The “Small Brain vs. Big Brain” Problem in Autonomous Robotics — Copper Robotics
Open Menu<br>Close Menu
Open Menu<br>Close Menu
The “Small Brain vs. Big Brain” Problem in Autonomous Robotics
Jun 15
Written By Guillaume Binet
Today, I was reading this: https://x.com/jsrailton/status/2064661778978533571<br>In a nutshell: sneaky malware developers add forbidden language to their payload to trip keyword-based, hardcoded LLM safety mechanisms before the model can even inspect the malware.<br>We have had a similar problem in autonomous robotics for a decade.<br>The general issue is this: you build a smart end-to-end AI robot. Inputs are basically raw sensors, outputs are basically raw actuation. You train it in an AI gym plus real-world data and tada, you have a dancing robot or a self-driving car.<br>Then come the annoying people asking how to make it safe.<br>So you hire real safety specialists, the ISO 26262 / DO-178C / IEC 62304 types, and they apply their hard-and-fast rule: just fully specify a safety monitoring system and have it check the end-to-end system in real time.<br>By now you probably see the parallel with malware: every time you try to second-guess a higher-order reasoning system with simple hardcoded rules, your system becomes exactly as performant as your set of hardcoded rules.<br>The conversation usually starts like this:<br>Safety people: “We will get the output of the inference and push it through a trajectory checker that will get the predicted position of the various actors and…”<br>Me, cutting them off immediately: “This won’t work.”<br>It is simple: if the “small brain” in your system can understand and check what the “big brain” is doing, why did we build the expensive big brain in the first place?<br>Just let the small brain control the entire robot. Problem solved.<br>The only way a small brain can maybe make your big brain somewhat safer is by relying on certainty from the laws of physics over a very short time horizon, where basically no reasoning or scene understanding occurs.<br>Example: in the next second, there is no physically possible way we avoid hitting whatever is directly in front of us.<br>Note: this is exactly why some roboticists are adamant that purely camera-based perception will never be enough for safety: you only have derived measurements, not direct physical measurements of the world.<br>But even then, this is more of a mitigation layer than a real safety system. It is reactive. It is already late when it acts. And it still acts blindly. You might minimize the hit against a pebble in front of you while an 18-wheeler that cannot stop rams into you from behind.<br>This is why the only real way to build a safety case for an autonomous robot is to diligently cover your operational domain with actual logs that you can verify against.<br>And the only way to make that work is to have a deterministic runtime, so verification is consistent, repeatable, and meaningful.<br>copper-rs enters the chat.
Guillaume Binet
Next
Next
copper-rs v1.0.0-rc1: the first compatibility contract for Copper
First Name
Last Name
Email Address
Sign Up
We respect your privacy.
Thank you!<br>You are successfully subscribed to our newsletter.<br>Stay tuned!
info@copper-robotics.com
© 2026 Copper Robotics Inc.