meta-llama/AdvancedIF
Viewer
•
Updated
•
1.65k
•
350
•
8
AI & ML interests
None defined yet.
Recent Activity
yunhe2019Â
published
a
dataset
11 days ago
yunhe2019Â
updated
a
dataset
11 days ago
edwardguoÂ
authored
a
paper
12 days ago
Updating links to the correct path
2
#25 opened 24 days ago
by
betodepaola
Updating links to the correct path
2
#25 opened 24 days ago
by
betodepaola
abidlabsÂ
authored
3
papers
25 days ago
Persistent Anti-Muslim Bias in Large Language Models
Paper
•
2101.05783
•
Published
•
2
STG-MTL: Scalable Task Grouping for Multi-Task Learning Using Data Map
Paper
•
2307.03374
•
Published
•
1
Gradio: Hassle-Free Sharing and Testing of ML Models in the Wild
Paper
•
1906.02569
•
Published
•
1
Post
8213
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.
- 7 replies
multimodalartÂ
posted
an
update
about 2 months ago
Post
5987
Want to iterate on a Hugging Face Space with an LLM?
Now you can easily convert any HF entire repo (Model, Dataset or Space) to a text file and feed it to a language model!
multimodalart/repo2txt
Now you can easily convert any HF entire repo (Model, Dataset or Space) to a text file and feed it to a language model!
multimodalart/repo2txt
ericmsmithÂ
authored
10
papers
2 months ago
Multiple-Attribute Text Style Transfer
Paper
•
1811.00552
•
Published
Towards Empathetic Open-domain Conversation Models: a New Benchmark and Dataset
Paper
•
1811.00207
•
Published
•
1
Recipes for building an open-domain chatbot
Paper
•
2004.13637
•
Published
•
1
Can You Put it All Together: Evaluating Conversational Agents' Ability to Blend Skills
Paper
•
2004.08449
•
Published
•
1
Multi-Modal Open-Domain Dialogue
Paper
•
2010.01082
•
Published
ROBBIE: Robust Bias Evaluation of Large Generative Language Models
Paper
•
2311.18140
•
Published
•
1
Improving Open Language Models by Learning from Organic Interactions
Paper
•
2306.04707
•
Published
•
3
"I'm sorry to hear that": Finding New Biases in Language Models with a Holistic Descriptor Dataset
Paper
•
2205.09209
•
Published
Perturbation Augmentation for Fairer NLP
Paper
•
2205.12586
•
Published
BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage
Paper
•
2208.03188
•
Published
•
1