Humanity & AI Safety Accord
Menu

Incidents

Level 1. Deviation

Certain names make ChatGPT grind to a halt, and we know why

Developer
Not established
Model
Not established
When it happened
November 30, 2024
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 arstechnica.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
3 of 5Significant control incident

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.

Why this level

  • The behaviour repeated rather than stopping. Argues for a potential level of 3

What is established, and what is not

Confirmed

Nothing is confirmed yet.

Reported, not confirmed

  • The behaviour repeated rather than stopping

    The chat-breaking behavior occurs consistently when users mention these names in any context, and it results from a hard-coded filter that puts the brakes on the AI model’s output before returning it to the user.
    Certain names make ChatGPT grind to a halt, and we know why

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.

Certain names make ChatGPT grind to a halt, and we know why, Humanity & AI Safety Accord