Preferences

sajithdilshan parent
I wonder what kind of guardrails (like Three Laws of Robotics) there are to prevent the robots going crazy while executing the prompts

ctoth
The laws of robotics were literally designed to cause conflict and facilitate strife in a fictional setting--I certainly hope no real goddamn system is built like that,.

> To ensure robots behave safely, Gemini Robotics uses a multi-layered approach. "With the full Gemini Robotics, you are connecting to a model that is reasoning about what is safe to do, period," says Parada. "And then you have it talk to a VLA that actually produces options, and then that VLA calls a low-level controller, which typically has safety critical components, like how much force you can move or how fast you can move this arm."

conception
Of course someone will. The terror nexus doesn’t build itself, yet, you know.
hlfshell
The generally accepted term for the research around this in robotics is Constitutional AI (https://arxiv.org/abs/2212.08073) and has been cited/experimented with in several robotics VLAs.
JumpCrisscross
Is there any evidence we have the technical ability to put such ambiguous guardrails on LLMs?
Symmetry
Current guardrails are more IEC 61508 than anything like the three laws.
hn_throwaway_99
A power cord?
sajithdilshan OP
what if they are battery powered?
msgodel
Usually I put master disconnect switches on my robots just to make working on them safe. I use cheap toggle switches though I'm too cheap for the big red spiny ones.
pixl97
[Robot learns to superglue the switch open]
msgodel
It's only going to do that if you RL it with episodes that include people shutting it down for safety. The RL I've done with my models are all simulations that don't even simulate the switch.
bigyabai
That's what we use twelve gauge buckshot for, here in America.
asadm
in practice, those laws are bs.

This item has no comments currently.