# Analysis of 22 GB Codex conversation data finds 71% of storage is screenshots > Source: > Published: 2026-09-08 20:05:38+00:00 # Analysis of 22 GB Codex conversation data finds 71% of storage is screenshots A developer analyzed their complete Codex conversation history totaling 22.83 GB across 1,231 files and found that embedded images account for 71% of the storage footprint. The byte-level analysis, conducted September 2-3, 2026, hashed every image with SHA-256 and compared duplicates within and across conversations. The findings raise questions about what OpenAI does with user-submitted image data in coding agent conversations. ## Topics ## Sources - Press [Read article](https://mint.dzgapp.com/build-journey/what-22-gb-of-agent-conversations-is-made-of/) ## Go deeper This intelligence is sourced automatically from public sources across the web and synthesised by the Prefactor AI pipeline. Stories are reviewed before publication.