Building robots since 1995; building robots with Codex since 2024 OpenAI Codex Ambassador - Northwest Arkansas
USA
Joined January 2025
- Tweets2.7K
- Following953
- Followers5.5K
- Likes13.6K
Pinned Tweet
gpt-6 astra is also handling all of the RL training/motion policy for the robot it has designed 😎
current progress with some basic obstacles/drops; i gave it a $25 budget for GPU rentals on vast.ai and it currently has ~$18 remaining
👀 @OpenAIDevs
ok ngl was initially disappointed that a new terra model was dropped rather than a frontier model
but...i decided to give it a go as my '/side' model and it's pretty good for that
very very fast on '/fast' mode which removes the frustration when needing to correct/guide/steer
quiet on X ≠ lack of progress; quite the opposite actually
i've somehow managed to completely burn weekly limits between the daily resets on the legacy 20x plan(s)
ask me anything lol
can't wait to upgrade my current robot controller (ipad mini 7) to this one 😍
New iPad mini was just released!
Looks like new Acoustic Display, OLED + nano texture, A20 Pro, and IP67 water resistance
Seems like decent upgrades apple.com/newsroom/2026/10/a…
rolie making stepping progress
seems like astra is spending a lot of time on the controller;
need to audit the whole process and likely guide it's sequencing
crazy that clip was only a year ago 🤯
now we've got codex designing a robot end-to-end; the engineering->cad design->motion policy
i'd say it's doing pretty well; here is a clip of the current motion policy
moving pretty good for a 20kg clanker right??
codex being better at predicting my next prompt than i am.....really shows me where the bottleneck lives
at this point i am consistently burning thru the codex weekly limit on 2x $200 plans
per day
anyone else or am i the oddball
hardware ppl: i need a STEVAL-VL53L9 board ASAP!
willing to pay double retail if anyone has an extra that they would sell
will be going on the chin of this robot
pls share with anyone that may be able to help!
ummmm idk abt this one
at this point, if your frontier 'sota' model can't do 3d, and 3d is the future (cad, ar/vr, robotics)....then maybe your sights aren't aimed in the right direction
The smartest code model in the world would not be good at 3d stuff unless it was trained specifically for it.
A lot of the labs recently got a big pile of 3d training data and an RL environment to improve 3d skills.
Take a look at the jump in 3d from Fable 5.1 to Opus 5.5. It's at least 4x better at 3d despite being a 5% better model at best.
Clearly Meta didn't go hard on 3d for this release. Doesn't mean the model is bad.
3dmaxxing is a different type of benchmaxxing, don't overthink it.
I'll take some fault here by sharing all the Fishslop demos. The 3d stuff is fun and cool as hell, but it's not a good representation of a model's real world code capability.
just wait until you experience the amnt of 'little details' on a robot build 😅
astra isn't perfect and occasionally does some really dumb stuff (like routes a usb cable thru a bracket or tries to use glass fuses 😂)
but the robot for @OpenAIDevs is coming along nicely
at this point i don't even need to use fusion anymore for the CAD stuff 😅
last night i told astra to make our own CAD package that would allow rendering of our accent lighting and allow for smooth/quick content creation;
this is what i woke up to this morning
also there's a progress update buried in there on the robot that astra is designing for the @OpenAIDevs codex physical hardware build 😎
watching astra in codex jump into my chrome browser to lookup mfg dims on elec connectors; then modeling the parts and dropping into the assembly.....is amazing.
i would do it the exact same way, except i'd get distracted/lost in chrome for 30min then forget what i was doing
why do i seem to be having such great 'luck' using astra for design/engineering/cad?
have realized it's not really luck at all; it's systems/divergent thinking & design/mfg experience
first lab that decides to hire me to solve this for the normies will win the market 😎
the little clip i posted above is the result of ~4 billion tokens since yesterday; burned 2x codex resets plus all of my credits
was it worth it? for this @OpenAIDevs robotics project, yes.
i couldn't come close to the same amnt of progress in same timeframe