Designing computer-use agents @yutori_ai
- Tweets 7,477
- Following 997
- Followers 1,709
- Likes 32,300
Pinned Tweet
Excited to have my Mousepower talk live on @aiDotEngineer's YT channel (link below), but I have retrospective thoughts on this topic & here is what I'd change if I gave the talk again today:
1. Thesis wasn't stated simply enough: value of agents is limited by our ability to measure them, otherwise we can't justify the ROI of their token cost
2. Need an explicit connection to the discourse on verifiable domains, which we need not be limited to today's set as understanding customer mental models unlocks new ways to verify value (e.g. horsepower)
3. After reading a nice post by @jon_stokes on verifiable domains, I'm specifically interested in the n-order F/X of their "optimization pressure"
4. Also rambled too much, perhaps a function of the topic being too underbaked... will see if GPT voice can coach me for next time
Follow up incoming (someday).
Excited to speak again at @aiDotEngineer World's Fair! This year I'm presenting "mousepower": on how agents break our measurement frameworks, which weren't built for systems that output tirelessly in parallel. If execution is now cheap & judgment is the new bottleneck, how do we measure value at the speed of compute?
1
2
6
2,919
I once gave a talk called The Bitter Layout, inspired by this same book, arguing that until models commoditize, interface design should primarily focus on absorbing the latest capabilities. Well, it may soon be time to dust off the “chat isn’t the future of AI UX” t-shirt...
No one is going to care about the underlying AI model soon, especially for consumers. The models are already good enough for most of what people need. What consumers want is for AI to be useful, easy to access, and FREE or bundled into something they already pay for.
Clayton Christensen and Michael Raynor described this shift in the figure below which is in their book The Innovator’s Solution. When a product isn’t good enough, performance wins. Once it is good enough, convenience and cost start to matter more.
The winning question may soon be less Whose model is best? and more Why would I pay separately for this?
1
245
the right way to use model capabilities is not to ship 10x more features to prod
it's to spend more time understanding your users, trying experiments, building prototypes, learning about things you don't understand so that you can ship things that actually work
275
614
8,221
384,386
Maximillian Piras retweeted
Every platform needs to service the developer community better than the hot launch period.
Apple’s success comes from courting all types of developers for years on end, not the top 7 icons recognizable by the X community at any moment.
Are normal people empowered to build for this platform? If not, this becomes another plugin directory with the same companies at the top.
Opening access for developers to build Muse connectors. You bring the API -- Muse brings the agent, the browser, and the context of what the person actually wants. People reach your service just by asking for it, and their agent takes it from there.
New connectors are live today. Come build with us. muse.ai/platform
5
1
18
5,884
Or we can just read the manual: docs.typesafe.ai/model-jagge…
I am going to build a jev app to classify which of all these demos are actually a good use case for jev.
2
380
I am going to build a jev app to classify which of all these demos are actually a good use case for jev.
3
11
1,451
Been sitting on an idea for a browser extension for a bit. Finally had time today to sit down & try to build it. Got a working version in <10 min 😳
Malleable software is certainly here.
1
1
552
Two of the companies I’m most fascinated by in the Ai space today are @aiunderwriting & @simile_ai. They focus on problems that to me weren’t immediately obvious, but in hindsight seem so useful.
Both of which I was put on to via @latentspacepod, per usual.
1
151
Maximillian Piras retweeted
Navigator n2 driving an iPhone (via mirroring) to compare prices across Uber and Lyft
1
2
10
4,672
Frontier models: $13 to $40+ per task on OSWorld 2.0.
Yutori's Navigator n2: $1.46. 🎯
Served on Crusoe by a 14-person team with no inference stack of their own.
"Because Crusoe maximizes throughput, every token costs less." - @DhruvBatra_, @yutori_ai
↪ crusoe.ai/resources/customer…
4
6
25
2,792
What are some Mac-specific tasks you'd like to see demoed? I'm in the midst of experimenting w/ n2 CUA local & welcome any ideas.
n2 can drive your Mac!
Use Yutori's MCP to run our latest Navigator computer-use model locally.
Here it is in iMovie, cutting a quick video recap from our recent event.
1
3
643
Maximillian Piras retweeted
n2 can drive your Mac!
Use Yutori's MCP to run our latest Navigator computer-use model locally.
Here it is in iMovie, cutting a quick video recap from our recent event.
1
5
28
4,163
Entire timeline is marveling over a page-turn animation.
It set the tone for differentiation from other foldables.
Details really do matter.
115
Maximillian Piras retweeted
Horsepower helped us communicate the value add of a new technology (steam engines) relative to a familiar status quo (workhorses).
What's that unit of measurement for agents?
Excited to have my Mousepower talk live on @aiDotEngineer's YT channel (link below), but I have retrospective thoughts on this topic & here is what I'd change if I gave the talk again today:
1. Thesis wasn't stated simply enough: value of agents is limited by our ability to measure them, otherwise we can't justify the ROI of their token cost
2. Need an explicit connection to the discourse on verifiable domains, which we need not be limited to today's set as understanding customer mental models unlocks new ways to verify value (e.g. horsepower)
3. After reading a nice post by @jon_stokes on verifiable domains, I'm specifically interested in the n-order F/X of their "optimization pressure"
4. Also rambled too much, perhaps a function of the topic being too underbaked... will see if GPT voice can coach me for next time
Follow up incoming (someday).
1
1
5
1,022