La gran start up china, trabajando con agentic IA.
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 been consistently inspired by classic systems research. Wide Research was directly inspired by the MapReduce paradigm introduced over 20 years ago by @JeffDean and Sanjay Ghemawat. As pioneers in large-scale distributed systems, Google encountered challenges others hadn't yet faced, and generously shared their solutions with the world.
Today, as Manus pushes the boundaries of AI agents, we're running into a new class of problems that only emerge at scale. We'll continue to share what we learn along the way.
Exhibit-099 showing that Google is the modern reincarnation of Bell Labs!
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 been consistently inspired by classic systems research. Wide Research was directly inspired by the MapReduce paradigm introduced over 20 years ago by @JeffDean and Sanjay Ghemawat. As pioneers in large-scale distributed systems, Google encountered challenges others hadn't yet faced, and generously shared their solutions with the world.
Today, as Manus pushes the boundaries of AI agents, we're running into a new class of problems that only emerge at scale. We'll continue to share what we learn along the way.
the mapreduce connection is brilliant here because it shows how ai agent coordination borrows from proven distributed systems patterns. manus essentially treats each agent like a worker node that can process research tasks independently and then merge findings, so you get massive parallelization without the coordination overhead that usually kills performance at scale.
this approach could unlock research speeds we've never seen before, especially for complex multi-faceted problems that benefit from diverse parallel exploration. meanwhile the fact that they're hitting scale problems others haven't faced yet suggests manus is operating at a fundamentally different level than current agent frameworks.
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 been consistently inspired by classic systems research. Wide Research was directly inspired by the MapReduce paradigm introduced over 20 years ago by @JeffDean and Sanjay Ghemawat. As pioneers in large-scale distributed systems, Google encountered challenges others hadn't yet faced, and generously shared their solutions with the world.
Today, as Manus pushes the boundaries of AI agents, we're running into a new class of problems that only emerge at scale. We'll continue to share what we learn along the way.
A general remark on MAS : 2 designs are interesting me today
The 2 families are distributed systems. Com protocol is critical. Human role & org based agent/MAS are generally a negative.
A/ multiple parallel general-purpose agents
Wide Research seems a good candidate here
1/n
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 been consistently inspired by classic systems research. Wide Research was directly inspired by the MapReduce paradigm introduced over 20 years ago by @JeffDean and Sanjay Ghemawat. As pioneers in large-scale distributed systems, Google encountered challenges others hadn't yet faced, and generously shared their solutions with the world.
Today, as Manus pushes the boundaries of AI agents, we're running into a new class of problems that only emerge at scale. We'll continue to share what we learn along the way.
Great stuff, parallelism was a huge speed unlock in our first iteration of BLAST (open-source browser-LLM serving engine and research project). Definitely huge potential in this direction but not 100% there yet [x.com/realcalebwin/status/19…]
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 been consistently inspired by classic systems research. Wide Research was directly inspired by the MapReduce paradigm introduced over 20 years ago by @JeffDean and Sanjay Ghemawat. As pioneers in large-scale distributed systems, Google encountered challenges others hadn't yet faced, and generously shared their solutions with the world.
Today, as Manus pushes the boundaries of AI agents, we're running into a new class of problems that only emerge at scale. We'll continue to share what we learn along the way.
Great job Peak @peakji - Manus has great engineering!
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 been consistently inspired by classic systems research. Wide Research was directly inspired by the MapReduce paradigm introduced over 20 years ago by @JeffDean and Sanjay Ghemawat. As pioneers in large-scale distributed systems, Google encountered challenges others hadn't yet faced, and generously shared their solutions with the world.
Today, as Manus pushes the boundaries of AI agents, we're running into a new class of problems that only emerge at scale. We'll continue to share what we learn along the way.
Still remember when we came up with this mapreduce idea on that flight many weeks ago. Didn’t expect it’s this hard to build😂
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 been consistently inspired by classic systems research. Wide Research was directly inspired by the MapReduce paradigm introduced over 20 years ago by @JeffDean and Sanjay Ghemawat. As pioneers in large-scale distributed systems, Google encountered challenges others hadn't yet faced, and generously shared their solutions with the world.
Today, as Manus pushes the boundaries of AI agents, we're running into a new class of problems that only emerge at scale. We'll continue to share what we learn along the way.