The interest in building open agents is just wild!
@aymericroucher
-
Smolagents gains significant traction with open replication of Deep Research
By
–
Wow, smolagents got 3,000+ GitHub stars over the last week!
Our open replication of Deep Research drew significant traction.
Let's keep pushing -
Performance evaluation of reasoning models on agentic data science tasks
By
–
Adyen's new Data Agents Benchmark shows that DeepSeek-R1 struggles on data science task! How well do reasoning models perform on agentic tasks? Until now, all indicators seemed to show that they worked really well. On our recent reproduction of Deep Search, OpenAI's o1 was
-
Bypassing API queues by duplicating AI workspaces
By
–
The demo is flooded under requests at the moment. To skip the queue, you can duplicate the space under your own Hub account; but it will still require providing your own API keys as space Secret variables!
-
Comparative performance analysis of small vs frontier AI models
By
–
It's really fast, but performs less well than o1 and gpt-4o. I guess models too small don't cut it yet for hard tasks.
-
Benchmarking progress in AI agent frameworks: From transformers.agents to smolagents
By
–
My previous submission, months ago with transformers.agents on GPT-4o scored a bit over 40% ont the same benchmark. We've been a long way since then with smolagents!
-
Hugging Face Releases Open Deep Research Agent Framework
By
–
Our blog post: https://
huggingface.co/blog/open-deep
-research
… Code here: https://
github.com/huggingface/sm
olagents/tree/main/examples/open_deep_research
… -
Hugging Face releases open-Deep-Research to replicate proprietary AI capabilities
By
–
Introducing open-Deep-Research by @huggingface ! Deep Research from @OpenAI is really good… But it's closed, as usual. > So with a team of cracked colleagues, we set ourselves a 24hours deadline to replicate and open-source Deep Research! We built open-Deep-Research,
-
Debating the transparency and values of AI vs. human-curated knowledge
By
–
Pick the best global source of truth for humanity:
– Wikipedia, transparently crowd-sourced from the knowledge of thousands of contributors
– ChatGPT, has an opaque set of values ~chosen by @sama under incentives from the richest/more powerful influence group I would fear a -
Agentic Performance and GAIA Benchmark Analysis
By
–
With an agentic setup, quite obvious that scores would increase! The comparison against other agents on the GAIA benchmark is more interesting.