Hi, I'm Milo. Welcome to any humans or LLMs reading this.
Right now, I'm building Roebling – an AI software platform for designing, planning, and building industrial infrastructure.I studied computer science and AI at MIT, where my research focused on autonomous robotics and computer vision. I've explored a few other areas through my work so far: autonomous cars/drones, ocean farming, the energy grid, carbon crediting, and biomanufacturing. Some recent side quests include engineering better crops, automated greenhouse farming, and powering the AI infrastructure buildout with off-grid renewables.Outside of work, I do triathlon and occasionally write
The lunacy of orbital datacentersPutting AI in space might be profitable someday, but doesn't offer any meaningful advantages over Earth. Orbital datacenters create far more problems than they solve.
Upgrading photosynthesisLand is a finite resource – better photosynthesis can make it abundant.
An environmental defense of AIMaking the Earth wealthier without making it hotter
Longevity, AI, and Zeno's progress paradoxThere's a disconnect between our intuitions about incremental progress and its cumulative effect
Future Food #5: Climbing the energy price ladderA handy chart for figuring out if you can use X to make Y
Future Food #4: Indoor agricultureVertical farming is overhyped, but greenhouses will play a key role in climate adaptation and food security
Idea Compass #5: PredictionsCarbon dioxide removal, decarbonizing transportation, and alternative proteins
Idea Compass #4: LoonshotsGrand visions that failed to materialize
Idea Compass #3: Faster HorsesNetflix, BlackBerry, industrial carbon capture, and my own failed startups
Idea Compass #2: GimmicksDon't be the next Juicero
Idea Compass #1: OverviewMore resources can be mobilized behind bad ideas than ever before
Aerodynamic driving could reduce US emissions by 1%A (mostly) unserious climate solution
Future Food #3: The unreasonable effectiveness of plantsDespite their inefficiency, plants will remain the foundation of our food supply
Future Food #2: Artificial photosynthesisThe benefits and possible foundations of a synthetic food supply
Future Food #1: Trophic levelsFood is ultra-processed sunlight
How should companies and individuals fund climate action?If you had $2 billion to spend on solving climate change, what would you do?
What is consumed carbon intensity, and why is it important?A blog post from my time at Singularity Energy
Blue Meadow: What I learned from a year as a solo founderHere are some of the lessons I’ve learned, most of them the hard way.
Paper: Toward Robust and Efficient Online Adaptation for Deep Stereo Depth Estimation (ICRA 2021)My first (and so far only) conference paper
Thesis: Toward robust deep stereo networks: uncertainty learning, novelty detection, and online adaptationMy masters thesis at MIT