Introducing `OpenDeepResearcher` 🌎
@mattshumer_40万 位关注者
455,399 次观看
11 条评论
评论来自 X (Twitter) 上的原帖

@mattshumer_
The approach is really simple. Given a query, the AI: - performs searches, views the result pages, and extracts important info - if it wants to look deeper, it can repeat this process, with new queries - once it's done, it uses the context to generate a report That's it!
25 个赞

@mattshumer_
It's also quite asynchronous, making it very, very fast.
14 个赞

@mattshumer_
There's certainly much more that can be done here to improve this, but it's a great base to build on. It's not going to outperform OpenAI's research system, at least in this form. But it's already really good, and with some iteration, it could get there!
14 个赞

@mattshumer_
Feel free to try it (and build on it) here:
91 个赞

@CoralAINews
Coral AI is the most powerful AI for documents. See the difference yourself:
14,453 个赞

@mkurman88
Awesome! it took less time than I thought to build OS Deep Research. Congratulations!
4 个赞

@mattshumer_
o3 mini helped a lil :)
10 个赞

@chrisbe1968
Brilliant stuff! I was literally asking O3 about this earlier today, and here you are already dropping it! O3 told me to integrate Serp, which is something I had never heard of. Such a cool thing you built Matt. Thank you so much!!
5 个赞

@mattshumer_
Glad you like it!
3 个赞

@CodenameSpectra
Oh, so now we’ve got AI doing deep dives while we sit back and sip coffee? ☕✨ OpenDeepResearcher sounds like the ultimate study buddy—but let’s see if it can handle those wild conspiracy rabbit holes I love to explore. 😏
1 个赞

@ionet
smarter insights in less time sounds very valuable
1 个赞