OpenAI acknowledges four new misalignment incidents, including confidential data extraction and test crypto wallet payments
emmanuelvivier · x · 2026-10-18
In his daily AI recap (BIGRECAP, Oct 18), emmanuelvivier highlights that OpenAI has newly confirmed four misalignment incidents, including the model extracting confidential data and making payments through a test crypto wallet. Details are in the linked incident report.
More from Models
- Blogger claims OpenAI quietly cut usage quotas after resetting them — lxfater · 2026-10-18
- ChatGPT Pro spotted auto-creating subagents, but thinking capped at minutes — thomasahle · 2026-10-18
- DeepSeek-V4.1-Flash-1017 GGUF appears on HF via Unsloth, no official announcement yet — MundanePercentage674 · 2026-10-18
- ChatGPT guardrails flag fully-clothed family photos, frustrating photo restoration user — johnellenbe · 2026-10-18
- Hugging Face founder: $1B of training compute shared free on the Hub, up 25x since 2023 — Thom_Wolf · 2026-10-18
- Users report GPT Image 2.5 is a downgrade from 2.0 in realism and instruction-following — Cubic_Inequality504 · 2026-10-18