9-Volt Fan's picture

9-Volt Fan

9voltfan2009

·

AI & ML interests

None yet

Recent Activity

liked a Space about 3 hours ago

nari-labs/Dia-1.6B

reacted to shekkizh's post with ❤️ about 6 hours ago

Think AGI is just around the corner? Not so fast. When OpenAI released its Computer-Using Agent (CUA) API, I happened to be playing Wordle 🧩 and thought, why not see how the model handles it? Spoiler: Wordle turned out to be a surprisingly effective benchmark. So Romain Cosentino Ph.D. and I dug in and analyzed the results of several hundred runs. 🔑 Takeaways 1️⃣ Even the best computer-using models struggle with simple, context-dependent tasks. 2️⃣ Visual perception and reasoning remain major hurdles for multimodal agents. 3️⃣ Real-world use cases reveal significant gaps between hype and reality. Perception accuracy drops to near zero by the last turn 📉 🔗 Read our arxiv article for more details https://www.arxiv.org/abs/2504.15434

reacted to shekkizh's post with 👍 about 6 hours ago

Think AGI is just around the corner? Not so fast. When OpenAI released its Computer-Using Agent (CUA) API, I happened to be playing Wordle 🧩 and thought, why not see how the model handles it? Spoiler: Wordle turned out to be a surprisingly effective benchmark. So Romain Cosentino Ph.D. and I dug in and analyzed the results of several hundred runs. 🔑 Takeaways 1️⃣ Even the best computer-using models struggle with simple, context-dependent tasks. 2️⃣ Visual perception and reasoning remain major hurdles for multimodal agents. 3️⃣ Real-world use cases reveal significant gaps between hype and reality. Perception accuracy drops to near zero by the last turn 📉 🔗 Read our arxiv article for more details https://www.arxiv.org/abs/2504.15434

View all activity

Organizations

models 2

9voltfan2009/DorkDiaries-RVC

Updated 16 days ago

9voltfan2009/WarioWare-RVC

Updated Nov 20, 2023 • 3

datasets

None public yet