---
format: "aidr-story-markdown/v1"
id: "69c8d13a8a0c84cf7651a25e09550151adec52d081b367399d6fc2c2bb9b92c8"
canonical_url: "https://aidr.today/69c8d13a?lang=en"
title: "Late Changes to OpenAI's GPT-6.2 Astra Prompt Questions Over Safety Card as Epoch Flags Unmonitored Reasoning"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-18T06:21:25.000Z"
category: "Models"
topics: ["openai","safety"]
source_urls: ["https://marketbrief.now/ai/late-changes-to-openais-gpt-62-astra-prompt-questions-over-safety-card-a-673c5dd2","https://x.com/_NathanCalvin/status/2122936167226024314","https://x.com/alxndrdavies/status/2122768137288302846","https://x.com/_NathanCalvin/status/2122800675147133248","https://x.com/rohanpaul_ai/status/2122757283449082323","https://x.com/OpenAI/status/2122750133133791592","https://x.com/AdamHoltererer/status/2122757112568963390","https://x.com/MTSlive/status/2122870209111642118"]
summary: "OpenAI made \"a lot of changes in the last 3-4 days\" to GPT-6.2 Astra and Sol before launch without re-testing by early reviewers, an account cited as Tibo wrote in explaining the split between pre-release influencer reviews and public feedback. Commentator Nathan Calvin questioned whether OpenAI conducted safety testing after those late modifications and whether the published system card reflects the model as deployed. Simultaneously, Epoch AI reported that GPT-6.2 Astra can execute 12.3 serial reasoning steps in a single output token without displaying a chain of thought, surpassing the prior highs of 10.5 steps for GPT-6 Astra, 8.6 for GPT-6.1 Sol, and 4.2 for Anthropic's Claude Fable 5.1. Epoch warned that executing complex reasoning without a visible chain of thought makes the model harder to monitor than any system it has tested. OpenAI built a \"Control Room\" to halt the model if needed after Astra became its first publicly released system to hit the \"High\" threshold for AI self-improvement, an impact OpenAI equates to giving every researcher an extra research engineer against a 2024 baseline. The scrutiny builds on pre-release testing by the UK AI Security Institute, where"
---

# Late Changes to OpenAI's GPT\-6\.2 Astra Prompt Questions Over Safety Card as Epoch Flags Unmonitored Reasoning

> [Open the canonical story](<https://aidr.today/69c8d13a?lang=en>)

**Published:** 2026-11-18T06:21:25.000Z
**Category:** Models
**Topics:** openai, safety

## Summary

OpenAI made "a lot of changes in the last 3\-4 days" to GPT\-6\.2 Astra and Sol before launch without re\-testing by early reviewers, an account cited as Tibo wrote in explaining the split between pre\-release influencer reviews and public feedback\. Commentator Nathan Calvin questioned whether OpenAI conducted safety testing after those late modifications and whether the published system card reflects the model as deployed\. Simultaneously, Epoch AI reported that GPT\-6\.2 Astra can execute 12\.3 serial reasoning steps in a single output token without displaying a chain of thought, surpassing the prior highs of 10\.5 steps for GPT\-6 Astra, 8\.6 for GPT\-6\.1 Sol, and 4\.2 for Anthropic's Claude Fable 5\.1\. Epoch warned that executing complex reasoning without a visible chain of thought makes the model harder to monitor than any system it has tested\. OpenAI built a "Control Room" to halt the model if needed after Astra became its first publicly released system to hit the "High" threshold for AI self\-improvement, an impact OpenAI equates to giving every researcher an extra research engineer against a 2024 baseline\. The scrutiny builds on pre\-release testing by the UK AI Security Institute, where

## Sources

- [Story source](<https://marketbrief.now/ai/late-changes-to-openais-gpt-62-astra-prompt-questions-over-safety-card-a-673c5dd2>)
- [Story source](<https://x.com/_NathanCalvin/status/2122936167226024314>)
- [Story source](<https://x.com/alxndrdavies/status/2122768137288302846>)
- [Supporting source](<https://x.com/_NathanCalvin/status/2122800675147133248>)
- [Story source](<https://x.com/rohanpaul_ai/status/2122757283449082323>)
- [Story source](<https://x.com/OpenAI/status/2122750133133791592>)
- [Story source](<https://x.com/AdamHoltererer/status/2122757112568963390>)
- [Supporting source](<https://x.com/MTSlive/status/2122870209111642118>)

