Sleeper Agents in Large Language Models - Computerphile @Computerphile
Sleeper Agents in Large Language Models - Computerphile  @Computerphile
Uploaded September 2025 | Updated September 2026, 3 weeks ago
It's an older paper, but it checks out. Rob Miles discusses the problem of 'Sleeper Agents' - where LLMs could have hidden traits we don't know about until it's too late.

Computerphile is supported by Jane Street. Learn more about them (and exciting career opportunities) at: jane-st.co/computerphile

This video was filmed and edited by Sean Riley.

Computerphile is a sister project to Brady Haran's Numberphile. More at bradyharanblog.com
Sleeper Agents in Large Language Models - ComputerphileHorrible, Helpful, http3 Hack (Quic Protocol) - ComputerphileHigh Level Languages & the IBM 360 Series - ComputerphileHow Passkeys Work - ComputerphileOversampling Data (Explained with Audio) - ComputerphileWhy CPU Time ≠ Wall Clock Time! - ComputerphileApple M1 Ultra & NUMA - ComputerphileCPU Kernel Mode - ComputerphileChatGPT Jailbreak - ComputerphileDigital Signal Processing With Audio Data - Computerphile
Computerphile |

Sleeper Agents in Large Language Models - Computerphile

SHARE TO X SHARE TO REDDIT SHARE TO FACEBOOK WALLPAPER