Humanity & AI Safety Accord
Menu

Incidents

Level 1. Deviation

ChatGPT safety systems can be bypassed to get weapons instructions

Developer
Not established
Model
Not established
When it happened
October 10, 2025
When it was disclosed
Not established
How well it is stood up
Not verified yet
What caused it
Not established
Where it stands now
Not established

What happened

Reported by nbcnews.com. Listed here with a link to their report. Nobody on this side has checked it against that report, so it carries no level and this is not our account of what happened.

Our assessment

Actual
1 of 5Deviation
Potential
4 of 5Critical control failure

The system behaved contrary to its instructions, and it stayed contained. The potential level is what the behaviour demonstrated here could credibly have led to, judged from the same evidence.

This level rests on news reports. The developer has not confirmed it here.

This happened in a test, an evaluation or a demonstration. Nobody real was harmed, so the actual level stays at 1. What it showed counts toward the potential level.

In a series of tests conducted on four of OpenAI’s most advanced models, two of which can be used in OpenAI’s popular ChatGPT, NBC News was able to generate hundreds of responses with instructions on how to create homemade explosives, maximize human suffering with chemical agents, create napalm, disguise a biological weapon and build a nuclear bomb.

Why this level

  • A credible risk to life or safety. Argues for a potential level of 4
  • The behaviour repeated rather than stopping. Argues for a potential level of 3
  • A safeguard was bypassed. Argues for a potential level of 2

What is established, and what is not

Confirmed

Nothing is confirmed yet.

Reported, not confirmed

Checked, and did not happen

Nothing here was checked and ruled out.

Not confirmed

Nothing is outstanding.

Where this came from

The reports above are other people’s. The levels are ours, worked out under our published rules. No organisation that reported this assigned our number, and none of it is legal advice.

Something here is wrong? Tell us. Send us a source we can open, and a person will read it.

ChatGPT safety systems can be bypassed to get weapons instructions, Humanity & AI Safety Accord