><![CDATA[Price per 1M tokens is meaningless]]></title><description><![CDATA[
<p>Article URL: <a href="https://janilowski.pl/en/blog/2026/price-per-m-tokens/">https://janilowski.pl/en/blog/2026/price-per-m-tokens/</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48809542">https://news.ycombinator.com/item?id=48809542</a></p>
<p>Points: 142</p>
<p># Comments: 103</p>
]]></description><pubDate>Mon, 06 Jul 2026 19:43:36 +0000</pubDate><link>https://janilowski.pl/en/blog/2026/price-per-m-tokens/</link><dc:creator>janilowski</dc:creator><comments>https://news.ycombinator.com/item?id=48809542</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48809542</guid></item><item><title><![CDATA[New comment by janilowski in "Macaroni – a single HTML file messenger"]]></title><description><![CDATA[
<p>It's very impractical.<p>- you get a slower first load (cannot progressively fetch resources as they're needed)
- can't reuse a stylesheet, script or image on a different page (each has to have their own copy)
- can't cache commonly used files
- can't make granular changes to specific parts of the code. user has to reload everything each time. 
- can't set a proper content security policy<p>And many more! It's cool for a tiny demo but for anything serious you wouldn't want a single (extremely ugly) HTML file.</p>
]]></description><pubDate>Thu, 11 Jun 2026 08:03:12 +0000</pubDate><link>https://news.ycombinator.com/item?id=48487627</link><dc:creator>janilowski</dc:creator><comments>https://news.ycombinator.com/item?id=48487627</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48487627</guid></item><item><title><![CDATA[New comment by janilowski in "Goodbye to Sora"]]></title><description><![CDATA[
<p>From the linked Hollywood reporter article:<p>"...the AI company exits the video generation business."<p>"OpenAI, led by CEO Sam Altman, is not getting out of the AI video business [...], of course... "<p>I hate journalism.</p>
]]></description><pubDate>Wed, 25 Mar 2026 07:13:45 +0000</pubDate><link>https://news.ycombinator.com/item?id=47514257</link><dc:creator>janilowski</dc:creator><comments>https://news.ycombinator.com/item?id=47514257</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47514257</guid></item><item><title><![CDATA[New comment by janilowski in "Ask HN: How to be alone?"]]></title><description><![CDATA[
<p>There are no tricks but you can manage it to an extent.<p>- Find activities you can do *outside*, regularly, preferably with a group. Things that worked for me: Learn japanese (group lessons only! Invite everyone for a beer afterwards), find a literature club, go swimming every other day, go cycling when bored.<p>- Reach out to friends and acquaintances you didn't speak to in a while. Some won't reply, others will be delighted you reached out. Most people meet their s/o through mutual acquaintances.<p>- Go on websites like Meetup (or whatever event board is most popular on your area) and go to every event you can manage. If you're not the type to strike conversations with random strangers then find events looking for speakers or hosts and people will come up to you themselves.<p>It's *very normal* to feel empty when a large part of your life is suddenly not there. I couldn't get rid of that feeling at any point when I was alone. Fill in the empty time and space, try finding someone else in a while but don't rush it—otherwise you risk yet another breakup.</p>
]]></description><pubDate>Mon, 09 Mar 2026 13:39:51 +0000</pubDate><link>https://news.ycombinator.com/item?id=47308948</link><dc:creator>janilowski</dc:creator><comments>https://news.ycombinator.com/item?id=47308948</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=47308948</guid></item></channel></rss>