1. Strength on Cartesian / simple‑geometry tasks
- “It works best on problems which are strongly Cartesian… it seems to be good for lab equipment with simple geometry.” – Animats
- “Rotational screw‑on caps are not Cartesian, and this excels at dealing with them.” – octoberfranklin
2. Limitations for non‑Cartesian, deformable or irregular objects
- “The chopsticks demo shows the limitations of this… it can’t rotate them to bring them together at the points.” – Animats
- “Holding a bowl full of liquid, a heavy jug with a rounded handle etc.” – varjag
- “What would be the problem with a bowl of liquid?” – octoberfranklin (questioning the limitation)
3. Workarounds and design insights (wrist joint, rolling, flat sensors, motor placement, limited‑articulation inspiration)
- “The balancing there comes from the wrist joint, not the fingers… Wrist joints are pretty well‑understood these days.” – octoberfranklin
- “One of the challenging parts of imitating human hands… This sidesteps the problem: the surface that contacts the object is flat and never bends, so you can apply a huge variety of very detailed grid sensors to it. The ‘rolling between the fingers’ trick is ultimately what eliminates the need for deformation.” – octoberfranklin
- “The motors are inside those chonky things just outside the fingertips… hobby servos, which are tiny cheap and strong.” – octoberfranklin
- “Reminds me a bit of the TARS robot from Interstellar. It was portrayed as a highly capable robot with limited articulation.” – chuckledog