My muse

I have a memory of learning Terraform and Pulumi just to avoid the pain of web UIs for AWS, GCP, and Azure. A while back, my agents started using the CLI instead. And lately I've felt a bit of nostalgia, and a bit of sadness. because a project I love, like Pulumi, doesn't make sense in an agentic future.

Banger

i had 12 Claude agents running in parallel for 6 hours and i managed to reverse engineer @supabase i'm making it available here so that you can save your tokens - 100% free & open-source: github.com/supabase/supabase

Ben Horowitz on treating your story as your strategy, and why founders often skip writing it even though it's one of the most important parts of the job: "The story of the company is also the strategy of the company... In your mind, you're kind of adjusting that strategy a little bit at a time every day. But then a quarter later, it's actually pretty different than what you started with." "So it's really important that you keep upgrading your story. The articulation of your story. I would definitely recommend it be in written form." "Something that you can share with everybody in the company, and everybody you're recruiting, everybody you're trying to raise money from, all your constituents, every customer." "The problem that I think founders have is it doesn't feel like work. Like, 'What are you doing today?' 'I'm working on my story.' That doesn't sound like work." "Because it doesn't feel like work, people don't do it, but it's probably one of the most important parts of the job." @bhorowitz w/ @speedrun GP @Tocelot

Alexandr Wang on what matters in an age of abundant intelligence: “The scarce resource isn’t going to be intelligence or agency. I really think it’s going to be vision and ambition.” “Do you have a clear view of what you want the world to look like in the future? What is the one way in which you wanna put your finger on the scale for how the future of the world will develop?” “AI will make that easier... But the flip side of that is then all of a sudden you can dream bigger.”

People wanna hate on this but I do think 2-3 days, staying up late, of extended focused pour your soul and mind into the computer and do almost nothing else is the ideal coding flow now. Unfortunately most jobs (and most people) are not setup to handle this or practiced with this intense on/off cycle, so it’s sounds and looks crazy. Not for everyone. But like the standard tech co office hours of 9-5 or more, 5 days a week with crazy amounts of context switching and meetings is an insane working style too and produces many undesirable psychological effects. Neither of these approaches are without health concerns nor downsides. Worst part of my job by far is the way hours are imposed as a regular low grade chronic stress grind and not these intense sessions. I would prefer a more manic and obsessive work style personally. It genuinely takes hours to get into a full proper vibecoding flow state. Similar to how meditating 20 minutes a day doesn’t really kick in until day 10 or so. Takes time for neurons to change and your body to get there. By hour 12 of vibecoding you reach areas of thought and creativity you can’t reach otherwise. Alas the plight of the creative and the obsessed. People see out of distribution individuals and yet don’t seem to wonder if their quirks and flaws are what lead to their successes in other areas in the first place.

OpenAI just hired someone who’s going to make them look at their data. A lot. 🤣

Took the Roadster off Earth. Moon and Mars are live now Each world has its own gravity, plus dust storms, precision landings, and a ghost you can race roadster-aerial-demo.netlify…

What a beautiful surprise to discover that most of Tailscale’s code is open source. The core client (including `tailscaled` and the CLI) lives on GitHub under a BSD license, and the Linux and Android clients are fully open source. Really nice to see.

as AI accelerates execution it also raises our expectations for how quickly things should get done speed only matters when the direction is right a perfectly executed project can still fail if the original specification is wrong which makes prioritization scoping and clear specs more important than ever

was at a community event and was asked a somewhat sad question: should developers be afraid of the labs eating the new possibilities jev opens up? with AI (system one) + software (system two): 1. there's no going back to a world without system one models 2. you control the software! 3. there's no way AI could beat the efficiency of this combo 4. you don't even send the model providers your whole program logic I think the days of "wrapper" apps will be seen as some of the darkest in software because people essentially did all of their programming in a system message and sent it over to a third party who was incentivized to bake that behavior into their 1st party product... keeping your logic in code and only asking AI for the minimum reverses that and keeps all of your logic yours. if you decompose enough, model providers can't even figure out what you're working on

There seem to be two groups: 1. Better-is-better group believes that agents finally make the better-is-better solutions happen. Formal methods, static types, Nix, ... 2. Worse-is-better group believes agents will make worse-is-better solution happen because with agents they're no longer worse. Dynamic type systems, bash scripts over neat DSLs, agents running tests dynamically, ... Quite funny to see

Taleb's barbell strategy

one man’s treasure is another man’s slop

This is my favorite essay I've read in the past 3 years or so. It argues that what all we and all other lifeforms really want is "Adaptive Complexity": a sort of Goldilocks-like perfect balance of complexity in our lives: not too stressed, not too bored. It's easy to pick it apart, but it's a useful framing. You can use it to explain all sorts of phenomena, such as why toxic fan bases form. Enjoyable read, highly recommend. contrapositive.substack.com/…

Don't blame the agent for writing the bad test Blame the codebase for allowing the bad test to be written

i’m sorry armin, but your nuanced take doesn’t fit my biased world view and incentives

Loving Gloss so far. I connected the MCP and my agent saved ~50 essays and papers from my X bookmarks in minutes, all sorted by topic. A few ideas: handle JS-heavy pages, follow redirects and a quick way to check what's already saved before bulk imports. @nutlope Happy to share the specific links if useful.

i feel like swe interviews could probably collapse into just 2 technical rounds: • system design (how well can you articulate your ideas, do you actually know how to engineer something) • onsite project to build a real thing with agents (can you translate your intent into high quality outcomes) everything else we used to ask is no longer necessary