Researcher says AI writing feedback is erratic, recommends using it sparingly
Understand this story
Researcher Juri Opitz shares his experience of getting writing feedback from large language models such as ChatGPT: each time, the model gives a lengthy list of problems, and asking again in a new session brings entirely new opinions, even overturning its own previous suggestions. He therefore recommends writing the first draft entirely without AI, then using it cautiously and sparingly afterward; if more than 90% of the feedback is nitpicking, you should stop, and you should not directly copy and paste AI-rewritten content. He says feedback from human readers is still the most useful.
AI overview based on source reports · Updated 2 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIWriting with AI – Tales and Tips
Researcher Juri Opitz describes how asking ChatGPT or other LLMs for feedback on drafts yields overwhelming lists of issues that recur even after fixes, with some suggestions useful for fluency and grammar but others stripping his natural voice or distorting meaning. He advises writing the first draft without AI, using it in carefully dosed amounts, challenging conceptual critiques by asking what would change the AI's view, and never blindly pasting suggested rewrites, noting human feedback remains most useful.
Activity for this story
- Current comparable activity
- 3
- Peak comparable activity
- 10Nov 12 23:00
- Change in the past 24 hours
- -50%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.