News for hackers. Stuff that matters.
Re:Ingesting PDFs and why Gemini 2.0 changes everything by serjester on Wednesday February 05, 2025 @06:55PM (#42957126)
That assumes that you're able to find a model that can match Gemini's performance - I haven't come across anything that comes close (although hopefully that changes).
Re:Ingesting PDFs and why Gemini 2.0 changes everything by jeswin on Thursday February 06, 2025 @09:08AM (#42962443)
Nice article, mirrors my experience. Last year (around when multimodal 3.5 Sonnet launched), I had run a sizeable number of PDFs through it. Accuracy was remarkably high (99%-ish), whereas GPT was just unusable for this purpose.