[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.]

![LLMSherpa Avatar](https://lunarcrush.com/gi/w:24/cr:twitter::911315541490569216.png) Sherpa [@LLMSherpa](/creator/twitter/LLMSherpa) on x 5559 followers
Created: 2025-07-16 16:15:17 UTC

Legitimately, you can talk about harm reduction all you please, but I've gotten thousands of pages of harmful output from GPT models.

And, yet, the ONLY warning letter I got from OpenAi was when I broke o1's CoT after release.

Priorities.


XXX engagements

![Engagements Line Chart](https://lunarcrush.com/gi/w:600/p:tweet::1945517603549483371/c:line.svg)

**Related Topics**
[open ai](/topic/open-ai)
[harm](/topic/harm)

[Post Link](https://x.com/LLMSherpa/status/1945517603549483371)