Manifold Research (@ManifoldRG) header
Manifold Research (@ManifoldRG) profile picture

We're a mission driven R&D institute dedicated to advancing fundamental discoveries and carrying them to real-world impact. https://teapawt.org/t.co/ITVo4NcEVP

Worldwide
Joined June 2020
Photo by Manifold Research (@ManifoldRG)Photo by Manifold Research (@ManifoldRG)Photo by Manifold Research (@ManifoldRG)Photo by Manifold Research (@ManifoldRG)Photo by Manifold Research (@ManifoldRG)Photo by Manifold Research (@ManifoldRG)Photo by Manifold Research (@ManifoldRG)Photo by Manifold Research (@ManifoldRG)Photo by Manifold Research (@ManifoldRG)Photo by Manifold Research (@ManifoldRG)
Manifold Research retweeted
Fable 5.2 reaching 89.3% on OSW 2.1 is another reminder that models will soon be bottlenecked by our ability to hand-write environments hard enough for them to hill climb. We're solving that bottleneck @figbrains 🚀
Models are outpacing our ability to build training environments by hand. We explore linked tasks and objectives from continuous real work, and map agent failure modes to that signal. Read more for a preview of our next frontier dataset after RealCUA.
1
6
304
Environments built by hand can't keep pace with agents that keep getting better at long tasks. Join us on Nov 19th, where @joehabibii from @figbrains will talk about learning from real work instead: luma.com/9t33szn5 teapawt.org/figbrains/status/21205…
Models are outpacing our ability to build training environments by hand. We explore linked tasks and objectives from continuous real work, and map agent failure modes to that signal. Read more for a preview of our next frontier dataset after RealCUA.
1
1
2
62
Our question for people building agents, which failures have you seen that came from context the agent was never given?
1
12
Manifold Research retweeted
We're releasing RealCUA, the first computer-use dataset of open-ended work in evolving environments. 600+ hours (and growing!) of real multi-objective work with interleaved tasks across thousands of steps in realistic desktops. 11-hour sample & access: data.fig.inc/realcua
21
42
8
433
68,794
Really great work from the Fig team on this! We’ll be hosting @joehabibii, Head of Operations at @figbrains, for a research talk on Nov. 19 to dig into RealCUA and the challenges of learning from real, open-ended computer use. Join us to learn more, plus live Q&A: luma.com/9t33szn5 teapawt.org/figbrains/status/21183…
We're releasing RealCUA, the first computer-use dataset of open-ended work in evolving environments. 600+ hours (and growing!) of real multi-objective work with interleaved tasks across thousands of steps in realistic desktops. 11-hour sample & access: data.fig.inc/realcua
1
3
5
236
Manifold Research retweeted
The Data Research team @figbrains has been tackling open endedness head on, and has learned a lot about knowledge work’s intricacies. If you’re interested in an early preview of Fig’s new approach to open ended environments, reach out here: data.fig.inc/preview great work from @joehabibii and @dippogriff
Our latest writeup shares what hundreds of hours of real, open-ended work taught us about the learning signals missing from today’s computer-use data. We'll be sharing new datasets and environments in the coming weeks, reach out for an early preview!
1
3
6
227
Manifold Research retweeted
Our latest writeup shares what hundreds of hours of real, open-ended work taught us about the learning signals missing from today’s computer-use data. We'll be sharing new datasets and environments in the coming weeks, reach out for an early preview!
2
4
6
1,048
Manifold Research retweeted
Headed to the Asilomar Conference on Signals, Systems and Computers tomorrow! I'll be there for @figbrains and @ManifoldRG, presenting GUI-Perturbed. If you're into agents, continual learning, memory, self-improvement, or multi-agent learning, come say hi. I'd love to grab a coffee and talk! Poster TP8a2.24, Tue 1:30pm, Merrill Hall Technical report: fig.inc/blog/domain-randomiz… Paper: arxiv.org/abs/2604.14262 #Asilomar2026
2
3
4
9
812
Join the MultiNet team in Boston tomorrow!
I’m attending & presenting @arcprize summit in Boston. Will be around tomorrow & Saturday. Dm / reply to me the most cracked people you know, i want to brain drain everyone (researchers, engineers, founders investors anyone) I’ll let them brain drain me too, so it’ll be worth it
1
5
301
GPT-6 Astra topped the benchmark at 78.5%, but Opus 5.5 still solved 10 tasks Astra failed. That’s exactly the kind of jagged capability profile that aggregate scores can hide. Tomorrow at 12 PM PT / 3 PM ET, @Yangyue_Wang from @figbrains joins us to break down the results across web browsing, robotics, driving, assembly, and more. Join us for the talk + live Q&A! luma.com/74kdretn
2
4
97
A small team of brilliant researchers on the MultiNet team raced to evaluate astra and opus 5.5 on what should be fairly simple mazes! check out the research update, and let us know what you think! teapawt.org/figbrains/status/21100…
A few weeks ago, we reported that frontier models make less progress as simple 2D mazes get longer. We tested GPT-6 Astra and Claude Opus 5.5 - length doesn't matter, but they struggle with reasoning about simple obstacles without being told.
4
103
One of the most important questions in AI right now is not just how capable frontier models are on average, but where they still fail unexpectedly. Join us this coming Tuesday for a talk followed by live Q&A to dig into exactly that, across web, robotics, driving, and more!
Frontier model performance is not uniform across tasks at all, despite what benchmarks say. On October 13, @Yangyue_Wang from @figbrains joins us to unpack performance across web, driving, robotics, assembly, and other agentic tasks. Astra leads overall at 78.5%, yet lower-scoring models still solve tasks it misses. Join us live at 12 PM PT! Registration below ↓
2
2
71
Manifold Research retweeted
There are few people who are as thoughtful about the frontier of intelligence and capabilities in as comprehensive a way as @Yangyue_Wang - I definitely recommend joining next Tuesday if you’re free @ lunch
Frontier model performance is not uniform across tasks at all, despite what benchmarks say. On October 13, @Yangyue_Wang from @figbrains joins us to unpack performance across web, driving, robotics, assembly, and other agentic tasks. Astra leads overall at 78.5%, yet lower-scoring models still solve tasks it misses. Join us live at 12 PM PT! Registration below ↓
1
4
151
Frontier model performance is not uniform across tasks at all, despite what benchmarks say. On October 13, @Yangyue_Wang from @figbrains joins us to unpack performance across web, driving, robotics, assembly, and other agentic tasks. Astra leads overall at 78.5%, yet lower-scoring models still solve tasks it misses. Join us live at 12 PM PT! Registration below ↓
1
2
4
6
398