Devin Plumb

April is for some reason the least memorable month

@NotTuxedoSam I’m livin’ out in SF I drive a Tesla just to prove I’m a real big baller ‘cause I made a billion dollars And I spent it on GPUs

i took a pill in Marina to show a VC i was cool

.@RyanCarniato do you have a skill for solid llms are so bad at solid

These takes are always wrong. Sure, users don't care about code quality *directly* BUT they care about features shipping fast, bugs fixed quickly, & the app not degrading. That's all downstream of code quality. A messy codebase is velocity-killing tech debt & users feel it.

Before my flight from SFO->JFK took off the passenger next to me saw me saying a prayer and reassured me that JetBlue has a good safety record. I told her I was just praying for the Viasat Wifi not to crap out

i fucking love california

I feel this way as well. I suspect many people with the desire to build something meaningful share this fear. But nothing we do, not even the things we build, let us outrun death. One of my favorite poems, Ozymandias, is a veiled critique of Napoleon Bonaparte and King George III, whose egos had just laid waste to Europe: I met a traveller from an antique land, Who said—“Two vast and trunkless legs of stone Stand in the desert. . . . Near them, on the sand, Half sunk a shattered visage lies, whose frown, And wrinkled lip, and sneer of cold command, Tell that its sculptor well those passions read Which yet survive, stamped on these lifeless things, The hand that mocked them, and the heart that fed; And on the pedestal, these words appear: My name is Ozymandias, King of Kings; Look on my Works, ye Mighty, and despair!" Nothing beside remains. Round the decay Of that colossal Wreck, boundless and bare The lone and level sands stretch far away.

A moat most founders can only dream of: higher customer retention than uptime

@charliermarsh Congratulations, Charlie!

We've entered into an agreement to join OpenAI as part of the Codex team. I'm incredibly proud of the work we've done so far, incredibly grateful to everyone that's supported us, and incredibly excited to keep building tools that make programming feel different.

Core memory: telling the Accel partnership why I was so excited about a linter Congrats @charliermarsh and the @astral_sh team on everything you've done already for the Python community and excited for your next chapter at @OpenAI

Eventually, source code will be written in CI

The bottleneck has so quickly moved from code generation to code review that it is actually a bit jarring. None of the current systems / norms are setup for this world yet.

@alvinsng pnpm i solid-js

Entrepreneurship is more about stamina than it is about genius

@milichab @SpaceX @xai @JasonBud Congratulations, Andrew! Excited for you

I’m joining @SpaceX and @xai with @JasonBud. X is the company realizing science fiction - reusable rockets, humanoid robots, data centers in space, and more. Almost 10 years ago, I joined SpaceX as an intern on Dragon 2 crew displays. This was in the era of the first rocket landings on barges, long before the Dragon 2 restored human spaceflight to America or Starlink delivered internet from space. Every day since then, I’ve thought about the next steps to land on the Moon - and to build a city on Mars, data centers in space, the brains behind robots, and beyond. There is no better place to build teams and products from the ground up with planetary scale resources. If you’re looking to work on the hardest problems that lay a foundation for humanity’s future to the Moon, Mars, and beyond - DM me.

@JasonBud @milichab Congratulations, Jason!

I’m proud to be joining SpaceX and xAI with @milichab It has become clear that software is changing fundamentally. More and more, people can shape the tools they use directly, and the ceiling of what can be built keeps rising. What makes xAI special is the scale of its ambition: to build from first principles all the way out to the stars. I’m especially grateful to work on products that expand human agency and freedom. That mission is deeply personal to me. My family came to the United States fleeing communism, and the belief that freedom should be part of the next generation of the internet has driven me every day since Andrew and I started Skiff. Now, we get to work on intelligence, understanding, and freedom on a universal scale.

@weswinder I think traditional IDEs don't quite make sense anymore, but we still need something new that's a really great surface for code review. Reading code is still gonna be a thing for awhile if you don't want stuff to break and be crazy slow.

Everyone on here is talking about Cursor b̵e̵i̵n̵g̵ s̵c̵r̵e̵w̵e̵d̵

most startups are fundamentally unambitious

@zack_overflow They do not know how to bisect the search space at all. They go depth-first and stack multiple hypotheses on top of each other, it's infuriating A possible reason is that a lot of the information from those small tests does not show up in the training data

Agents have gotten really good at debugging but I feel like they by default lack overall guidance on how to do it effectively Productive debugging is usually about splitting the search space by doing little tests to eliminate possibilities I still see Claude do it the ADHD way where it does a little research and then becomes convinced the problem is the first idea it comes up with, instead of validating its hypothesis, and goes down a rabbit hole to fix it It's interesting because this is fixed with a simple system prompt addition e.g. "validate your hypotheses when debugging". The models already can do it, it's just a taste-related thing that needs to be injected into it