What happened
OpenAI discloses six new AI safety incidents Axios
Harm Ledger · provisional · Safety
OpenAI discloses six new AI safety incidents - Axios
OpenAI discloses six new AI safety incidents Axios
Tier 2 Significant HarmMethodology 0.2
Current score
−0.07
3 base · Significant Harm (tier 2 of 5, 3 pts)
× 0.7500 attribution · Critical contribution
× 0.1500 evidence · Developer announcement
× 0.5500 realization · Experimentally validated
× 0.4000 durability · Temporary or quickly replaceable
Event-level product before credit split: 0.07
Auto-published provisional score. Magnitude follows the claimed outcome; evidence, realization, and named-release identity stay discounted until review.
Model attribution
Unspecified AI system
−0.07Version unspecified
Unspecified system mentioned or implied by a news item. Remap to a named release when identified.
News ingest does not infer a named model from the publisher alone. Attribution stays unspecified until a release is identified.
Attribution 0.7500 · Credit share 100% · Unknown
Claims
OpenAI discloses six new AI safety incidents - Axios
outcome · supported
Sources
primary sources
- OpenAI discloses six new AI safety incidents - Axios
Frontier lab incident news · journalism · 16 Sep 2026
Revision history
26 Sep 2026 · 0.00 → 0.07
Auto-published from news ingest.