Comment by SkiFreeWin3 12 days ago [dead] 3 comments SkiFreeWin3 Reply ar_turnbull 12 days ago Interesting. I made a skill for my Claude agent based on Wikipedia’s list of AI writing tells. /remove-ai-writingIt works reasonably well (better if you run it a few times), but still benefits from a final pass by a human editor IMO.https://github.com/arturnbull/remove-ai-writing jedbrooke 12 days ago Honestly, I get pretty good improvement from just adding a “Emoji are forbidden” and a small list of banned words and phrases (the usual suspects like “it’s not just x, it’s y” etc) flexagoon 12 days ago Banning bold font and saying to avoid lists and tables as much as possible is an immediate massive improvement to LLM output quality
ar_turnbull 12 days ago Interesting. I made a skill for my Claude agent based on Wikipedia’s list of AI writing tells. /remove-ai-writingIt works reasonably well (better if you run it a few times), but still benefits from a final pass by a human editor IMO.https://github.com/arturnbull/remove-ai-writing
jedbrooke 12 days ago Honestly, I get pretty good improvement from just adding a “Emoji are forbidden” and a small list of banned words and phrases (the usual suspects like “it’s not just x, it’s y” etc) flexagoon 12 days ago Banning bold font and saying to avoid lists and tables as much as possible is an immediate massive improvement to LLM output quality
flexagoon 12 days ago Banning bold font and saying to avoid lists and tables as much as possible is an immediate massive improvement to LLM output quality
Interesting. I made a skill for my Claude agent based on Wikipedia’s list of AI writing tells. /remove-ai-writing
It works reasonably well (better if you run it a few times), but still benefits from a final pass by a human editor IMO.
https://github.com/arturnbull/remove-ai-writing
Honestly, I get pretty good improvement from just adding a “Emoji are forbidden” and a small list of banned words and phrases (the usual suspects like “it’s not just x, it’s y” etc)
Banning bold font and saying to avoid lists and tables as much as possible is an immediate massive improvement to LLM output quality