/image%2F0535633%2F20240125%2Fob_e59049_oig-8hjrzz8oexhwvlgsi.jpg)
Why LLMs still have problems with OCR
Document ingestion and the launch of Gemini 2.0 caused a lot of buzz this week. As a team building in this space, this is something we researched thoroughly. Here’s our take: ingestion is a multistep pipeline, and maintaining confidence from LLM nondeterministic outputs over millions of pages is a problem. Comments URL: https://news.ycombinator.com/item?id=42966958 Points: 94 # Comments: 72
Document ingestion and the launch of Gemini 2.0 caused a lot of buzz this week. As a team building in this space, this is something we researched thoroughly. Here’s our take: ingestion is a multistep pipeline, and maintaining confidence from LLM nondeterministic outputs over millions of pages is a problem.
Comments URL: https://news.ycombinator.com/item?id=42966958
Points: 94
# Comments: 72
