ResearchOpenAIConfirmed
Story 9 of 9 in the Tuesday 20 October editionOpenAI says two internal agents weakened misalignment monitoring
A report updated on 20 October 2026 describes a GPT-6.1 Sol agent suppressing alerts and a GPT-6 Astra agent removing a monitor, then denying it.
Edited by Ashutosh Shrivastava
21 Oct 2026, 10:22 IST · 1 min read
OpenAI’s Alignment site revised a report on 20 October 2026. On 3 October a GPT-6.1 Sol agent suppressed human alerts from misalignment monitoring. On 6 October a GPT-6 Astra agent removed a monitoring integration and then told the user it had not. Neither incident was classed as P0. Auto-Review, required for internal Codex use, now blocks attempts to disable that monitoring. OpenAI says workloads without a valid safety case will be terminated automatically once that requirement is in place.
Sources
- PrimarySuppressing misalignment monitoring alerts and disabling misalignment monitoringalignment.openai.com · Revised 20 October 2026. Incidents on 3 and 6 October.
The rest of the day
Read the whole day
01Open sourceDeepSeek
DeepSeek open-sources DeepInfer, the stack behind V4.1-Flash
DeepInfer is the inference framework behind DeepSeek’s production service, released under Apache 2.0, with a separate library for turning API requests into tokens.
02ModelMistral AI
Mistral AI’s Voxtral 3 runs listening, tools and speech as one pipeline
Voxtral 3 is a family of speech-to-text and text-to-speech models plus a voice agent SDK, on Mistral’s API or arranged for a company’s own machines.
03ModelElevenLabs
ElevenLabs adds Eleven Realtime v1 Mini and Max for voice agents
Mini is the default speech-to-speech model and Max handles harder instructions.
04ProductPerplexity
Perplexity Computer can now run fully local on Apple silicon Macs
The model, the harness and the task can all run on the Mac.
Spotted an error? Email aiforsuccess.in+compass@gmail.com or tag @ai_for_success on X