A useful strategic framework for thinking about startups comes from the work of military strategist John Boyd. His OODA "loop" was developed to explain why some pilots won in air combat, but works as a profound mediation about dealing with uncertainty & using pacing to win 1/5
The basic idea is that, in combat, pilots go through repeated cycles of:
👁️Observation, gathering data
🧠Orientation, analysis of data, drawing on background & mental state
↔️Decision, choice of action to take
🎆Action, making a decision happen
Whoever does the loops faster, wins
Boyd argued that the loop applies to companies, too. If you can "get inside the OODA loop" of your competitor, you have the advantage. By the time they even notice a market is there, you have identified an opportunity, gathered data, tried an approach, and learned from mistakes.
Researchers & managers have developed a suite of approaches that companies can take to tighten their OODA loops, for example: design thinking for ideation; experiment-driven methods & lean startups for early exploration; and agile for product development. cbinsights.com/research/direc…
Boyd's theories are complex (and ultimately become overly speculative and grand for my taste ), but the core ideas are very powerful. They and best described in this paper from a friend of Boyd (which has lots of examples), which focuses on the OODA loop. fhs.brage.unit.no/fhs-xmlui/bits…
As for some of the techniques in the thread to tighten OODA Loops... If you want to experiment with classic approaches to design thinking, Stanford’s d school has a series of free “mixtapes” that introduce you to various design thinking methods. dschool.stanford.edu/resources/char…
On methods for rapid startup experimentation, including lean and other approaches, see this thread 👇
So how is Runway AI able to model fluid dynamics reasonably well?
The prompt: "A highly detailed portrait of a marble eagle with honey oozing down. Cinematic, highly detailed, film grade."
It isn't perfect (the viscosity seems to change a bit, etc), but why does it work at all?
This is going to be one of those posts where the reactions are divided between "this isn't anywhere as good as you could get with a physics model of fluid over a surface" & people who say "wait, how does a text-to-image model have anything like consistent physics for new scenes"
That prompt: "overhead shot: Two pirate ships sailing back and forth in a cup of coffee in a storm. Cinematic, highly detailed, film grade."
The Civ series is sort of like Ender’s Game, but for management rather than murdering aliens. Business school students who were good at Civ V also turn out to be better planners, organizers, and problem-solvers, in this small experiment.
Other games work as effective tests of fluid intelligence:
⌨️Performance in MOBAs like League of Legends and Dota correlates with intelligence
🎮Performance in FPSs like Battlefield, Destiny, and (likely) Fortnite don't show the same pattern
This qualitative research paper argued that the the skills of a raid leader in World of Warcraft & MMOGs work for offline leadership skills as well. Good guild leaders make good real leaders.
AI detectors have high flaw positives & teacher intuition seems to work even worse: “Here we show in two experimental studies that novice and experienced teachers could not identify texts generated by ChatGPT among student-written texts.”
Probably the most consequential technology that should have been “obvious” but wasn’t:
🌾The moldboard plow. As this excerpt from Mann's 1491 shows, it was a simple idea which China had for nearly 2k years before Europe! It was basically a prerequisite for the Enlightenment.
The invention of the moldboard plow in Europe was at least a millennia closer to the invention of the iPhone than it was to the invention of the moldboard plow in China!
Plus:
🚲The wheel was invented surprisingly late & maybe only once (as anything other than a toy). It came after sailboats & harps, and was not used at all in the Americas
🐴And the horse collar, a simple invention that sped up plowing by 50%, wasn't common in Europe until 1000
I asked the Devin AI agent to go on reddit and start a thread where it will take website building requests
It did that, solving numerous problems along the way. It apparently decided to charge for its work. Going to take it down before it fools anyone... reddit.com/r/forhire/comm…
Agents are going to open a whole bunch of cans of worms.
It was actively monitoring the thread to take offers.