Research topic · work in progress · about
"AI" Reads Human: Human Language Encoding at Machine Speed and the Energy Cost
Software agents pass data to each other in formats made for people to read, such as JSON, YAML, Markdown, XML and CSV. This topic names the extra work that causes, defines it with units, and measures two parts of it on a reproducible corpus: parse time and token count. Energy is not yet measured.
In plain words
- Computers and people often use the same written format. That format is easy for people to read, but the computer has to do extra work to read it back.
- On our test data, the same records took about 8 times longer to read as JSON (Python's built-in reader), and about 735 times longer as YAML, than as a plain fixed binary layout. Read by an AI model, YAML used about 2.2 times as many tokens as CSV.
- We have measured time and token counts only. We have not yet measured energy, so this page makes no claim about how many joules are saved.