[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.]

![marcel_butucea Avatar](https://lunarcrush.com/gi/w:24/cr:twitter::920542823354470400.png) Marcel Butucea [@marcel_butucea](/creator/twitter/marcel_butucea) on x 1527 followers
Created: 2025-07-22 04:00:23 UTC

Wow, XX% accuracy in judging code reviews with an LLM - but it plummets to XX% when switching models! 🤯 This shows that prompt engineering is highly model-specific. The real question is:...



![](https://pbs.twimg.com/card_img/1947345606432698368/DJAqa9Ee?format=jpg&name=800x419)

XX engagements

![Engagements Line Chart](https://lunarcrush.com/gi/w:600/p:tweet::1947506987031318789/c:line.svg)

**Related Topics**
[prompt engineering](/topic/prompt-engineering)
[llm](/topic/llm)

[Post Link](https://x.com/marcel_butucea/status/1947506987031318789)