There are no lossless transformations of natural-language text
- ID
- 13321
- Status
- summarized
- Published
- 12 Aug 2026, 7:48 AM
- Fetched
- 12 Aug 2026, 8:07 AM
- Provider
- Simon Willison
- Category
- developer-ai
- Original URL
- https://simonwillison.net/2026/Aug/11/there-are-no-lossless-transformations-of-natural-language-text/
- Source URL
- https://simonwillison.net/atom/everything/
Summary
- Score
- 7.0
- Created
- 12 Aug 2026, 8:07 AM
- Tags
- Audience
- developersvibe_codersai_agent_users
What happened
Simon Willison highlights Sophie Alpert's internal policy on acceptable AI writing use by engineers, centered on the principle that there are no lossless transformations of natural-language text—every rewrite changes meaning, and an LLM lacking your mental model will lose information. Alpert's key rule: you must stand behind every idea and sentence in your docs, and it's unacceptable to tell a reviewer 'AI wrote that, just ignore it.'
Why it matters
If your team uses LLMs to draft or polish docs, PR descriptions, or specs, adopt an explicit policy like Alpert's: the author owns every sentence and must be able to defend it. This shifts AI-assisted writing from 'generate and ship' to 'generate, verify, and take responsibility,' which prevents the subtle meaning drift that erodes trust in documentation over time.
Discussion angle
Where do you draw the line between acceptable AI assistance (grammar fixes, formatting) and unacceptable use (generating ideas or explanations you can't immediately defend)? Share concrete examples of docs that went wrong because nobody owned the output.