Chill some Netflix and Chill

Finally, Netflix you can chill.

justin.searls.co

Hot Sleeper

The summer heat ended up thawing out my podcast, so I had no choice but to go buy a new microphone and grumble into it for a couple hours. Just how that works. Please enjoy. I am actively soliciting mailbag participation. As always, the address is podcast@searls.co, and I'd be really curious to hear how America is doing because it seems like everything is going great. For the first time I let Claude write these links for me, because it never occurred to me I didn't have to format the markdown manually:

justin.searls.co

Content Hiatus

I've decided to go on a content hiatus. This will be my last dispatch for a while. I don't know how long I'll be gone. Why? Because I've been posting to an anonymous audience on the Internet almost every day since I was eleven years old. I posted through Bill Clinton's impeachment, 9/11, the Iraq War, the Deepwater Horizon oil spill, the version of Siri that would tell you where to hide a body (https://www.theverge.com/2011/10/12/2486618/siri-weird-iphone-4s), binders full of women, and a pandemic that changed everything and then nothing at all. Very few of my friends live like I do. They aren't pundits. They don't post takes. They lead normal-looking lives, maintain healthy-seeming relationships, and have better hair than I do. These people are a mystery to me. Where do their excess opinions go? What do they do with all their creative ideas? Do any of them actually rinse and repeat, and does it even make a difference? How do they beat back the encroaching loneliness of existence? You probably already know the answers to the above questions, because odds are you're among the vast majority of people who don't post. Unfortunately for the present author, my adolescence was inextricably tangled up in the hunt for page views. I grew up mistaking attention for validation and validation for meaningful human connection. This did my adult psyche no favors. Like a bad Speed spinoff, it's as if a crude bomb was wired to a Geocities hit counter (https://wideangle.co/blog/visitor-counter-geocities-and-the-90s) and planted deep inside my brain—rigged to explode if I should ever fall below 3 shitposts per week. I have no way to know if it's safe to log off until I give up and stop posting. On a less dramatic note, the idea of "being just a little bit more chill" strikes the exasperated attention whore in me as exotic and titillating. Who knows, maybe this change will make room for a new hobby, like pickleball or methamphetamines. I'm already starting to see the appeal. I've managed to avoid firing off so much as a pithy one-liner since my most recent episode of Breaking Change (https://justin.searls.co/casts/breaking-change-v53-pod-freeze/) on March 20th. I'm honestly loving it so far: actually listening to people when they talk, making substantive progress on my higher-priority projects, and sitting silently with my thoughts instead of workshopping them all into tweets. Normally, this is the part of the newsletter where I'd list off bullet points to highlight everything I created in the last month, but now that I've entered my post-content era, I simply cannot be fussed. You're smart, you can figure out how to visit a website (https://justin.searls.co) and scroll down. This is me pivoting. I'm no longer optimizing for "reach," but rather "happiness (https://theoatmeal.com/comics/unhappy)." I've been speed-running life in pursuit of financial independence and overall self-reliance, but… for what? So I could waste hours every other week editing a podcast? At some point or another, I should probably make good on all the things I promised myself back when I was mortgaging my health and hairline on the life of freedom I now enjoy. We only have so many days in this world, which is why I routinely pause and ponder, "what does my perfect day look like?" Fortunately, I'm already doing a lot of the things I love doing. But when I close my eyes and imagine my ideal morning, noon, and night, I don't see myself manically tweaking a blog post or slavishly editing a video. I mean, look at me. These are not the crow's feet of a man who has endless time to fuck around with that shit: Signing off for now. If you ever miss me, you can always drop a line (justin@searls.co). – Justin

justin.searls.co

Pod Freeze

The promise of Breaking Change is that with every major version (this being the 60th episode of the program, but only the 53rd such release), I will break something. Well, I finally did it. I think I broke the show. Find out how by listening for yourself! Want to be my friend? Drop me a line at justin@searls.co. Want to file a complaint with my supervisor? Forward your concerns to podcast@searls.co. These links may rot, but alas—death comes for us all:

justin.searls.co

freeCodeCamp: Which Devs Are Screwed?

Quincy Larson (https://www.freecodecamp.org/news/author/quincy/) over at freeCodeCamp (https://www.freecodecamp.org) had me on their podcast to discuss how the rapidly changing software industry is impacting junior developers and what they can do about it. I don't normally spend time talking about this stuff, because I started programming in the 90s and can't claim to know anything about what it's like to just be starting now. I've also always discouraged people from getting into software development unless they're super passionate about it, which has been out of step with the "learn to code" hype train that gathered steam over the last fifteen years only to run into a brick wall recently.

justin.searls.co

Models are commodities, harnesses are differentiators

Ben Thompson's latest (https://stratechery.com/2026/agents-over-bubbles/) rests on a single load-bearing assumption: that the harness and the model are tightly coupled, the way Apple's hardware and software are. It follows, then, that if agents require integration between model and harness, that the companies building that integration—specifically Anthropic and OpenAI—are actually poised to be significantly more profitable than it might have seemed as recently as late last year. This assumption is incorrect. To date, agents have not clearly benefited from proprietary integration to their favored model. I thought this was obvious, but I sometimes forget that not everybody else has made it their full-time hobby to mix and match various coding agents with various large language models for the past year.

justin.searls.co

Dual-loop BDD is the new Red-green TDD

This one goes out to all the testing neophytes who only recently realized (https://simonwillison.net/guides/agentic-engineering-patterns/red-green-tdd/) that it's useful to have an automated means of verifying their code does what it claims to do. For the last month, I've been working on prove_it (https://github.com/searls/prove_it), a framework for building quality harnesses for Claude Code (https://claude.com/product/claude-code)—primarily via its hooks system (https://code.claude.com/docs/en/hooks). In a recent release, I added TDD enforcement to its default configuration. First, it injects a test-first development approach into every plan Claude generates. Then, a PreToolUse hook follows up with permissionDecisionReason reminders whenever the agent deviates from the one true path (e.g., repeatedly edits source files without touching any tests, never runs a test to see it fail, etc.).

justin.searls.co

Red-green rally

I'm still iterating on my experimental Claude Code verification harness, prove_it (https://github.com/searlsco/prove_it). This week my focus has been on nudging agents to practice test-driven development. Traditionally, we called this "TDD", but which has recently been renamed to "red-green TDD" as it has been discovered that this is what LLMs interpret as "real TDD". Anyway, so that I could watch it steer an agent in a fresh codebase in real time, I opened a new directory and asked Claude Code to one-shot a terminal-based tennis game, replete with scoring and an AI that I couldn't beat. In OCaml. And it worked! It actually test-drove everything. Neat!

justin.searls.co

Len Testa: Bring back the Starcruiser

Today, we're joined by a very special guest, Len Testa (https://bsky.app/profile/lentesta.bsky.social)! You might know him from The Disney Dish podcast (https://podcasts.jimhillmedia.com/show/the-disney-dish-with-jim-hill/) or from his excellent theme park travel planning app Touring Plans (https://touringplans.com). Or you might not know him at all! No wrong answers. This episode is all about Disney's ill-fated Star Wars: Galactic Starcruiser (https://en.wikipedia.org/wiki/Star_Wars:_Galactic_Starcruiser) live action role-playing hotel—which we both had the opportunity to experience right when it first launched. It was a life-changing experience for both of us, so why did it fail? Is it true that the top Disney brass learned all the wrong lessons from that failure? And will the CEO-in-waiting Josh D'Amaro ever have the courage to attempt something so ambitious again? Listen to this episode, in which we speak with an unearned confidence that suggests we have all of these answers! You can reach out to Len at len@touringplans.com and you can write into the show at podcast@searls.co. He'll read your e-mail and reply to it, but I may only skim it.

justin.searls.co