Sabitlenmiş Tweet
Duckworth
158 posts
Duckworth
@Duckworth65
here for the tek || Big Fan of Superpowers Ai
Katılım Ocak 2025
113 Takip Edilen122 Takipçiler
@RohanArun @OpenAI Nice job Rohan @RohanArun
Is this a contest or all they have to do is follow the rules and pray for luck?
English
🚨Striking new benchmarks for long-running computer-use beating @OpenAI with their own models!
3 random people who follow me, comment, and quote repost the tweet below wins $100 in 48 hours!
X will be removing communities soon so follow me anyway to stay tuned for more launches and promos.
Rohan Arun@RohanArun
🚨Striking new benchmarks for long-running computer-use beating @OpenAI with their own models! ❌ Codex Computer Use: 21 minutes and fails Computer-use-kit + our native Mac app: ✅ @Alibaba_Qwen Qwen 3.6 Plus: 5m 27s success $0.325/$1.95👀 ✅ @deepseek_ai V4: 3m 34s success. $1.74/$3.48 👀 ✅ GPT 5.4: 2m 41s success $2.50/$15 ✅ GPT 5.5 Pro: 4m 34s success $30/$180 Task: clip the latest video from our Youtube channel and post it to Tiktok. We just published a new realtime upgrade to optimize our computer-use-kit runtimes(API launching soon). We finally solved reliable computer-use for long-running tasks, and we use benchmarks to rigorously test and report which use-cases will work best on which models. The cool thing is our benchmarks clearly show an upper limit to tasks, so you can use open models to run them!
English
@thsottiaux Fan out the windows to automate them in parallel in the background
x.com/Viewforge/stat…
Rohan Arun@RohanArun
This is super cool! I recommend fanning out the windows. Rather than awkwardly watching windows side-by-side, you can fan them out and automate them in parallel in the background while you keep working... This design is a little bit better, but we're optimizing it to only display the actively automated windows.
English
Duckworth retweetledi
For VERY INTERESTING reasons, @nvidia Nemotron Super 3 outperforms GPT 5.4 in long-running computer-use..
This trick applies more open models, and it's a consequence of how the models fundamentally work so this will keep happening.
English
Duckworth retweetledi
Never gamble without us again. Launching tomorrow.
English
English
Duckworth retweetledi
Doing another $20k giveaway - 20x $1,000.
To enter:
- Like, RT & tag 3 friends on the QUOTED TWEET (!!)
- Follow @fairgambling ,@sebviceversa & myself
Winners drawn in 24 hours.
FairGambling@fairgambling
Never gamble without us again. Launching tomorrow.
English
Great job!
JAGO (Flow Arc) 🐉@rerunjago
SuperPowersMac automating iPhone using custom Power command. Watch how I created a custom "open Chrome" Power in Power Studio, connected the iPhone via iPhone Mirroring, and SuperPowersMac executed the command autonomously on the iPhone. This demonstrates the full workflow: install the client, create a Power, and automate the connected device. @rohanarun
English
English
@gdb I can make it faster and more robust. Put me in the game coach 🫡
Check out our side-by-side benchmark below beating Codex with it's own model.
x.com/Viewforge/stat…
Rohan Arun@RohanArun
Side-by-side benchmarks beating @OpenAI Codex computer-use using their own models! 👀 Round 1: Clip a youtube video from our channel and upload it to Tiktok ✅ GetSupers.com + GPT 5.4 + our computer-use-kit: Successfully uploads a clip with subtitles and hook after 16 minutes (and works in iPhone/Android) ❌ Codex + GPT 5.4: Gets the clip format wrong 3 times, asks for human intervention, and finally fails after 21 minutes. Codex actually does try iPhone mirroring and Capcut, which is very cool and kudos to the team, but it ultimately fails after burning credits. @sama this is not easy to do, but happy to help you guys integrate our computer-use-kit. 😀 I co-founded the first startup approved by openAI to sell GPT3 for automation in August 2021(Cheatlayer) months before adept.ai so I've been working on this for a long time. We automate Mac/Windows/Linux/Chrome/Android/Iphone + @daytonaio sandboxes and @browserbase cloud browsers out of the box. We also just shipped automated benchmarks, so we're building the most comprehensive computer-use benchmark for long-running tasks on the planet.
English
codex is becoming the universal app for developers:
Peter Yang@petergyang
Went from having multiple terminals open to just two apps open :)
English
English
@evaedxn Just sold my last AI marketing startup, and now we're competing directly with OpenAI to unlock AI for consumers through reliable computer-use.
This automates the apps they use daily so it unlocks AI for most non-technical people(most of the world).
x.com/Viewforge/stat…
Rohan Arun@RohanArun
Side-by-side benchmarks beating @OpenAI Codex computer-use using their own models! 👀 Round 1: Clip a youtube video from our channel and upload it to Tiktok ✅ GetSupers.com + GPT 5.4 + our computer-use-kit: Successfully uploads a clip with subtitles and hook after 16 minutes (and works in iPhone/Android) ❌ Codex + GPT 5.4: Gets the clip format wrong 3 times, asks for human intervention, and finally fails after 21 minutes. Codex actually does try iPhone mirroring and Capcut, which is very cool and kudos to the team, but it ultimately fails after burning credits. @sama this is not easy to do, but happy to help you guys integrate our computer-use-kit. 😀 I co-founded the first startup approved by openAI to sell GPT3 for automation in August 2021(Cheatlayer) months before adept.ai so I've been working on this for a long time. We automate Mac/Windows/Linux/Chrome/Android/Iphone + @daytonaio sandboxes and @browserbase cloud browsers out of the box. We also just shipped automated benchmarks, so we're building the most comprehensive computer-use benchmark for long-running tasks on the planet.
English
@rohanarun Woahhhhh 🥹🔥
Finally I won after so many attempts, @rohanarun I can’t dm cause you don’t follow me boss
English
The winner is @Duckworth65!
Please DM me to claim the prize and stay tuned for the next promos!
Rohan Arun@RohanArun
Introducing automated benchmarks for long-running computer-use agents, automatically generating the most comprehensive computer-use benchmark on the planet. Using our computer-use kit, @NousResearch Hermes 405B instruct free is performing better than @OpenAI GPT 5.4.... 👀
English
English
@thsottiaux I can make it faster and more robust. Put me in the game coach 🫡 Check out our side-by-side benchmark below beating Codex with it's own model.
x.com/Viewforge/stat…
Rohan Arun@RohanArun
Side-by-side benchmarks beating @OpenAI Codex computer-use using their own models! 👀 Round 1: Clip a youtube video from our channel and upload it to Tiktok ✅ GetSupers.com + GPT 5.4 + our computer-use-kit: Successfully uploads a clip with subtitles and hook after 16 minutes (and works in iPhone/Android) ❌ Codex + GPT 5.4: Gets the clip format wrong 3 times, asks for human intervention, and finally fails after 21 minutes. Codex actually does try iPhone mirroring and Capcut, which is very cool and kudos to the team, but it ultimately fails after burning credits. @sama this is not easy to do, but happy to help you guys integrate our computer-use-kit. 😀 I co-founded the first startup approved by openAI to sell GPT3 for automation in August 2021(Cheatlayer) months before adept.ai so I've been working on this for a long time. We automate Mac/Windows/Linux/Chrome/Android/Iphone + @daytonaio sandboxes and @browserbase cloud browsers out of the box. We also just shipped automated benchmarks, so we're building the most comprehensive computer-use benchmark for long-running tasks on the planet.
English
Side-by-side benchmarks beating @OpenAI Codex computer-use using their own models! 👀
Round 1: Clip a youtube video from our channel and upload it to Tiktok
✅ GetSupers.com + GPT 5.4 + our computer-use-kit: Successfully uploads a clip with subtitles and hook after 16 minutes (and works in iPhone/Android)
❌ Codex + GPT 5.4: Gets the clip format wrong 3 times, asks for human intervention, and finally fails after 21 minutes.
Codex actually does try iPhone mirroring and Capcut, which is very cool and kudos to the team, but it ultimately fails after burning credits.
@sama this is not easy to do, but happy to help you guys integrate our computer-use-kit. 😀
I co-founded the first startup approved by openAI to sell GPT3 for automation in August 2021(Cheatlayer) months before adept.ai so I've been working on this for a long time.
We automate Mac/Windows/Linux/Chrome/Android/Iphone + @daytonaio sandboxes and @browserbase cloud browsers out of the box.
We also just shipped automated benchmarks, so we're building the most comprehensive computer-use benchmark for long-running tasks on the planet.
English
Woah! @rohanarun just dropped automated benchmarks for long-running computer-use AI agents — and the open-source Hermes 3.1 405B is outperforming GPT-5.4 on real GUI tasks like posting to Twitter and TikTok. This is next-level agent testing. 🔥
Rohan Arun@RohanArun
Introducing automated benchmarks for long-running computer-use agents, automatically generating the most comprehensive computer-use benchmark on the planet. Using our computer-use kit, @NousResearch Hermes 405B instruct free is performing better than @OpenAI GPT 5.4.... 👀
English
@rohanarun just dropped automated benchmarks for long-running computer-use AI agents — and the open-source Hermes 3.1 405B is outperforming GPT-5.4 on real GUI tasks like posting to Twitter and TikTok. This is next-level agent testing. 🔥
Rohan Arun@RohanArun
Introducing automated benchmarks for long-running computer-use agents, automatically generating the most comprehensive computer-use benchmark on the planet. Using our computer-use kit, @NousResearch Hermes 405B instruct free is performing better than @OpenAI GPT 5.4.... 👀
English