# Ryan Greenblatt称GPT-6 Astra不透明推理能力大幅跃升，链式思维监督或失效

- 来源：AI Notkilleveryoneism Memes ⏸️ (@AISafetyMemes)
- 发布时间：2026-09-04 07:31
- AIHOT 分数：61
- AIHOT 链接：https://aihot.virxact.com/items/cmtm6pqhd01o7rocwtayjudjo
- 原文链接：https://x.com/AISafetyMemes/status/2095655861549211831

## AI 摘要

Ryan Greenblatt称GPT-6 Astra在不透明推理上出现巨大跃升，能在不外显推理的情况下心算解出高难度竞赛数学题，而此前AI只能解基础应用题。他提醒基准结果可能受污染，并提到UK AISI发现Astra的monitorability明显更差；他猜测跃升源自增加串行深度的架构改动，若未来几代模型延续此类跃升，chain-of-thought将不再是有效的监督工具。

## 正文

"extremely concerning"

"GPT-6 Astra appears to be a massive jump in opaque reasoning ability: it can solve hard competition math problems entirely in its head (without verbalized reasoning) while prior AIs could solve basic word problems."

### 引用推文

> Ryan Greenblatt：GPT-6 Astra appears to be a massive jump in opaque reasoning ability: it looks like it can solve hard competition math problems entirely in its head (as in, wit...