abidlabs/call-for-tasks
1.28 kB
Abubakar Abid PRO
👁 Image
P0ll0B's profile picture👁 Image
eduagarcia's profile picture👁 Image
Gabriel's profile picture
P0ll0B's profile picture👁 Image
eduagarcia's profile picture👁 Image
Gabriel's profile picture
·
AI & ML interests
self-supervised learning, applications to medicine & biology, interpretation, reproducibility
Recent Activity
new activity about 18 hours ago
black-forest-labs/FLUX.1-schnell:Fix RuntimeError on inference: pin diffusers + transformers to a compatible pair liked a model about 20 hours ago
zai-org/GLM-5.2 upvoted a changelog 2 days ago
Agent Traces on the HubOrganizations
👁 Hugging Face's profile picture
👁 Org for Gradio Tests's profile picture
👁 MIT-15.561-2022's profile picture
👁 Spaces-explorers's profile picture
👁 Gradio's profile picture
👁 Gradio Client Demos's profile picture
👁 Templates's profile picture
👁 CVPR Demo Track's profile picture
👁 AUBMC AIM's profile picture
👁 Stanford CS236g 2022's profile picture
👁 pytorch's profile picture
👁 Test Demo's profile picture
👁 Sorbonne Université's profile picture
👁 HF Course Demos's profile picture
👁 Gradio-Themes-Party's profile picture
👁 Univ-Pitts-ECE-1395's profile picture
👁 Yale CPSC 577's profile picture
👁 Gradio-Blocks-Party's profile picture
👁 Evaluate Metric's profile picture
👁 HuggingFaceM4's profile picture
👁 Workshop June 13 Classroom's profile picture
👁 Hugging Face University 2022's profile picture
👁 Fatima Fellowship's profile picture
👁 Hugging Face H4's profile picture
👁 Hugging Face OSS Metrics's profile picture
👁 Gradio PR Deploys's profile picture
👁 Gradio Test Deploy's profile picture
👁 Blog-explorers's profile picture
👁 UniverseTBD's profile picture
👁 Hacktoberfest 2023's profile picture
👁 ICML2023's profile picture
👁 Gradio Discord Bots's profile picture
👁 Gradio Templates's profile picture
👁 Gradio Community's profile picture
👁 Social Post Explorers's profile picture
👁 community-science-team's profile picture
👁 smolagents's profile picture
👁 FastRTC's profile picture
👁 Inference Endpoints Images's profile picture
👁 Agents-MCP-Hackathon's profile picture
👁 Trackio's profile picture
👁 Old Gradio Test Spaces's profile picture
👁 TestPrivateDefault's profile picture
👁 MCP-1st-Birthday's profile picture
👁 Hugging Face Biology Research's profile picture
👁 Trackio Tests's profile picture
👁 Gradio Hackathon Allstars's profile picture
👁 Hugging Face Applications's profile picture
👁 ML intern explorers's profile picture
👁 Gemma Challenge's profile picture
👁 Org for Gradio Tests's profile picture
👁 MIT-15.561-2022's profile picture
👁 Spaces-explorers's profile picture
👁 Gradio's profile picture
👁 Gradio Client Demos's profile picture
👁 Templates's profile picture
👁 CVPR Demo Track's profile picture
👁 AUBMC AIM's profile picture
👁 Stanford CS236g 2022's profile picture
👁 pytorch's profile picture
👁 Test Demo's profile picture
👁 Sorbonne Université's profile picture
👁 HF Course Demos's profile picture
👁 Gradio-Themes-Party's profile picture
👁 Univ-Pitts-ECE-1395's profile picture
👁 Yale CPSC 577's profile picture
👁 Gradio-Blocks-Party's profile picture
👁 Evaluate Metric's profile picture
👁 HuggingFaceM4's profile picture
👁 Workshop June 13 Classroom's profile picture
👁 Hugging Face University 2022's profile picture
👁 Fatima Fellowship's profile picture
👁 Hugging Face H4's profile picture
👁 Hugging Face OSS Metrics's profile picture
👁 Gradio PR Deploys's profile picture
👁 Gradio Test Deploy's profile picture
👁 Blog-explorers's profile picture
👁 UniverseTBD's profile picture
👁 Hacktoberfest 2023's profile picture
👁 ICML2023's profile picture
👁 Gradio Discord Bots's profile picture
👁 Gradio Templates's profile picture
👁 Gradio Community's profile picture
👁 Social Post Explorers's profile picture
👁 community-science-team's profile picture
👁 smolagents's profile picture
👁 FastRTC's profile picture
👁 Inference Endpoints Images's profile picture
👁 Agents-MCP-Hackathon's profile picture
👁 Trackio's profile picture
👁 Old Gradio Test Spaces's profile picture
👁 TestPrivateDefault's profile picture
👁 MCP-1st-Birthday's profile picture
👁 Hugging Face Biology Research's profile picture
👁 Trackio Tests's profile picture
👁 Gradio Hackathon Allstars's profile picture
👁 Hugging Face Applications's profile picture
👁 ML intern explorers's profile picture
👁 Gemma Challenge's profile picture
Posts 20
Why I think local, open-source models will eventually win.
The most useful AI applications are moving toward multi-turn agentic behavior: systems that take hundreds or even thousands of iterative steps to complete a task, e.g. Claude Code, computer-control agents that click, type, and test repeatedly.
In these cases, the power of the model is not how smart it is per token, but in how quickly it can interact with its environment and tools across many steps. In that regime, model quality becomes secondary to latency.
An open-source model that can call tools quickly, check that the right thing was clicked, or verify that a code change actually passes tests can easily outperform a slightly “smarter” closed model that has to make remote API calls for every move.
Eventually, the balance tips: it becomes impractical for an agent to rely on remote inference for every micro-action. Just as no one would tolerate a keyboard that required a network request per keystroke, users won’t accept agent workflows bottlenecked by latency. All devices will ship with local, open-source models that are “good enough” and the expectation will shift toward everything running locally. It’ll happen sooner than most people think.
The most useful AI applications are moving toward multi-turn agentic behavior: systems that take hundreds or even thousands of iterative steps to complete a task, e.g. Claude Code, computer-control agents that click, type, and test repeatedly.
In these cases, the power of the model is not how smart it is per token, but in how quickly it can interact with its environment and tools across many steps. In that regime, model quality becomes secondary to latency.
An open-source model that can call tools quickly, check that the right thing was clicked, or verify that a code change actually passes tests can easily outperform a slightly “smarter” closed model that has to make remote API calls for every move.
Eventually, the balance tips: it becomes impractical for an agent to rely on remote inference for every micro-action. Just as no one would tolerate a keyboard that required a network request per keystroke, users won’t accept agent workflows bottlenecked by latency. All devices will ship with local, open-source models that are “good enough” and the expectation will shift toward everything running locally. It’ll happen sooner than most people think.
