Super stoked to team up with @swyx and @tylerjdunn on Thursday sep 24 to put on a series of “software factory show and tell” round tables at the @heavybit long horizon dev stack devguild Come show off a small tactical thing that helps you ship better/faster/cleaner 45 minute sessions w/ small break ~12-20 people per session Quick intros, 30s to intro yourself and what you want to show off Organizers pick the first speaker, who presents and then picks the next speaker, and so on - audience driven! 2-5 minutes to demo, 2 minutes for questions No pitches, show us something YOU do internally when building! Have some free ticket codes still, DM if you want one!

NEW: your chance to be on stage at DevGuild. Introducing the Software Factory Show & Tell. Bring a 5-min demo. No pitches, no polish. Judges @swyx, @dexhorthy and @tylerjdunn will award the best on stage. Sept 24, SF →

the best thinking about limit behavior of software development i’ve seen. not surprising from ty! superdark factories already have precedent, as compute-bound researchers prioritize using compute markets (seen at e.g. Jane Street), but could show up in other domains very soon

Imagine the most extreme possible factory: a factory that drives itself, a factory that determines its own objectives and optimizes itself to accomplish them. It is something like a fully automated firm, a company with no people inside, a recursively self-optimizing body that decides what to make, how to make it, and why. How might one build such a thing? What would it mean to steer or govern such a thing? Marek Poliks, Roberto Alonso Trillo, @tylerjdunn, @hscottdouglas & @thejaymo call this factory a superdark factory, a factory whose insides churn too quickly to comprehend, whose logics branch into tangles too dense to reconstruct, and whose standards of performance are too ephemeral to direct. They believe that it is possible to build such a factory now, with existing tools, should one decide to do so. Read The Superdark Factory in Antikythera Journal at Get the EPUB at

this paper has fundamentally changed how i view agentic software engineering. so much of the current discourse is what the next 3-6mo looks like, but Ty and the Disintegrator folks have managed to zoom out and paint a clear thesis as to what the next 3-6 years might look like. my favorite takeaway from the paper was the "neurotic governor" - the idea that the output of a software factory is limited by the "neurotic governor's" need to understand all the outputs

Everyone has been asking me what I’m up to after the @continuedev acquisition The answer: I wrote a paper with Disintegrator titled *The Superdark Factory: Toward the Full Automation of Software* that was published in Antikythera (MIT Press) today