top | item 45784168 (no title) predkambrij | 4 months ago CSV is a lot lighter on tokens, compared to json, so it can go further, before a LLM gets exhausted. discuss order hn newest finnborge|4 months ago If you haven't already seen the DeepSeek OCR paper [1], images can be profoundly more token-efficient encodings of information than even CSVs![1]: https://github.com/deepseek-ai/DeepSeek-OCR/blob/main/DeepSe...
finnborge|4 months ago If you haven't already seen the DeepSeek OCR paper [1], images can be profoundly more token-efficient encodings of information than even CSVs![1]: https://github.com/deepseek-ai/DeepSeek-OCR/blob/main/DeepSe...
finnborge|4 months ago
[1]: https://github.com/deepseek-ai/DeepSeek-OCR/blob/main/DeepSe...