Revision History
How to Steal ChatGPT-4, GPT-4 and other Proprietary LLMs · 6 revisions
Sizes are character counts of the article source. The signed number is the change from the previous revision.
Recent edit summaries
Detailed summaries recorded by editors. Generic maintenance summaries are omitted here; every recorded revision remains below. Dates describe the edit, not necessarily the event it covers.
- Correction: fixed the targets Anthropic attributed to DeepSeek, Moonshot and MiniMax, the description and timing of OpenAI's February 2026 memo, and reference 8's title; added sources and a link to distillation attack
Version 6 · Nov 1, 2026, 12:04 AM
- Improve internal links (2026-10-13)
Version 5 · Oct 13, 2026, 10:03 AM
- Added 6 contextual internal links
Version 4 · Jul 23, 2026, 03:01 PM