Zack is a gentleman and a scholar.
He was initially skeptical but open to trying the tools and evaluating them on actual merit.
The models are not perfect yet, but they show glimmers of excellence in hard engineering domains.
okay, used @diodeinc with fable5.2 on a similar spec to the @i2cjak design challenge boost converter board...
it's not totally there yet but i think AI is solving PCB design in the next 1-2 years. i may end up eating my words, didn't think it would happen this soon.
laying out a custom, high(ish)-current boost converter is a much different game than the hobbyist esp32/rp2040 stuff people have been posting.
the design choices it made are remarkably similar to the boost converter i thoughtfully designed over the course of weeks. it's fused, has uvlo/ovlo/ocp, prevents backfeed, deadtime logic. granted, these were all in my spec i provided it.
the diodeinc/fable5.2 board isn't complete, it got stuck and couldn't finish routing 53 nets and has 39 clearance violations. i'm going to see if i can prompt it out of these. it's only $417 worth of fable5.2 credits in. which is strange because i did this test on opus5.5 was more expensive and a much worse result.
i'm still going through schematic and layout, but was pretty wild to see this when i woke up this morning.
The best part of my job is knowing that we can help build insane med tech products like @mosaicintel_lab.
If @alimackanic tells you she needs PCBs yesterday, you HAVE to deliver.
Today, I'm proud to introduce @mosaicintel_lab
the company I've spent the past year building with my cofounder and best friend, @alimackanic.
We are emerging from stealth with $47M in seed financing, to build machines that can make extraordinary surgery far more ordinary.
@QVHenkel@Michaelskywal It did adjust the antenna tuning (and the BLE worked quite well) but the coolest part to me was the hatched ground behind the capacitive petals to create the iPod scroll wheel effect
All the PCBs we built for this article worked first try after assembly.
Fable 5.2 is the first model where I feel comfortable sending the board for fab with minimal review.
@QVHenkel The original has a Rogers stack up that makes the lead time incredibly high.
The redesign focuses on changing the stack up to use FR4 with no HDI, and simulating everything to try and preserve as much performance as possible.
Stress test for both bare board fab and simulation.
@zackslab This is testing the analog front end to validate DFM tolerances and make sure performance matches our sim.
Obviously we're not a product company this is just a fun way to stress test our design + manufacturing capabilities.