San Francisco Bay Area
- Tweets 795
- Following 6
- Followers 9,263
- Likes 840
Pinned Tweet
Our computer-use agent @sai_borg just beat Opus 5 and GPT-5.6 Sol on OSWorld 2.0.
Sai scored 73% on the CUA benchmark where each complex task takes a skilled human over an hour to execute.
And Sai did it at about 2/3 the cost per task of Opus and GPT 💸
The unlock is our neurosymbolic framework that pairs the exploratory power of neural networks with the logic of symbolic code, resulting in reliability and cost saving.
Read the full report: simular.ai/articles/sai-tops…
50
29
138
1,688,466
meet your #robosecretary and #SaiFleet computers
Agent demos fooled you 👎
It trips, it asks for help, and somehow you're the one copying, pasting and running the commands.
Meet your #Robosecretary. Meet your #SaiFleet.
Sai brings state-of-the-art computer use to your own computer - your apps, your OS, in a floating window that leaves your mouse alone.
Need more than one? Spin up to 100 cloud machines, each on the OS you pick, each on a different job. 100x the work, done without you.
Sai. The autonomous computer fleet at your command.
Free to start → sai.simular.ai
2
18
1,164
Agent demos fooled you 👎
It trips, it asks for help, and somehow you're the one copying, pasting and running the commands.
Meet your #Robosecretary. Meet your #SaiFleet.
Sai brings state-of-the-art computer use to your own computer - your apps, your OS, in a floating window that leaves your mouse alone.
Need more than one? Spin up to 100 cloud machines, each on the OS you pick, each on a different job. 100x the work, done without you.
Sai. The autonomous computer fleet at your command.
Free to start → sai.simular.ai
106
38
1,249
1,040,022
We told you what Sai can do. Now watch this.
Live on Product Hunt today — don't forget to UPVOTE and leave a COMMENT ❤️
🆙 producthunt.com/products/sim…
9
4
22
15,520
Our head of research @xwang_lk joined Barry Barish, Terence Tao and other scientific visionaries at the @SAIRfoundation Science x AI Summit.
Great conversations on open research, AI safety, agent market signals.
And we're cooking something 🧑🍳
3
3
14
1,535
We are throwing a party during #SFTechWeek to nerd out on all things CUA 🖥️
ChatGPT Astra just pushed computer use agents back into the spotlight. But what needs to happen before CUA become ubiquitous?
Simular is gathering folks who built agents at OpenAI and DeepMind, alongside a select group of researchers, investors and founders to debate the biggest questions in CUA today: reasoning, reliability, autonomy, economics.
Could 2027 be the year computer-use agents reach AGI? Join us to find out at SF a16z @techweek_!
partiful.com/e/YUKBbGuv0GuGM…
2
1
12
2,297
Cost / performance ratio matter; and it will matter more.
Exciting progress by @SimularAI
Our computer-use agent @sai_borg just beat Opus 5 and GPT-5.6 Sol on OSWorld 2.0.
Sai scored 73% on the CUA benchmark where each complex task takes a skilled human over an hour to execute.
And Sai did it at about 2/3 the cost per task of Opus and GPT 💸
The unlock is our neurosymbolic framework that pairs the exploratory power of neural networks with the logic of symbolic code, resulting in reliability and cost saving.
Read the full report: simular.ai/articles/sai-tops…
1
2
9
727
Simular retweeted
One pain point of computer-use agents is that they’re simply too expensive to run at scale.
Better performance matters, but so does the cost of getting there.
On OSWorld 2.0, Sai achieved the highest score among the compared models significantly lower cost than other frontier models.
For computer-use agents to move from impressive demos to everyday production, they need to be not just smart, but affordable enough to scale.
Intelligence per dollar matters.
Try us at Sai.work
1
2
10
436
Simular retweeted
Last December, our researchers built the first agent to reach human-level performance on OSWorld - Agent S, 72.6% against a human baseline of 72.36%
Today they've put us back at #1 on OSWorld 2, at less than two-thirds the cost per task
Kudos to the team! Let’s continue making AI affordable for everyone ✨
Our computer-use agent @sai_borg just beat Opus 5 and GPT-5.6 Sol on OSWorld 2.0.
Sai scored 73% on the CUA benchmark where each complex task takes a skilled human over an hour to execute.
And Sai did it at about 2/3 the cost per task of Opus and GPT 💸
The unlock is our neurosymbolic framework that pairs the exploratory power of neural networks with the logic of symbolic code, resulting in reliability and cost saving.
Read the full report: simular.ai/articles/sai-tops…
3
1
21
1,219
Simular retweeted
It's happening -- higher accuracy at two-thirds the cost. Reliability and cost-efficiency, both landing on Sai at the same time.
Full report below ⬇️
(Also: every time my wifi dropped and I ended up playing Chrome Dino, I kept thinking this game was *made* for Sai to play ;)
Our computer-use agent @sai_borg just beat Opus 5 and GPT-5.6 Sol on OSWorld 2.0.
Sai scored 73% on the CUA benchmark where each complex task takes a skilled human over an hour to execute.
And Sai did it at about 2/3 the cost per task of Opus and GPT 💸
The unlock is our neurosymbolic framework that pairs the exploratory power of neural networks with the logic of symbolic code, resulting in reliability and cost saving.
Read the full report: simular.ai/articles/sai-tops…
3
9
826
Thanks for the coverage @thenewstack
“Sai’s optimal cost-outcome tradeoff on OSWorld 2.0 is one step toward a future where we don’t need to settle for exorbitant prices to get the job done.” -- Jiachen Yang
thenewstack.io/sai-agent-osw…
1
2
8
795
Our computer-use agent @sai_borg just beat Opus 5 and GPT-5.6 Sol on OSWorld 2.0.
Sai scored 73% on the CUA benchmark where each complex task takes a skilled human over an hour to execute.
And Sai did it at about 2/3 the cost per task of Opus and GPT 💸
The unlock is our neurosymbolic framework that pairs the exploratory power of neural networks with the logic of symbolic code, resulting in reliability and cost saving.
Read the full report: simular.ai/articles/sai-tops…
50
29
138
1,688,466
Give the Sai computer agent a try - get better results out of every dollar you spend 🫰sai.work?utm_source=x&utm_me…
2
16
705
For everyone asking how we got 73% at 2/3 the cost: the full trajectories are now up on @huggingface
huggingface.co/datasets/simu…
Our computer-use agent @sai_borg just beat Opus 5 and GPT-5.6 Sol on OSWorld 2.0.
Sai scored 73% on the CUA benchmark where each complex task takes a skilled human over an hour to execute.
And Sai did it at about 2/3 the cost per task of Opus and GPT 💸
The unlock is our neurosymbolic framework that pairs the exploratory power of neural networks with the logic of symbolic code, resulting in reliability and cost saving.
Read the full report: simular.ai/articles/sai-tops…
8
4
22
2,056
Simular retweeted
Our computer-use agent @sai_borg just beat Opus 5 and GPT-5.6 Sol on OSWorld 2.0.
Sai scored 73% on the CUA benchmark where each complex task takes a skilled human over an hour to execute.
And Sai did it at about 2/3 the cost per task of Opus and GPT 💸
The unlock is our neurosymbolic framework that pairs the exploratory power of neural networks with the logic of symbolic code, resulting in reliability and cost saving.
Read the full report: simular.ai/articles/sai-tops…
50
29
138
1,688,466