Hacker News: anirudhb99https://news.ycombinator.com/user?id=anirudhb99Hacker News RSShttps://hnrss.org/hnrss v2.1.1Sat, 30 May 2026 03:50:21 +0000<![CDATA[New comment by anirudhb99 in "Ingesting PDFs and why Gemini 2.0 changes everything"]]>member of the gemini team here -- personally, i'd recommend directly using gemini vs the document understanding services for OCR & general docs understanding tasks. From our internal evals gemini is now stronger than these solutions and is only going to get much better (higher precision, lower hallucination rates) from here.

]]>Wed, 05 Feb 2025 23:34:12 +0000https://news.ycombinator.com/item?id=42956923anirudhb99https://news.ycombinator.com/item?id=42956923https://news.ycombinator.com/item?id=42956923<![CDATA[New comment by anirudhb99 in "Ingesting PDFs and why Gemini 2.0 changes everything"]]>thanks a ton for all the amazing feedback on this thread! if

(a) you have document understanding use cases that you'd like to use gemini for (the more aspirational the better) and/or

(b) there are loss cases for which gemini doesn't work well today,

please feel free to email anirudhbaddepu@google.com and we'd love to help get your use case working & improve quality for our next series of model updates!

]]>Wed, 05 Feb 2025 19:55:28 +0000https://news.ycombinator.com/item?id=42954189anirudhb99https://news.ycombinator.com/item?id=42954189https://news.ycombinator.com/item?id=42954189<![CDATA[New comment by anirudhb99 in "Ingesting PDFs and why Gemini 2.0 changes everything"]]>(from the gemini team) we're working on it! semantic chunking & extraction will definitely be possible in the coming months.

]]>Wed, 05 Feb 2025 19:49:47 +0000https://news.ycombinator.com/item?id=42954096anirudhb99https://news.ycombinator.com/item?id=42954096https://news.ycombinator.com/item?id=42954096