Show HN: Staying up to date with the overwhelming amount of AI research
firebender.aiHey HN!
There’s been an explosion of AI research papers being published (see arxiv growth https://www.researchgate.net/figure/Number-of-papers-publish...). As AI/ML founders it was difficult to find papers that actually aligned with our goals and often skimmed through many unrelated papers. It would be nice to have a way to sift through the noise.
This last week, we built https://firebender.ai/. It takes in a description of what you’re trying to accomplish, and on a weekly basis, delivers TLDRs of recent AI papers you'd most likely want to dive into. Here’s a sample description and curated list (https://firebender.ai/sample). It works by indexing new Arxiv papers (LDA, elasticsearch), then GPT-4 generates queries, summarizes results, and does the final round of filtering.
Sign up at https://firebender.ai/ and look out for an email on Friday! Any and all feedback is appreciated. The sample paper descriptions could be more concise. Maybe Chain of density (COD) can help here https://arxiv.org/pdf/2309.04269.pdf ?