[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.]

# ![@casper_hansen_ Avatar](https://lunarcrush.com/gi/w:26/cr:twitter::1163801450968997889.png) @casper_hansen_ Casper Hansen

Casper Hansen posts on X about where is, what i, everything is, agi the most. They currently have XXXXXX followers and 1245 posts still getting attention that total XXXXXX engagements in the last XX hours.

### Engagements: XXXXXX [#](/creator/twitter::1163801450968997889/interactions)
![Engagements Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1163801450968997889/c:line/m:interactions.svg)

- X Week XXXXXX +92%
- X Month XXXXXXX -XXXX%
- X Months XXXXXXXXX -XX%
- X Year XXXXXXXXX +588%

### Mentions: X [#](/creator/twitter::1163801450968997889/posts_active)
![Mentions Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1163801450968997889/c:line/m:posts_active.svg)

- X Week XX +18%
- X Month XX +8.90%
- X Months XXX +181%
- X Year XXX +171%

### Followers: XXXXXX [#](/creator/twitter::1163801450968997889/followers)
![Followers Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1163801450968997889/c:line/m:followers.svg)

- X Week XXXXXX +0.58%
- X Month XXXXXX +4.10%
- X Months XXXXXX +54%
- X Year XXXXXX +249%

### CreatorRank: XXXXXXX [#](/creator/twitter::1163801450968997889/influencer_rank)
![CreatorRank Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1163801450968997889/c:line/m:influencer_rank.svg)

### Social Influence [#](/creator/twitter::1163801450968997889/influence)
---

**Social topic influence**
[where is](/topic/where-is), [what i](/topic/what-i), [everything is](/topic/everything-is), [agi](/topic/agi)
### Top Social Posts [#](/creator/twitter::1163801450968997889/posts)
---
Top posts by engagements in the last XX hours

"For those that think this is hype: no it's not. I invented a little training/eval set last night. Model score is about XX% with my own optimized prompt. GEPA takes that to XX% with auto="light" optimization. I imagine this can go to XX% with heavy optimization. Insane potential in this to become an automated optimizer for your model in production. Why train if you can just auto-adapt the model as prompts come through"  
[X Link](https://x.com/casper_hansen_/status/1978169521794859437) [@casper_hansen_](/creator/x/casper_hansen_) 2025-10-14T18:42Z 10.5K followers, 23.7K engagements


"Thanks Claude knew I could count on you my yes man"  
[X Link](https://x.com/casper_hansen_/status/1977637930043928825) [@casper_hansen_](/creator/x/casper_hansen_) 2025-10-13T07:29Z 10.5K followers, 2008 engagements


"@ayushchopra96 How small and where is this from Most training approaches can struggle in open-ended problems especially if the model is not that capable"  
[X Link](https://x.com/casper_hansen_/status/1977731700529541260) [@casper_hansen_](/creator/x/casper_hansen_) 2025-10-13T13:42Z 10.5K followers, XXX engagements


"@jackminong from what i know that stuff requires a partnership as there is trust involved from openai's side that whatever you are doing won't cause harm or end up as bad PR"  
[X Link](https://x.com/casper_hansen_/status/1978520401387950249) [@casper_hansen_](/creator/x/casper_hansen_) 2025-10-15T17:56Z 10.5K followers, XXX engagements


"qwen is so loved in the research community for one simple thing: it just works. it's insane how much tinkering you have to do for some models to work. the iteration time compounds especially for 100B+ models. guaranteed annoyance"  
[X Link](https://x.com/casper_hansen_/status/1978162195281183023) [@casper_hansen_](/creator/x/casper_hansen_) 2025-10-14T18:13Z 10.5K followers, 2110 engagements


"@ayushsdev You need either an eval in the loop to make GEPA work or you need to design some mechanism where you can auto-magically generate it as prompts come through"  
[X Link](https://x.com/casper_hansen_/status/1978866295966777451) [@casper_hansen_](/creator/x/casper_hansen_) 2025-10-16T16:51Z 10.5K followers, XXX engagements


"Calling it now: Every inference engine should have a built-in GEPA system that auto-evolves your prompt over time"  
[X Link](https://x.com/casper_hansen_/status/1978851428354379807) [@casper_hansen_](/creator/x/casper_hansen_) 2025-10-16T15:52Z 10.5K followers, 11.1K engagements


"I found X new methods that all outperform GEPA; except none of them are open-source. I stopped believing such papers a long time ago. The unfortunate reality of today is that papers are nothing more than a few words. If your code is not public how can I verify that it works Papers: - Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models: - C-Evolve: Consensus-based Evolution for Prompt Groups: - Maestro: Joint Graph & Config Optimization for Reliable AI Agents:"  
[X Link](https://x.com/casper_hansen_/status/1979535725222584658) [@casper_hansen_](/creator/x/casper_hansen_) 2025-10-18T13:11Z 10.5K followers, 16.1K engagements


"largely agree with karpathy in some aspects but also think the models of today are already what we would consider AGI just XX years ago"  
[X Link](https://x.com/casper_hansen_/status/1979563620477661445) [@casper_hansen_](/creator/x/casper_hansen_) 2025-10-18T15:02Z 10.5K followers, 1995 engagements