[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.]

![kylejeong21 Avatar](https://lunarcrush.com/gi/w:24/cr:twitter::1281175702788702210.png) Kyle Jeong [@kylejeong21](/creator/twitter/kylejeong21) on x 2788 followers
Created: 2025-07-15 16:23:19 UTC

@zeeg i don’t have a specific server in mind, but just thinking if we’re predicting tool calls instead of running them and giving the llm also context of the tool output (which i guess you can simulate too), then it won’t be able to predict properly for more complex servers


XX engagements

![Engagements Line Chart](https://lunarcrush.com/gi/w:600/p:tweet::1945157236814192690/c:line.svg)

**Related Topics**
[llm](/topic/llm)

[Post Link](https://x.com/kylejeong21/status/1945157236814192690)