2027. every hour, another person generates a magnum opus 2.5 hour long movie for a couple grand and shills a shitcoin around it. the outputs are technically impressive, on par with pre-2023 $500m feature films, but the narratives are vast and Claudeatouille’d. nobody has ever said “no” in the process of making many of these things and it shows. but what if there are actual geniuses constrained by financial limits making masterpieces in it all? how do you determine which movies are great, and which ones are the works of hidden geniuses? it’s become obvious that you can hack AI media reviewers by putting certain things in there that AI graders really like — quiet seams doing real slow work, “truth-seeking” based edgy iconography, ledgers. You can make a Claude movie to appease Claude film critics but what if you don’t want to watch a 2 hour Wes Anderson on Zoloft pastiche, or a schizophrenic assault on the senses? in a dilapidated mansion in the rustbelt, a gaggle of nonbinary ex-humanities majors have converted their group house into an FRO. they watch. all they do is watch. every single feature length slop masterpiece. they take notes on paper. they discuss. they summon the spirits of Maltin and Ebert. they review. The mythical human grader. they write a physical Sunday newspaper full of reviews, printed in the husk of the Pittsburgh Post Gazette, on actual newsprint. they chose to make it purple. coastal elites subscribe because they want to know what’s worth watching, and because carrying that physical purple newspaper is a signal, a tasteslop fashion accessory to stack on their Claude-prescribed barrel jeans, Carhartt coat, Margiela Tabis.
Fun timing: I'm now leading engineering for Sidekick as well. Hiring EMs for both. Come help millions of entrepreneurs make it real.
Sidekick: https://t.co/4HOlVk1j5E
Mobile: https://t.co/oUcMoT0Vx5
Doing another run of “Unraveling the Algorithm” this month, a hands-on workshop about the shared history of weaving and computing.
Nov 25th 6pm at New Stadium in Toronto, registration details below!
Ty to our friends at @newsystems_ 🤍
implicit state machine jihad has been declared internally
how many did you kill this weekend?
we've put down 24 implicit state machines dogs, and gutted 3 more
all hail xstate
Sometimes it's better to focus less on BEING a thing and focus more on MAKING things
I've known a lot of people who called themselves writers and never actually got around to releasing a book
Let go of the identity. Focus on the product.
Message threads are now in public beta on the Messages API.
The API caches your conversation on the server between turns, so instead of resending the full conversation, you send only new messages and the previous message ID, and Claude starts responding sooner.
IaC isn't dying, it's becoming more essential. Non-deterministic layers add new volatility to the stack, but they don't break the core principles. For example, it's becoming more obvious that we want some layers to be truly reproducible.
Vibecoding with no understanding and learning just in time is the default for all major codebases
School brainwashed you into thinking you need to learn something first completely before doing it. No, you just do it and learn along the way. If you get stuck learn more.
Everything is figureoutable.
I like the term code archaeology but I prefer exploring the code labyrinth. You never know what you will find
I've been thinking about this a bunch lately. Codebases have become organic, perhaps they always were, and we require new abstractions to do excellent engineering.
Cybernetics is back. What's old is new again, and this is the current best way to think about it. For all their flaws, Anthropic has the *exact* right idea with "SuperFans". I mean, I'm sort of in awe of how good that particular blog post was. There's this commitment to excellence that I greatly admire, and a level of AGI-pilled reasoning that meets the moment.
In my opinion, you should work with models you trust and then give them the autonomy to own part of your codebase. This doesn't mean they don't get audited, or manually checked, or interviewed - it just means that each component gets a type of guy who is obsessed with that component.
If you think about this from a higher level of abstraction, what you're really doing is enabling *zones of dynamic attention* where the models are using their fluid intelligence to design a component and then justify that component in the context of all the others. If a new one gets built that may cause issues, that model works with the model for the other component to ensure mutual compatibility. It's almost like the components themselves have come to life and are trying to figure out how best they might fit together.
The old ways of engineering are over. Codebases that are built like this will be far more competitive almost inevitably as the skill of the model surpasses that of the average programmer and sheer parallelization wins the day. Obsession over PRs, dedication to reading every line, these are vestigial neuroses that must be abandoned if we are to succeed well into the future.
Operational excellence without constant human oversight is possible with good enough models and clever enough scaffolds. The hardest part is almost always going to be turning it on and managing the first few problems. These systems will probably never be perfect, but they are the path forward.
we will need to rebuild and rewrite much of software to adapt to a new, faster pace.
code used to arrive one drop at a time. soon, if not already, code will be written as if it were a continuous stream, like a violent river twisting and turning as it pleases.
this is not a new thing: big tech cos have had to deal with this with the enormous scale of their engineering teams. but now ai has brought an incredibly elastic and capable workforce wielded by every engineer. this is your problem now, and the only way to adapt is to evolve your systems so agents - even and especially the ones with little context about the right way of doing things - can thrive. make the easy thing the right thing.
your codebase is becoming organic architecture. agent contributions grow around the constraints and guardrails you’ve designed. good software engineering matters even more now! and no, the continuous stream of code is not something you have to watch helplessly. be more ambitious and design systems, frameworks, and languages to control the chaos.
the time for mourning coding is long over
usually kind of blithe about old actors dying but i kind of regard captain picard as the closest humanity has ever come to a portrayal of The Ideal Person
Software is not disappearing, we are producing more software than ever. What is changing is the premise. The modern foundations of software engineering has been built around encapsulation. Today, it's getting hard and sometimes impossible to defend the layering.