[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

![marksg Avatar](https://lunarcrush.com/gi/w:24/cr:twitter::37065919.png) Mark G [@marksg](/creator/twitter/marksg) on x XXX followers
Created: 2025-07-22 03:18:26 UTC

Google DeepMind in achieving Gold in the IMO (Int’l Math Olympiad) used an inference architecture similar to the RLToT technique that I guessed might have been used by OpenAI who also achieved Gold.


![](https://pbs.twimg.com/media/Gwblrd5bsAAJpJv.jpg)

XXX engagements

![Engagements Line Chart](https://lunarcrush.com/gi/w:600/p:tweet::1947496432170373219/c:line.svg)

**Related Topics**
[open ai](/topic/open-ai)
[inference](/topic/inference)
[$googl](/topic/$googl)
[stocks communication services](/topic/stocks-communication-services)

[Post Link](https://x.com/marksg/status/1947496432170373219)