an AI chatbot as a collaborator

I started out as a sceptic in the recent AI revolution because the bots aren't really intelligent in the human sense. But I'm gradually becoming a convert to using them as an amazingly useful tool and collaborator. 

In addition to the usual application for coding, and for answering questions about complex software ("How do you do a conditional Sollidworks mate that depends on the part configuration? How do you stop support generation in Bambulab Studio above a particular height?"), I've started asking Gemini mechanical engineering questions. 

The easy ones involve calculation, like figuring out the required stepper motor torque for lifting an 8-pound shaft with a 2mm pitch leadscrew. The harder ones are higher-level design questions.

I tried it on a problem I was having with the card reader. It works, but it requires precise adjustment of the push rods that act on the microswitches. They have limited acceptable travel: after the switch triggers, the actuator only has less than 1mm of additional travel before it bottoms out and causes something to be stressed. I tried 3D printing flexible tips using TPU filament to put on the ends of the push rods, but it was not a success.

I asked Gemini for a better solution, and it came up with a brilliantly simple one: rotate the switches to be vertical instead of horizontal, and have the push rods slide down against the actuator. Then it doesn't matter if they travel too far.  I did that, and it works great!

Coming attractions

All my prototypes so far have been only 4 digits high, which is good enough for testing but not for useful computing. I've now started experimenting with higher stacks to see if any new problems arise. Here is a test jig for a 14-digit Mill register stack, with only three of the long pinions populated.

The goal is 20-digit stacks, which requires a new framing scheme. Stay tuned.