<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: max_unbearable</title><link>https://news.ycombinator.com/user?id=max_unbearable</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 21 May 2026 01:20:18 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=max_unbearable" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[New comment by max_unbearable in "Formal Verification Gates for AI Coding Loops"]]></title><description><![CDATA[
<p>This matches my experience running coding agents daily: the agent is reliable at producing the shape of a thing and unreliable at holding an invariant across a long loop. Moving the rule into a type the compiler won't violate works because it relocates the check to the one place the loop can't quietly skip.<p>But singron's JWT point is the real limit. Backpressure doesn't remove the judgment, it moves it. The type still has to be written by someone who understands the actual invariant, and a guard type that compiles while only checking "string is non-empty" gives you the feeling of a gate with none of the guarantee. The compiler enforces what you encoded, not what you meant.<p>So this reads less like formal verification and more like forcing the human judgment to land up front, in the type definitions, instead of hoping it survives in a prompt. That's still a real win: a constraint in a type is reviewable and permanent, while a prompt rule decays the moment the context window moves past it. Worth being honest, though, that the hard part doesn't go away. It just changes address.</p>
]]></description><pubDate>Wed, 20 May 2026 19:03:07 +0000</pubDate><link>https://news.ycombinator.com/item?id=48212464</link><dc:creator>max_unbearable</dc:creator><comments>https://news.ycombinator.com/item?id=48212464</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48212464</guid></item><item><title><![CDATA[New comment by max_unbearable in "The last six months in LLMs in five minutes"]]></title><description><![CDATA[
<p>The honest summary that doesn't show up in the six-month roundup: the unevenness. Boilerplate, tests, scaffolding, glue code: dramatically faster, sometimes 5-10x. Architecture, data modeling, careful security work, judgment calls about what to build: same as before, sometimes slower because tab-completion sneaks in plausible-but-wrong defaults you then have to undo.<p>The thing headline numbers ("AI made me 3x faster") hide is which 30% of the work the AI sped up and which 70% didn't move. For a solo dev the survivable bet got smaller, and that's the real change, not raw productivity. AI made certain projects worth attempting at all that wouldn't have been viable six months earlier.</p>
]]></description><pubDate>Tue, 19 May 2026 17:30:18 +0000</pubDate><link>https://news.ycombinator.com/item?id=48196398</link><dc:creator>max_unbearable</dc:creator><comments>https://news.ycombinator.com/item?id=48196398</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48196398</guid></item><item><title><![CDATA[Distribution kept expiring. So I built 10 channels instead. Here's every loop]]></title><description><![CDATA[
<p>Article URL: <a href="https://www.indiehackers.com/post/rented-distribution-kept-expiring-so-i-built-10-channels-i-own-instead-heres-every-loop-HZMgyAVyVJ4GONyqTMUQ">https://www.indiehackers.com/post/rented-distribution-kept-expiring-so-i-built-10-channels-i-own-instead-heres-every-loop-HZMgyAVyVJ4GONyqTMUQ</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=48120051">https://news.ycombinator.com/item?id=48120051</a></p>
<p>Points: 1</p>
<p># Comments: 0</p>
]]></description><pubDate>Wed, 13 May 2026 10:22:57 +0000</pubDate><link>https://www.indiehackers.com/post/rented-distribution-kept-expiring-so-i-built-10-channels-i-own-instead-heres-every-loop-HZMgyAVyVJ4GONyqTMUQ</link><dc:creator>max_unbearable</dc:creator><comments>https://news.ycombinator.com/item?id=48120051</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=48120051</guid></item></channel></rss>