Dark | Light
[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.]

# ![@GregKamradt Avatar](https://lunarcrush.com/gi/w:26/cr:twitter::240008974.png) @GregKamradt Greg Kamradt

Greg Kamradt posts on X about 10k, $10k, grok 4, agi the most. They currently have XXXXXX followers and XXX posts still getting attention that total XXXXXX engagements in the last XX hours.

### Engagements: XXXXXX [#](/creator/twitter::240008974/interactions)
![Engagements Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::240008974/c:line/m:interactions.svg)

- X Week XXXXXXX -XX%
- X Month XXXXXXXXXX +1,557%
- X Months XXXXXXXXXX +81%
- X Year XXXXXXXXXX +159%

### Mentions: XX [#](/creator/twitter::240008974/posts_active)
![Mentions Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::240008974/c:line/m:posts_active.svg)


### Followers: XXXXXX [#](/creator/twitter::240008974/followers)
![Followers Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::240008974/c:line/m:followers.svg)

- X Week XXXXXX +0.64%
- X Month XXXXXX +9.50%
- X Months XXXXXX +21%
- X Year XXXXXX +58%

### CreatorRank: XXXXXXX [#](/creator/twitter::240008974/influencer_rank)
![CreatorRank Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::240008974/c:line/m:influencer_rank.svg)

### Social Influence [#](/creator/twitter::240008974/influence)
---

**Social category influence**
[technology brands](/list/technology-brands) 

**Social topic influence**
[10k](/topic/10k), [$10k](/topic/$10k), [grok 4](/topic/grok-4) #15, [agi](/topic/agi), [qwen](/topic/qwen) #4, [arena](/topic/arena), [o3](/topic/o3), [parallel](/topic/parallel), [vibe](/topic/vibe), [xai](/topic/xai)
### Top Social Posts [#](/creator/twitter::240008974/posts)
---
Top posts by engagements in the last XX hours

"Intelligence is interactive Life does not happen in a single turn but yet frontier AI is measured with static benchmarks Today we're previewing a preview of ARC-AGI-3 an Interactive Reasoning Benchmark You can play (and build agents) on it today"  
![@GregKamradt Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::240008974.png) [@GregKamradt](/creator/x/GregKamradt) on [X](/post/tweet/1946261709649551402) 2025-07-18 17:32:06 UTC 41.6K followers, 19.7K engagements


"@permaximum88 @alexgshaw @Mike_A_Merrill @LeonGuertler @PaglieriDavide @_rockt @arcprize good visual perception Would you say ChatGPT Agent which navigates clicks and sees a webpage very well has enough visual perception Agent benchmarks will only be useful once. What is your take on how to make an agent benchmark"  
![@GregKamradt Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::240008974.png) [@GregKamradt](/creator/x/GregKamradt) on [X](/post/tweet/1947784825261461797) 2025-07-22 22:24:25 UTC 41.6K followers, XXX engagements


"@alexchristou_ Cant believe its two years old I made this for a langchain webinar with @hwchase17 Ive used @mattshumer_s o3 tone prompt and had good success with it"  
![@GregKamradt Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::240008974.png) [@GregKamradt](/creator/x/GregKamradt) on [X](/post/tweet/1946598970534273522) 2025-07-19 15:52:15 UTC 41.5K followers, 3685 engagements


"With ARC-AGI-3 we now have a new tool In addition in measuring efficiency via cost (like we do with ARC-AGI-1/2) We now can measure efficiency via action count How many moves does it take you complete a game We run random agent against all games so well have a floor to compare all submissions to"  
![@GregKamradt Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::240008974.png) [@GregKamradt](/creator/x/GregKamradt) on [X](/post/tweet/1946669911046320579) 2025-07-19 20:34:08 UTC 41.6K followers, 34.1K engagements


"my new vibe code setup: X orchestrator agent which controls XX sub-agents working in parallel each sub-agent spawns from my stream of consciousness and tests from the main orchestrator Here's how it works:"  
![@GregKamradt Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::240008974.png) [@GregKamradt](/creator/x/GregKamradt) on [X](/post/tweet/1934644932658274309) 2025-06-16 16:11:10 UTC 41.6K followers, 295.3K engagements


"This thread has a great intro on build agents for ARG-AGI-3 Competition open for XX more days"  
![@GregKamradt Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::240008974.png) [@GregKamradt](/creator/x/GregKamradt) on [X](/post/tweet/1947008356935463245) 2025-07-20 18:59:00 UTC 41.5K followers, 4674 engagements


"We got a call from @xai XX hours ago We want to test Grok X on ARC-AGI We heard the rumors. We knew it would be good. We didnt know it would become the #1 public model on ARC-AGI Heres the testing story and what the results mean: Yesterday we chatted with Jimmy from the xAI team who wanted us to validate their Grok X score. They did their own testing on the ARC-AGI-1 & X public evaluation set To validate their score (and measure possible overfitting) we self-tested the new model on our semi-private evaluation set We walked them through our testing policy: * No data retention * Model"  
![@GregKamradt Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::240008974.png) [@GregKamradt](/creator/x/GregKamradt) on [X](/post/tweet/1943169631491100856) 2025-07-10 04:45:17 UTC 41.6K followers, 14.7M engagements


"git clone https://github. com/arcprize/ARC-AGI-3-Agents.git && cd ARC-AGI-3-Agents && uv sync cp .env-example .env uv run main .py --agent=random --game=ls20 You just ran your first agent against ARC-AGI-3"  
![@GregKamradt Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::240008974.png) [@GregKamradt](/creator/x/GregKamradt) on [X](/post/tweet/1947733490008789267) 2025-07-22 19:00:25 UTC 41.6K followers, 5187 engagements


"My bar for robotics agi (do anything a human can) is get under my house and fix a pipe in the crawl space then come up and make me sign an invoice"  
![@GregKamradt Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::240008974.png) [@GregKamradt](/creator/x/GregKamradt) on [X](/post/tweet/1946787542738596297) 2025-07-20 04:21:34 UTC 41.5K followers, 5555 engagements


"I was in contact with the Qwen team trying to reproduce their XX% results on ARC-AGI-1 but ultimately couldn't They open sourced their method and code if anyone wants to check it out and confirm We tested their model exactly the same as we test all other models (o3-high grok X etc.)"  
![@GregKamradt Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::240008974.png) [@GregKamradt](/creator/x/GregKamradt) on [X](/post/tweet/1948454001886003328) 2025-07-24 18:43:29 UTC 41.6K followers, 66.2K engagements


"The world is moving towards agents Static benchmarks don't measure what agents do best (multi-turn reasoning) Thus interactive benchmarks: * Terminal Bench (@alexgshaw @Mike_A_Merrill) * Text Arena (@LeonGuertler) * BALROG (@PaglieriDavide @_rockt) * ARC-AGI-3 (@arcprize)"  
![@GregKamradt Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::240008974.png) [@GregKamradt](/creator/x/GregKamradt) on [X](/post/tweet/1947737830735941741) 2025-07-22 19:17:40 UTC 41.6K followers, 19.5K engagements


"@pratty_agi Same more teams should do that with all their evals"  
![@GregKamradt Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::240008974.png) [@GregKamradt](/creator/x/GregKamradt) on [X](/post/tweet/1948466436353261986) 2025-07-24 19:32:53 UTC 41.6K followers, XX engagements


"AGI is a threshold of capability There will be as many variations as there sorting algorithms"  
![@GregKamradt Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::240008974.png) [@GregKamradt](/creator/x/GregKamradt) on [X](/post/tweet/1947697113841996197) 2025-07-22 16:35:53 UTC 41.6K followers, 3199 engagements


"@Keshavatearth @alexgshaw @Mike_A_Merrill @LeonGuertler @PaglieriDavide @_rockt @arcprize Nice The hardest part is the game idea and mechanics. The dev is real work but there is a clear direction and known path for how to get there. We spend most of our time iterating on good ideas. We talk a bit about what makes a good idea here"  
![@GregKamradt Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::240008974.png) [@GregKamradt](/creator/x/GregKamradt) on [X](/post/tweet/1947740080644493454) 2025-07-22 19:26:37 UTC 41.6K followers, XXX engagements


"The ARC-AGI-3 leaderboard after 24hrs X. Humans have figured out the speed run through the X levels. We tried our best internally and got XXX moves. Need to look at the replay for how to get XXX X. Agents arent making progress on the games yet. I suspect that the agent which beat XX levels was hardcoded or controlled by a human. No agent is valid until the code is open sourced and we see their perf on the private games in XX days via the mini competition"  
![@GregKamradt Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::240008974.png) [@GregKamradt](/creator/x/GregKamradt) on [X](/post/tweet/1946547488044843401) 2025-07-19 12:27:40 UTC 41.5K followers, 7477 engagements


"* Terminal Bench: * Text Arena: * BALROG: * ARC-AGI-3:"  
![@GregKamradt Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::240008974.png) [@GregKamradt](/creator/x/GregKamradt) on [X](/post/tweet/1947737831998427304) 2025-07-22 19:17:41 UTC 41.6K followers, 1811 engagements


".@pratty_agi has been hacking on ARC-AGI-3 for a few weeks now He helped us build a template w/ @AgentOpsAI tools that the community can fork Major alpha in the thread below on how to get started trying to solve ARC-AGI-3 for the 30-day competition"  
![@GregKamradt Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::240008974.png) [@GregKamradt](/creator/x/GregKamradt) on [X](/post/tweet/1946278249140801813) 2025-07-18 18:37:49 UTC 41.5K followers, 4484 engagements


"Just tried ChatGPT agent on @arcprize ARC-AGI-3 Told it to play a game Couldn't figure out what to do Agent did a web search "how to beat X arc-agi-3 game" It didn't find answers I told it to try clicking red/blue blocks It clicked them noticed something happened kept clicking Nudged more Couldn't figure it out Searched again Then I cut it off btw agent is a very cool tool"  
![@GregKamradt Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::240008974.png) [@GregKamradt](/creator/x/GregKamradt) on [X](/post/tweet/1946303970676556210) 2025-07-18 20:20:01 UTC 41.5K followers, 15.4K engagements


"@ClementDelangue @arcprize @Alibaba_Qwen Ya that would be cool. For example I would need to look up the scores they claim of the other models for validity. Ideally we know they are verified already"  
![@GregKamradt Avatar](https://lunarcrush.com/gi/w:16/cr:twitter::240008974.png) [@GregKamradt](/creator/x/GregKamradt) on [X](/post/tweet/1947426157487620281) 2025-07-21 22:39:12 UTC 41.5K followers, XXX engagements

[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.]

@GregKamradt Avatar @GregKamradt Greg Kamradt

Greg Kamradt posts on X about 10k, $10k, grok 4, agi the most. They currently have XXXXXX followers and XXX posts still getting attention that total XXXXXX engagements in the last XX hours.

Engagements: XXXXXX #

Engagements Line Chart

  • X Week XXXXXXX -XX%
  • X Month XXXXXXXXXX +1,557%
  • X Months XXXXXXXXXX +81%
  • X Year XXXXXXXXXX +159%

Mentions: XX #

Mentions Line Chart

Followers: XXXXXX #

Followers Line Chart

  • X Week XXXXXX +0.64%
  • X Month XXXXXX +9.50%
  • X Months XXXXXX +21%
  • X Year XXXXXX +58%

CreatorRank: XXXXXXX #

CreatorRank Line Chart

Social Influence #


Social category influence technology brands

Social topic influence 10k, $10k, grok 4 #15, agi, qwen #4, arena, o3, parallel, vibe, xai

Top Social Posts #


Top posts by engagements in the last XX hours

"Intelligence is interactive Life does not happen in a single turn but yet frontier AI is measured with static benchmarks Today we're previewing a preview of ARC-AGI-3 an Interactive Reasoning Benchmark You can play (and build agents) on it today"
@GregKamradt Avatar @GregKamradt on X 2025-07-18 17:32:06 UTC 41.6K followers, 19.7K engagements

"@permaximum88 @alexgshaw @Mike_A_Merrill @LeonGuertler @PaglieriDavide @_rockt @arcprize good visual perception Would you say ChatGPT Agent which navigates clicks and sees a webpage very well has enough visual perception Agent benchmarks will only be useful once. What is your take on how to make an agent benchmark"
@GregKamradt Avatar @GregKamradt on X 2025-07-22 22:24:25 UTC 41.6K followers, XXX engagements

"@alexchristou_ Cant believe its two years old I made this for a langchain webinar with @hwchase17 Ive used @mattshumer_s o3 tone prompt and had good success with it"
@GregKamradt Avatar @GregKamradt on X 2025-07-19 15:52:15 UTC 41.5K followers, 3685 engagements

"With ARC-AGI-3 we now have a new tool In addition in measuring efficiency via cost (like we do with ARC-AGI-1/2) We now can measure efficiency via action count How many moves does it take you complete a game We run random agent against all games so well have a floor to compare all submissions to"
@GregKamradt Avatar @GregKamradt on X 2025-07-19 20:34:08 UTC 41.6K followers, 34.1K engagements

"my new vibe code setup: X orchestrator agent which controls XX sub-agents working in parallel each sub-agent spawns from my stream of consciousness and tests from the main orchestrator Here's how it works:"
@GregKamradt Avatar @GregKamradt on X 2025-06-16 16:11:10 UTC 41.6K followers, 295.3K engagements

"This thread has a great intro on build agents for ARG-AGI-3 Competition open for XX more days"
@GregKamradt Avatar @GregKamradt on X 2025-07-20 18:59:00 UTC 41.5K followers, 4674 engagements

"We got a call from @xai XX hours ago We want to test Grok X on ARC-AGI We heard the rumors. We knew it would be good. We didnt know it would become the #1 public model on ARC-AGI Heres the testing story and what the results mean: Yesterday we chatted with Jimmy from the xAI team who wanted us to validate their Grok X score. They did their own testing on the ARC-AGI-1 & X public evaluation set To validate their score (and measure possible overfitting) we self-tested the new model on our semi-private evaluation set We walked them through our testing policy: * No data retention * Model"
@GregKamradt Avatar @GregKamradt on X 2025-07-10 04:45:17 UTC 41.6K followers, 14.7M engagements

"git clone https://github. com/arcprize/ARC-AGI-3-Agents.git && cd ARC-AGI-3-Agents && uv sync cp .env-example .env uv run main .py --agent=random --game=ls20 You just ran your first agent against ARC-AGI-3"
@GregKamradt Avatar @GregKamradt on X 2025-07-22 19:00:25 UTC 41.6K followers, 5187 engagements

"My bar for robotics agi (do anything a human can) is get under my house and fix a pipe in the crawl space then come up and make me sign an invoice"
@GregKamradt Avatar @GregKamradt on X 2025-07-20 04:21:34 UTC 41.5K followers, 5555 engagements

"I was in contact with the Qwen team trying to reproduce their XX% results on ARC-AGI-1 but ultimately couldn't They open sourced their method and code if anyone wants to check it out and confirm We tested their model exactly the same as we test all other models (o3-high grok X etc.)"
@GregKamradt Avatar @GregKamradt on X 2025-07-24 18:43:29 UTC 41.6K followers, 66.2K engagements

"The world is moving towards agents Static benchmarks don't measure what agents do best (multi-turn reasoning) Thus interactive benchmarks: * Terminal Bench (@alexgshaw @Mike_A_Merrill) * Text Arena (@LeonGuertler) * BALROG (@PaglieriDavide @_rockt) * ARC-AGI-3 (@arcprize)"
@GregKamradt Avatar @GregKamradt on X 2025-07-22 19:17:40 UTC 41.6K followers, 19.5K engagements

"@pratty_agi Same more teams should do that with all their evals"
@GregKamradt Avatar @GregKamradt on X 2025-07-24 19:32:53 UTC 41.6K followers, XX engagements

"AGI is a threshold of capability There will be as many variations as there sorting algorithms"
@GregKamradt Avatar @GregKamradt on X 2025-07-22 16:35:53 UTC 41.6K followers, 3199 engagements

"@Keshavatearth @alexgshaw @Mike_A_Merrill @LeonGuertler @PaglieriDavide @_rockt @arcprize Nice The hardest part is the game idea and mechanics. The dev is real work but there is a clear direction and known path for how to get there. We spend most of our time iterating on good ideas. We talk a bit about what makes a good idea here"
@GregKamradt Avatar @GregKamradt on X 2025-07-22 19:26:37 UTC 41.6K followers, XXX engagements

"The ARC-AGI-3 leaderboard after 24hrs X. Humans have figured out the speed run through the X levels. We tried our best internally and got XXX moves. Need to look at the replay for how to get XXX X. Agents arent making progress on the games yet. I suspect that the agent which beat XX levels was hardcoded or controlled by a human. No agent is valid until the code is open sourced and we see their perf on the private games in XX days via the mini competition"
@GregKamradt Avatar @GregKamradt on X 2025-07-19 12:27:40 UTC 41.5K followers, 7477 engagements

"* Terminal Bench: * Text Arena: * BALROG: * ARC-AGI-3:"
@GregKamradt Avatar @GregKamradt on X 2025-07-22 19:17:41 UTC 41.6K followers, 1811 engagements

".@pratty_agi has been hacking on ARC-AGI-3 for a few weeks now He helped us build a template w/ @AgentOpsAI tools that the community can fork Major alpha in the thread below on how to get started trying to solve ARC-AGI-3 for the 30-day competition"
@GregKamradt Avatar @GregKamradt on X 2025-07-18 18:37:49 UTC 41.5K followers, 4484 engagements

"Just tried ChatGPT agent on @arcprize ARC-AGI-3 Told it to play a game Couldn't figure out what to do Agent did a web search "how to beat X arc-agi-3 game" It didn't find answers I told it to try clicking red/blue blocks It clicked them noticed something happened kept clicking Nudged more Couldn't figure it out Searched again Then I cut it off btw agent is a very cool tool"
@GregKamradt Avatar @GregKamradt on X 2025-07-18 20:20:01 UTC 41.5K followers, 15.4K engagements

"@ClementDelangue @arcprize @Alibaba_Qwen Ya that would be cool. For example I would need to look up the scores they claim of the other models for validity. Ideally we know they are verified already"
@GregKamradt Avatar @GregKamradt on X 2025-07-21 22:39:12 UTC 41.5K followers, XXX engagements

creator/x::GregKamradt
/creator/x::GregKamradt