peakji Profile Banner
Yichao 'Peak' Ji Profile
Yichao 'Peak' Ji

@peakji

Followers
25K
Following
86
Media
6
Statuses
55

Co-founder & Chief Scientist @ManusAI | Training AI since 2013, training Pokémon since 1998.

Joined February 2010
Don't wanna be here? Send us removal request.
@peakji
Yichao 'Peak' Ji
4 months
After four overhauls and millions of real-world sessions, here are the lessons we learned about context engineering for AI agents:
Tweet card summary image
manus.im
This post shares the local optima Manus arrived at through our own "SGD". If you're building your own AI agent, we hope these principles help you converge faster.
21
75
444
@peakji
Yichao 'Peak' Ji
24 days
Honestly, I'm surprised too — that's a legacy Manus from a few versions back lol...
@zephyr_z9
Zephyr
24 days
LOL How the hell is Manus No. 1??
1
5
29
@peakji
Yichao 'Peak' Ji
28 days
Happy to see Manus hitting SOTA in @scale_AI & @ai_risks' new benchmark, but that 2.5% on the Y-axis says we've still got a loooong way to go😅
@hendrycks
Dan Hendrycks
29 days
Can AI automate jobs? We created the Remote Labor Index to test AI’s ability to automate hundreds of long, real-world, economically valuable projects from remote work platforms. While AIs are smart, they are not yet that useful: the current automation rate is less than 3%.
2
2
21
@alexandr_wang
Alexandr Wang
28 days
A new eval, Remote Labor Index, measures AI's ability to automate real-world, economically valuable projects from remote work platforms. Currently entirely unsaturated (max score of 2.5%) A great collaboration between @scale_AI and @ai_risks!
@hendrycks
Dan Hendrycks
29 days
Can AI automate jobs? We created the Remote Labor Index to test AI’s ability to automate hundreds of long, real-world, economically valuable projects from remote work platforms. While AIs are smart, they are not yet that useful: the current automation rate is less than 3%.
50
60
549
@peakji
Yichao 'Peak' Ji
1 month
The all new web dev experience are now fully rolled out and available to all users. Behind it is still a unified general agent architecture, where every capability works together seamlessly: researching deeply to create sites, analyzing collected data, turning those insights
Tweet card summary image
manus.im
We released Manus 1.5: faster, higher quality, unlimited context, and an upgraded builder to create full apps in one prompt with backend, login, databases, AI features, notifications, and analytics.
@ManusAI
Manus
1 month
Introducing Manus 1.5 Faster, better quality results. Unlimited context. Build full-stack web apps, with real AI features, backends, user logins, custom domains and analytics. Run your biz, start your side hustle, or just have fun. If you can dream it, Manus can build it.
9
13
136
@RLanceMartin
Lance Martin
1 month
Context Engineering in Manus i had a great conversation w/ @peakji abt the design of @ManusAI_HQ + how these use context engineering. wrote some notes here (video link below). https://t.co/rmTD4m37Fm
6
23
179
@peakji
Yichao 'Peak' Ji
3 months
Grateful to be named in this year's MIT TR35 at 33. Fourteen years ago, I was fortunate to be on Forbes 30 Under 30 at 19. The past 14 years have been about learning, failing, and striving. Innovation is a journey, not a moment.
@techreview
MIT Technology Review
3 months
Yichao “Peak” Ji developed Manus, one of the buzziest AI apps of the year, in the latest project that blends his technical prowess with killer consumer instincts. We named him as one of this year’s 35 Innovators Under 35.
9
7
80
@peakji
Yichao 'Peak' Ji
3 months
What's going on here @GeminiApp, aren't we supposed to be best buddies? 😂
@omooretweets
Olivia Moore
3 months
IMO, this may be the most interesting data from our @a16z top 100 AI apps report. We looked at "Affinity Scores" for the top 6 most popular LLMs. Ex. what other apps are you most likely to have if you're a Claude or Perplexity user? This gave us mini-profiles of AI
2
1
17
@peakji
Yichao 'Peak' Ji
3 months
Today a16z released the latest AI Top 50 list. As a small startup, it's truly an honor that we made it with not just one, but two products. The company is charging toward the $100M milestone, and I'm about to enter my 15th year in entrepreneurship. In the beginning, I thought
15
10
182
@omooretweets
Olivia Moore
3 months
🚨 Announcing the latest @a16z top 100 AI apps! This marks the fifth edition 🎉 of our global ranking of consumer AI websites and mobile apps by usage. And in my opinion, it was our most surprising list yet! Our top takeaways + who made it 👇
69
159
1K
@chetanp
Chetan Puttagunta
3 months
Manus hits $90m run rate! Remarkable execution and a fantastic product being built in Singapore. Building exclusively on models from Anthropic, Google, and OpenAI, Manus is defining the next generation of ai powered productivity software for consumers and teams.
36
57
832
@peakji
Yichao 'Peak' Ji
3 months
Just had a great conversation with @paulharapin at Stripe Tour Singapore. It's amazing to see Manus grow from launch in March to a $90M revenue run rate, with $100M just around the corner. Grateful for Stripe's strong support along the way!
12
4
70
@mwseibel
Michael Seibel
4 months
Trying Manus Wide Research and loving it. If I were a product guy at that company, I’d be thinking of ways to make Manus more proactive. I’d love to have a daily or weekly call with the product where I can brainstorm research projects it could do for me then go off and do them.
15
10
199
@kimmonismus
Chubby♨️
4 months
With “Wide Research,” @ManusAI_HQ is bringing about a fundamental change in agentic work. I instructed the tool to scan 100 scientific articles – including titles, abstracts, authors, journals, year, number of citations, institution, and country. Everything was automatically
16
54
332
@peakji
Yichao 'Peak' Ji
4 months
Wide Research is our latest exploration in agent-agent collaboration. Built on our large-scale virtualization infrastructure, Manus can now autonomously dispatch a team of homogeneous Manus agents to work in parallel and aggregate the results. While building AI agents, we've
@ManusAI
Manus
4 months
Introducing Wide Research
10
17
144
@peakji
Yichao 'Peak' Ji
4 months
Choose the system architecture that benefits the most from switching to a stronger model, instead of comparing design choices using the same model. I treat it as a regularization factor in context engineering. It helps you discover more robust, generalizable architectures. It
@shengyulei
yuleis
4 months
@peakji Thanks for sharing the note, super helpful! What do you mean by 'Maximize F(M_strong) - F(M_weak)'?
3
1
16
@peakji
Yichao 'Peak' Ji
4 months
Forgot to include a key lesson in the blog: Context engineering can also overfit - not just to specific model families, but also to today's model limitations via premature optimization. At Manus, we never commit to an architecture based on static benchmarks. Instead, we treat
@peakji
Yichao 'Peak' Ji
4 months
After four overhauls and millions of real-world sessions, here are the lessons we learned about context engineering for AI agents:
6
5
59
@ManusAI
Manus
6 months
Today, Manus Integrates Veo3! Manus isn't just where you generate videos — it's where you craft cinematic experiences. Characters speak naturally with synchronized audio, scenes unfold longer to tell complete narratives, and everything feels sharper, richer, more alive than
102
332
3K
@peakji
Yichao 'Peak' Ji
6 months
Thinking of you guys, while the rest of us are squashing bugs back in Singapore. 🫠
@hidecloud
hidecloud
6 months
We were excited to meet with @satyanadella and the team in Seattle last week - and are excited for our partnership ahead!
4
2
86