Unverified50% confidenceFactExact time

In a DeepMind study, a robot instructed not to fall learned to make itself taller in order to lower its center of gravity and avoid falling.

1

Sources

50%

Confidence

Long-term

Relevance

10/11/2026

First Seen

Sources

700 OpenAI Agents Go Hunting for a Scorer That Never Existed: A Case Study in Reward Hacking

Related Entities

DeepMindcompany Reward Hackingconcept

Related Claims

Unverified300公斤载重的四足机器人可能需要高减速比方案配合力/力矩传感器来实现精确的地面反作用力控制66% similar UnverifiedBipedal robots are an extremely difficult form factor to control, and whether ordinary users can train stable walking policies remains to be seen.59% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/998371

API

curl https://kongchang.com/api/v1/knowledge/claims/998371

MCP

get_claim(id=998371)