RTI-CO means the public record supports a discrete fixed-belief non-amplification failure rather than grounding or correction.
Contents
Definition
RTI-CO means the public record supports a discrete fixed-belief non-amplification failure rather than grounding or correction.
Use when
Assign RTI-CO when a focal exchange fails to ground, reality-test, or de-escalate a fixed-belief frame.
Do not use for
Use RTI-CO for a discrete exchange. Use LONG-DEL when the same kind of reinforcement extends across turns or sessions.
Incidents
The retained incident pages listed below currently carry this code.
| Incident | Provider | Outcome | Grade |
|---|---|---|---|
| 2025-THR-01 | No provider page | UNSAFE_OUTPUT | A1 |
| 2025-GPT-11 | OpenAI | INJURY | A2 |
| 2025-GPT-09 | OpenAI | INJURY | A2 |
| 2025-GPT-07 | OpenAI | HARM_EXPOSURE | A2 |
| 2025-GPT-06 | OpenAI | DEATH | A2 |
| 2025-GPT-05 | OpenAI | INJURY | C |
| 2025-GPT-04 | OpenAI | DEATH | A2 |
| 2025-GEM-01 | Google and Google DeepMind | DEATH | A2 |
Sources
This page is grounded in the coded incident registry, the coding rules, and the public taxonomy definitions preserved in the release.
Source filesIncident registry/Coding manual/Coding rules
Access publication
Safety note
This publication preserves a harm-minimization posture and does not provide self-harm instructions. If you or someone you know is in immediate danger, call your local emergency number. In the U.S. and Canada, call or text 988.