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 🚀
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…
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
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
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
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!
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
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
Benchmarks hide serious gaps in model performance.
Last Friday, we learned the extent of this in "How Good Are Frontier Models, Really?"
@Yangyue_Wang from @figbrains dug into why model capabilities remain so jagged even as benchmark scores keep climbing.
Missed it? No problem! Watch the full talk here:
youtube.com/watch?v=59WZlXqH…
Want to dig deeper, collaborate, or keep following this work?
Email us at [email protected]
Or join the Manifold community on Discord!
discord.gg/rd9yvfDNw
1
27
For more talks at the edge of science and technology research, check out our Luma Calendar!
luma.com/manifold
11
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
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
How good are frontier models, really?
This Friday, @Yangyue_Wang from @figbrains joins us to unpack where today’s best models still fail across web, robotics, driving, assembly, and more.
Join us live ↓
luma.com/74kdretn
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 ↓
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 ↓
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 ↓
Register here:
luma.com/74kdretn
28









