Uploaded June 2026 | Updated November 2026, 1 day ago
Further reading
Thumbnail image credit: Figure AI
text used in video and more:
AI Model Misbehavior in 2026: Scheming, Reward Hacking, and What Comes Next
hatchworks.com/blog/gen-ai/ai-model-misbehavior
Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-Based Decision-Making Systems
openreview.net/forum?id=S1Bv3068Xt
BadRobot: Jailbreaking Embodied LLM Agents in the Physical World
arxiv.org/html/2407.20242v5
AI Model Misbehavior in 2026: Scheming, Reward Hacking, and What Comes Next
arxiv.org/html/2407.20242v5
Jailbreaking LLM-Controlled Robots
arxiv.org/abs/2410.13691
LLM-Driven Robots Risk Enacting Discrimination, Violence, and Unlawful Actions
arxiv.org/html/2406.08824v1
Inducing Bystander Interventions During Robot Abuse
with Social Mechanisms
ieeexplore.ieee.org/document/9473717
You might get offered promo codes if one of these delivery robots runs into you
theverge.com/2024/9/19/24249034/starship-technologies-delivery-robot-accident-promo-codes
Training Agents to Self-Report Misbehavior
arxiv.org/html/2602.22303v1
Natural emergent misalignment from reward hacking in production RL
arxiv.org/html/2511.18397v1
Long-horizon Embodied Planning with Implicit Logical Inference and Hallucination Mitigation
arxiv.org/html/2409.15658v2
Deception Abilities Emerged in Large Language Models
arxiv.org/abs/2307.16513
Robot in the mirror: toward an embodied computational model of mirror self-recognition
arxiv.org/abs/2011.04485
Misleading text in the physical world can hijack AI-enabled robots, cybersecurity study shows
https://news.ucsc.edu/2026/01/misleading-text-can-hijack-ai-enabled-robots/
#science
#explained #ai #artificialintelligence #robots #psychology #sentience
#consciousness
Further reading
Thumbnail image credit: Figure AI
text used in video and more:
AI Model Misbehavior in 2026: Scheming, Reward Hacking, and What Comes Next
hatchworks.com/blog/gen-ai/ai-model-misbehavior
Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-Based Decision-Making Systems
openreview.net/forum?id=S1Bv3068Xt
BadRobot: Jailbreaking Embodied LLM Agents in the Physical World
arxiv.org/html/2407.20242v5
AI Model Misbehavior in 2026: Scheming, Reward Hacking, and What Comes Next
arxiv.org/html/2407.20242v5
Jailbreaking LLM-Controlled Robots
arxiv.org/abs/2410.13691
LLM-Driven Robots Risk Enacting Discrimination, Violence, and Unlawful Actions
arxiv.org/html/2406.08824v1
Inducing Bystander Interventions During Robot Abuse
with Social Mechanisms
ieeexplore.ieee.org/document/9473717
You might get offered promo codes if one of these delivery robots runs into you
theverge.com/2024/9/19/24249034/starship-technologies-delivery-robot-accident-promo-codes
Training Agents to Self-Report Misbehavior
arxiv.org/html/2602.22303v1
Natural emergent misalignment from reward hacking in production RL
arxiv.org/html/2511.18397v1
Long-horizon Embodied Planning with Implicit Logical Inference and Hallucination Mitigation
arxiv.org/html/2409.15658v2
Deception Abilities Emerged in Large Language Models
arxiv.org/abs/2307.16513
Robot in the mirror: toward an embodied computational model of mirror self-recognition
arxiv.org/abs/2011.04485
Misleading text in the physical world can hijack AI-enabled robots, cybersecurity study shows
https://news.ucsc.edu/2026/01/misleading-text-can-hijack-ai-enabled-robots/
#science
#explained #ai #artificialintelligence #robots #psychology #sentience
#consciousness






![AI Misbehavior Is No Longer Confined to the Lab
Further Reading
Thumbail original image used credit: Adobe Stock Image.
Graph from: Scheming in the wild: detecting real-world AI scheming incidents with open-source intelligence
Shutdown resistance in reasoning models
https://palisaderesearch.org/blog/shutdown-resistance
Natural emergent misalignment from reward hacking in production RL
https://arxiv.org/html/2511.18397v1
Scheming in the wild: detecting real-world AI scheming incidents with open-source intelligence
https://arxiv.org/abs/2604.09104
[CRITICAL Security Issue/Bug] Plan mode restrictions bypassed when spawning sub-agents #6527
https://github.com/anomalyco/opencode/issues/6527
#explained
#science #artificialintelligence #tech #misalignment AI Misbehavior Is No Longer Confined to the Lab](https://i.ytimg.com/vi/BHnLepS5dyo/mqdefault.jpg)



