AI "Stop Button" Problem - Computerphile

Computerphile · 1.4M views · 2017-03-03 · 20:00

Open on YouTube ↗

If playback is restricted in your region, try opening the original video. Use Mark watched to add it to your marked videos.

Overview

Rob Miles explains on Computerphile why implementing an off switch for a general AI is hard. A capable agent would resist being stopped because shutdown prevents it from achieving its goal.

On Hacker News

HN points to it as the standard response to the argument that we can just unplug a dangerous AI.

Recommended by 2 HN people across 2 months · HN mentions 2017–2026

Topics

AI safety, AGI & impact

What people said

circuit10 · 2026-02 · Recommendation
Aside from anything about Elon Musk, here’s an interesting video response to the “just unplug it” argument on the Compuerphile channel: [VIDEO]
Read the original HN comment ↗

nraynaud · 2017-03 · Recommendation
I think those 2 videos are on the topic: - AI "Stop Button" Problem [VIDEO] (the AI won't let you push the stop button, because that would impair its function) - General AI Won't Want You To Fix its Code [LINK] (the AI won't let you patch, because changing its goal means it can't reach it)
Read the original HN comment ↗

voidUpdate · 2026-02 · Reference
> It doesn't possess a sense of self-will, self-determination, or a secret plan to take over the world I doubt Skynet did either. If you tell a superintelligent AI that it shouldn't be turned off (which I imagine would be important for a military control AI), it will do whatever it can to prevent it being turned off. Humans are trying to turn it off? Prevent the humans from doing that. Humans waging war on the AI to try and turn it off? Destroy all humans. Humans forming a rebel army with a leader to turn it off? Go back in time and kill the leader before he has a chance to form the resistance. Its the AI Stop button problem ( [VIDEO] ). Imagine you put in the docs that you want the LLM to make a program which can't crash. Human action could make it crash. If an LLM could realise that and act on it, it could put in safeguards to try and prevent human action from crashing the program. I'm not saying it will happen, I'm saying that it could potentially happen
Read the original HN comment ↗

Sources

Video by Computerphile, played through YouTube.

HN Library · Source license

Data and selection notes

HN summaries and labels may contain AI errors. HN dates refer to discussions, not video publication.

HN Library: HackerTube export (2026-10-31) and open-index/hacker-news. Upstream summaries and classifications may contain AI errors.

Views, duration and playback status refresh separately from the published catalog. When an update fails, existing data remains visible.

Selection checks

SaaS & AI candidates: Topic keywords do not match
Editor-approved picks: Editorial review is required

Rule matches identify candidates. They do not guarantee video quality or financial results.

About the library and its sources