@thebruchez Yeah I was quite surprise based on my simulation, it seems very robust to error and only limited by step motor resolution even with 8 bit math
I think it will be a fun project to try to compare with commercial optical splicer to see how much cost we could reduce
A parable tells us blind men misread an elephant by only touching one part. I’m going to prove it wrong!
This summer, I’m building an open-source ASIC for an auto-aligner. Sweeping just 3 points, my ASIC reads and locks into its optimal point.
Stay tuned!
https://t.co/4vVGLi6diG
Want to see distributed computing explained via Pong?
Inspired by TinyTPU and TinyTapeout workshop at FOSSi, I wrote a paper under a week pairs this demo with a proposed next-gen optical I/O chip architecture & a roadmap to prototype it.
Read it on GitHub: https://t.co/td2oIRfIDW
@Benathon@r3l0z It is meant to be as it is the boundary of two chip!
The left half of the screen is controlled by “left chip” and the right screen is controlled by “right chip”. In the real product, it will be two separate monitor connected to different chip!
Hey @PalmerLuckey want to know where the real engineers in North America are?
Waterloo, Canada.
In the @akatoshouse community, there’s a guy who built a transformers model from scratch just by reading the paper. It took over a year and he literally rediscovered the gradient vanishing problem from first principles, amongst other things
There’s another guy, a chemical engineer with zero background in hardware or chip design, who learned to code then meticulously researched and wrote a paper on building a next-gen TSMC from scratch (releasing Tuesday)
And a 3rd guy who is designing and engineering autonomous construction fleets from our basement
People in this city understand how to make real things. Come take a look someday 🫡