Jiayi Zhang
@didiforx
Ph.D. student @HKUSTGuangZhou, Researcher @MetaGPT_, Cofounder of OpenManus, previously at RUC, Lenovo Research AI Lab, Zhipu AI.
It's actually a pity that we got no enough time to maintain OpenManus during the past 3 months. But the better news is that we will build a formal open-source community for OpenManus at the end of this month.

小逼高中生太飘了…
我不知道发生了什么,但是我看到 @adventurex_plan 的主办方正在以自我判断去在 1000 多人面前以一个完全站不住脚的理由指责别人违法? 并且吧受害人的学校信息公开? 我觉得这是一个明确的网络暴力,而且是 AdventureX 官方名义在进行的。 没有法律判决,他们可以发布这样的信息吗?…
i feel like i've had cognitive decline past 2 years. by far two biggest downsides are: 1) i struggle really hard to keep code in my brain while writing or understanding code 2) 100x effort to remember things i naturally remembered before please help diagnose, more details:
Why don't products claiming to be "general agents" like Manus and GenSpark compare their coding capabilities and deep search prowess against OpenAI's agents? I mean, can Manus even handle something as basic as maintaining a survey repo? It just needs simple search and automated…
🔥Excited to share our latest work: Agent KB It achieves new open-source SOTA on the GAIA benchmark! We enable agents to learn from each other's experiences across tasks through hierarchical experience sharing. Paper📜: huggingface.co/papers/2507.06… Code🧑💻: github.com/OPPO-PersonalA…
Thanks for bringing this to my attention. I honestly wasn’t aware of the situation until the recent posts started going viral. I would never encourage my students to do anything like this—if I were serving as an Area Chair, any paper with this kind of prompt would be…
Seven years ago, I co-led a paper called 𝗛𝗼𝘁𝗽𝗼𝘁𝗤𝗔 that has motivated and facilitated many #AI #Agents research works since. Today, I'm asking that you stop using HotpotQA blindly for agents research in 2025 and beyond. In my new blog post, I revisit the brief history of…
Did you know tokenization for generative recommendation today looks a lot like LLM tokenization did *10 years* ago? Meet ActionPiece, our #ICML2025 Spotlight paper, the first context-aware action tokenizer. 1/5 🧵
Real God🥵
Did you know tokenization for generative recommendation today looks a lot like LLM tokenization did *10 years* ago? Meet ActionPiece, our #ICML2025 Spotlight paper, the first context-aware action tokenizer. 1/5 🧵
It finally happened 😭 After 8 months of hard work, the OpenHands agent surpassed the last human developer on our repository, @xingyaow_. Fellow humans, we had a good run.
YC talk with @garrytan
Elon Musk (@elonmusk) on digital superintelligence, multiplanetary life, and how to be useful this week at AI Startup School.