A writer hands only spell-checking to AI
Understand this story
A writer with dyslexic tendencies says he no longer manually corrects spelling errors and instead hands spell-checking to AI. His reasoning is that LLMs split text into tokens and understand it in context, so they can read the intended meaning even when letters are out of order. He insists on rereading, finding and fixing errors himself, outsourcing only spelling to AI so as not to hand over abilities such as organizing thoughts and structuring arguments to the model as well.
AI overview based on source reports · Updated 1 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AISkills I'm Willing to Let AI Have
The author, who has dyslexic tendencies and often transposes letters between words, describes how LLMs read text as tokens and infer meaning from context, so typos no longer block understanding. They note they have stopped rereading and fixing their own mistakes, and worry that the habit of letting the model figure it out could spread to skills like organizing thoughts and structuring arguments. They decide to keep letting AI read through typos but to resume rereading and correcting their own writing, and ask readers which skills they are letting AI have.
Activity for this story
- Current comparable activity
- 4
- Peak comparable activity
- 9Nov 13 17:00
- 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.