Yesterday, OpenAI released Deep Research, a system that browses the web to summarize content and answer questions based on the summary.The system is impressive and blew our minds when we tried it for the first time. One of the main results in the blog post is a strong improvement of performances on the General AI Assistants benchmark (GAIA), a benchmark we’ve been playing with recently as ...

The Open Deep Research tool demonstrated promising performance, achieving a score of 55.15% on the GAIA validation benchmark, compared to OpenAI's Deep Research score of 67.36% 1. Hugging Face's implementation consists of two main components: a large language model utilizing OpenAI's o1, and an open-source agentic framework 2. Notably, the team discovered that employing a coding agent yielded ...

6 天之前 · On Tuesday, Hugging Face researchers released an open source AI research agent called "Open Deep Research," created by an in-house team as a challenge 24 hours after the launch of OpenAI's...

6 天之前 · Just two days after OpenAI announced Deep Research, a new AI agent within ChatGPT that can sift through online sources for you, its open-source counterpart has already emerged. On Tuesday,...

2 天之前 · Hugging Face's Open Deep Research scored a 55.15 percent accuracy on a benchmark called General AI Assistants, while OpenAI's version scored 67.36, leaving some room for improvement.

6 天之前 · Hugging Face has shared progress on Open Deep Research, which aims to replicate the functionality of ChatGPT's new Deep Research feature. It's also going to make an open-source Operator rival.

5 天之前 · In another remarkable demonstration of the incredible speed at which the AI market is moving, a team at Hugging Face has replicated Deep Research, the OpenAI agent product which was released...

A group of developers at AI dev platform Hugging Face, including Thomas Wolf, the company’s co-founder and chief scientist, say they’ve built an “open” version of OpenAI’s deep research ...

5 天之前 · The Hugging Face system achieved a 55.15 percent success rate on the GAIA benchmark, which tests AI systems on complex, multi-step tasks. This places their performance between Microsoft's Magentic-One (around 46 percent) and OpenAI Deep Research (approximately 67 percent).

4 天之前 · The launch of Open Deep Research by Hugging Face is an exciting development in the field of AI research. As an open-source research agent, it is designed to browse the internet and compile detailed research reports, significantly enhancing the capabilities of researchers worldwide. This new tool builds upon existing AI models, integrating an ...