Re:Show HN: Why write code if the LLM can just do the thing?...
by predkambrij on Saturday November 01, 2025 @02:41PM
(#45784168)
CSV is a lot lighter on tokens, compared to json, so it can go further, before a LLM gets exhausted.
[ Parent
| on HN ]
Re:Show HN: Why write code if the LLM can just do the thing?...
by finnborge on Saturday November 01, 2025 @03:36PM
(#45784624)
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...