Everything Aymeric (Emmerich) said on any show that made the record, most notable first. Each card names its show and opens the statement there.
Roucher: DeepSeek-R1 ranks slightly below OpenAI o1 on smolagents tasks
“I tried R one, but R one is a bit under O one with small agents. And I think this is also a matter of formatting. Like sometimes the model struggles to just output them, the code snippets in the correct way that we expect.”
Roucher: AI agents will reach a 90% GAIA score by 2026
“So I think if we solve Gaia, that's like 90% score. That means mostly we double productivity of every task done in front of a computer. And if you take the trend line of the scores so far this should be crossed in 2026 or something.”
Roucher: Code agents perform better than JSON tool calling
“I found this is highly suboptimal, and that's why I've designed the other code agent, which is really like the core opinion in the library is that code agents work better.”
Roucher: Effective web browsing agents must use vision and direct GUI inputs
“Web browsing is designed for humans. So that means it's really visual. And so a web browsing agent, a good one, should use, in my opinion a vision model and perform actions with point and click and keyboard, basically.”
Roucher: Visual AI models will likely jump the reasoning S-curve in 2025
“But as with text agents, we've really found that we made a jump on the S curve with reasoning models. I think it's going to be the same with the next visual models, basically better base models just allow you to jump over this S curve. And probably I think it'…”
Roucher says Hugging Face plans to heavily prioritize GUI agents
“That's the next step for us at Hugging Face. We're going to push really hard on building GUI agents, so basically agents that can use any GUI.”
Roucher: Hugging Face will fine-tune DeepSeek-R1 for agent workflows
“Looking forward to this, and for instance we're going to fine-tune R-One on agentic stuff, so we'll, we'll get really good powerhouse models soon.”
Roucher: smolagents core agents.py file is under 1,000 lines
“The main file in it, the agents.py file that we have at the core of the library is under the 1000 lines of code.”