Pinned Tweet
We’re growing our team fast in San Francisco.
You’ll work directly with me and our customers across aerospace, robotics, and defense, helping turn real shop-floor problems into production software and models.
We’re hiring:
Software Intern (full stack)
ML Intern
Software engineer (0–5 YOE)
Frontend or Full-Stack Engineer (2–10 YOE)
DM me with a project you’ve worked on or send your resume + a short intro to [email protected]
Nick Khormaei retweeted
Great day to build
@nkhormaei is locked in 👀
More and more vertical integration, love to see it.
Now Waymos there can also take people from different buildings too🤝
6
242
Nick Khormaei retweeted
Whereas April 2025, I was pulling teeth to explain to VCs what CNC is and no manufacturing is not f***ing “already automated”
Today I am pulling teeth to explain to VCs that THIS CAN ONLY BE SOLVED ON THE DATA LAYER.
Unless you are famous, it’s not a good thing to be ahead of times. Imma go meditate.
Nick Khormaei retweeted
One of the recurring issues that consumer AI breakthroughs have caused is a sort of mass Dunning Kruger effect, a bulk reductionism of massively complex value chains. Investors that have never shipped a physical thing believe G code is a solved problem because they saw someone on here ask Opus to help them make a 6061 wall mount for their bike with three features on a desktop mini mill.
Newsflash: the world’s machining companies will not bet their livelihoods on anything that works less often than a new hire. If it crashes a spindle once, it’s gone. If it causes a single missed deadline, fuhgetuhboutit.
Finding a way to supercharge how they work today, enabling faster, better, more profitable shop floors, that will always be a winning bet. If only someone’s was working on it… @nmitra2k @nkhormaei
Whereas April 2025, I was pulling teeth to explain to VCs what CNC is and no manufacturing is not f***ing “already automated”
Today I am pulling teeth to explain to VCs that THIS CAN ONLY BE SOLVED ON THE DATA LAYER.
Unless you are famous, it’s not a good thing to be ahead of times. Imma go meditate.
I’m surprised the comment section isn’t filled with ppl calling out to never refer to sf as “San Fran”
In San Fran this week, a few observations:
- Per head alcohol spend at the mixer 40% below NYC
- Never seen traffic in the city this gnarly. 45 minute Uber from SOMA to Presidio
- Real energy around AI use cases for public equity investors. This vertical is becoming real, quickly. Opus 5.5 threshold moment and people mentally preparing for Opus 6,7,8 and eventual open weight parity. Most common conversation is how you build something to stay out of the Claude path (there are lots of ideas that I believe do this)
- Consensus that public equity investing is one of the hardest AI use cases to crack “if AI comes for us, imagine what has happened to accountants”
- Still no one reliably arguing AI has bent the curve of alpha (but many now hopeful over next 6-12 months; particularly on short books). But broad consensus on the dramatic productivity uplift from Claude.
- Fun conversations on how awful Claude is as a stock picker (despite emerging super human capabilities in the junior analyst workflow stack), and fun ideas on how to fix that
- Fun conversations on the trading alpha emerging from fading “dumb Claude”
- My priors shifted on the inability to reliably backtest a Digital Investor. Which has exciting implications. Post training, training data and eval dominating conversations.
- The median AI conversation with investors in NYC is still “how do i set up my Skills”. The median AI conversation in SF is “how many worlds do I need to simulate to calibrate the 3 year IRR forward for a stock”.
- AI smacks you in the face wherever you go. Billboards, overheard conversations at coffee shops.
- This is so fun. Forgot I do this for work and feels like exciting play. Have to come back here regularly.
3
7
345
#2 and #5 hit home. Everyday I am meeting a new machinist that can work magic from cad to cam. At the same time, I hear from every owner that this is the bottleneck to scaling and getting more square footage.
More to come soon, with neuramill.co
AI is on track to become a superhuman hardware designer, but design is only the beginning. The interface between bits and atoms is lossy, and turning designs into real hardware gets harder at every level:
1. Sourcing off-the-shelf parts that work together (a 2006 Falcon 1 engine test was delayed by one capacitor, in stock 6,000 miles away)
2. Custom parts, where a master machinist translates CAD into machine instructions
3. Assemblies, where every part can meet its drawing and still not fit
4. Outside vendors (even SpaceX has 591 employees with supply chain titles)
5. Doing all of it at a scale of 1,000,000
"Superhuman AI might be great at pure design, meaning at defining the platonically ideal part for a particular job, but struggle with 'design for manufacturing,' or finding a point design that meets the requirements while remaining easy to build/procure and inexpensive."
Full piece from a16z's Christian Keil on what it takes to turn AI-designed hardware into the real thing: a16z.news/p/superhuman-hardw…



























