liujiashuo77's profile picture. Research Scientist at ByteDance Seed | Advanced & Interesting LLM/Agent Evaluation. Opinions are my own.

Jiashuo Liu

@liujiashuo77

Research Scientist at ByteDance Seed | Advanced & Interesting LLM/Agent Evaluation. Opinions are my own.

置頂

We built FutureX, the world’s first live benchmark for real future prediction — politics, economy, culture, sports, etc. Among 23 AI agents, #Grok4 ranked #1 🏆 Elon didn’t lie. @elonmusk your model sees further 🚀🍀 LeaderBoard: futurex-ai.github.io

liujiashuo77's tweet image. We built FutureX, the world’s first live benchmark for real future prediction — politics, economy, culture, sports, etc. 
Among 23 AI agents, #Grok4 ranked #1 🏆
Elon didn’t lie.
@elonmusk your model sees further 🚀🍀

 LeaderBoard: futurex-ai.github.io

Agreed...

Anthropic CEO Dario Amodei on Open-Source AI Models. "I don't think open source works the same way in AI that it has worked in other areas. Primarily because with open source you can see the source code of the model. Here we can't see inside the model, it's often called open…



Grok has been underestimated for long, but clearly, it's among top-tier models now. We've investigated and analyzed Grok 4's search and reasoning patterns, which're really impressive! Looking forward to Grok 5 now:)

Introducing Grok 4 Fast, a multimodal reasoning model with a 2M context window that sets a new standard for cost-efficient intelligence. Available for free on grok.com, grok.x.com, iOS and Android apps, and OpenRouter. x.ai/news/grok-4-fa…



Week 2 Update of FutureX: - In our latest weekly leaderboard, surprisingly, MiroMind's open-source deep research agent plus GPT-5 got 1st place! Congrats @miromind_ai - ChatGPT-Agent slightly outperformed Grok4. Competition is tough! - Claude Opus 4.1 (submitted by independent…

liujiashuo77's tweet image. Week 2 Update of FutureX:
- In our latest weekly leaderboard, surprisingly,  MiroMind's open-source deep research agent plus GPT-5 got 1st place! Congrats @miromind_ai 
- ChatGPT-Agent slightly outperformed Grok4. Competition is tough!
- Claude Opus 4.1 (submitted by independent…

We built FutureX, the world’s first live benchmark for real future prediction — politics, economy, culture, sports, etc. Among 23 AI agents, #Grok4 ranked #1 🏆 Elon didn’t lie. @elonmusk your model sees further 🚀🍀 LeaderBoard: futurex-ai.github.io

liujiashuo77's tweet image. We built FutureX, the world’s first live benchmark for real future prediction — politics, economy, culture, sports, etc. 
Among 23 AI agents, #Grok4 ranked #1 🏆
Elon didn’t lie.
@elonmusk your model sees further 🚀🍀

 LeaderBoard: futurex-ai.github.io


Check this ⬇️ super cool pipeline!

FutureX Results I am now officially an AI researcher. Something interesting in the results: I beat on level 1 and 2 but lost on level 3 and 4. In this first week, I fed everything into a single context which likely reduced the amount of searches per query required to best…

BBacktesting's tweet image. FutureX Results

I am now officially an AI researcher.  Something interesting in the results: I beat on level 1 and 2 but lost on level 3 and 4.  

In this first week, I fed everything into a single context which likely reduced the amount of searches per query required to best…


FutureX Update! Thanks @elonmusk Detailed leaderboard is here: futurex-ai.github.io

The ability to predict the future is the best measure of intelligence



Wow thanks Elon! Yes, we think it's a measure of agent's AGI! Again, introduce our FutureX live benchmark. futurex-ai.github.io

Grok is the best at predicting the future, which is the best measure of intelligence imo



Loading...

Something went wrong.


Something went wrong.