https://blog.chughes.co/tags/llm/Recent content in Llm on Chris Hughes | Development JournalHugo -- 0.164.0en-usSat, 25 Jul 2026 00:00:00 +0000https://blog.chughes.co/posts/2026-07-25-what-happened-when-i-took-a-podcast-literally/Sat, 25 Jul 2026 00:00:00 +0000https://blog.chughes.co/posts/2026-07-25-what-happened-when-i-took-a-podcast-literally/<p><em>Written with Claude.</em></p> <p><img alt="Two boards compared. On a board of grid cells the void-framed item is picked 12 of 12 times and the cell-framed item 0 of 12. On a board of genuinely unmeasured competitors the same void-framed item is picked 5 of 24 times, while cell framing stays at 0 of 24." loading="lazy" src="https://blog.chughes.co/images/2026-07-25-what-happened-when-i-took-a-podcast-literally/hero.svg"></p> <h2 id="two-ideas-from-an-episode-about-curiosity-one-of-which-i-shipped-as-law-and-measured-the-same-day">Two ideas from an episode about curiosity, one of which I shipped as law and measured the same day</h2> <p>Taking a pop-science idea seriously turns out to mean two opposite-feeling things at once: you adopt it as a working standard for how you operate, and you stay willing to let a measurement kill the specific version of it you already wrote down. Both halves came out of one podcast episode on curiosity, and both halves landed in the same day of work. The half I adopted as a standard is still standing because it was never a claim about the world. The half I wrote into a governing document, the prose rulebook that the software agents in my workspace read before they act, came out of a 12-out-of-12 result and got narrowed before the day was out by probes built specifically to try to break it, and the thing that survived was not the thing I had been excited about.</p>