Top all-time · #9705
Mike Caulfield
Personal blog · mikecaulfield.substack.comaiwriting
Mike Caulfield writes The End(s) of Argument, a personal blog at mikecaulfield.substack.com about ai and writing. Since 2024, 8 different Hacker News readers have linked it 9 times, most often “Is the LLM response wrong, or have you just failed to iterate it?”. It is still writing: the last post was on 2026-10-19, and you can follow it by feed.
Too few sampled comments (2) to say how often HN recommends it.?
Why HN links it
HN readers link Mike Caulfield's Substack for LLM prompting ideas, including a "sorting prompts" method for coding agents and a long prompt for getting models to write in different styles.
Summarised by Claude from a sample of 2 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Looking for the structure underneath the noise.
Most-linked posts?
- Is the LLM response wrong, or have you just failed to iterate it?2 people · 2 mentions · first linked 2025-09-10
What Hacker News says?
I think asking your questions in that form is akin to "sorting prompts" that I learned about from https://mikecaulfield.substack.com/p/is-the-llm-response-wro... and I have been using successfully when when writing code (e.g. [as a Claude code slash command]( https://www.joshbeckman.org/notes/936274709 )). Essentially, you're asking the LLM to do research and categorize/evaluate that research instead of just giving…
Comment linking /p/is-the-llm-response-wrong-or-have
on “Two things LLM coding agents are still bad at”Submitted Differences in link hallucination and source comprehension across different LLM as a story · 78 points
HN discussionI really enjoyed this recent post on prompts to get the LLM to write in different styles. It's from Mike Caulfield who I just love anyways, who has been so committed & eloquent a proponent of/towards a high-signal world for so long, https://mikecaulfield.substack.com/p/a-300-word-prompt-that-... https://mikecaulfield.substack.com/p/introducing-jamesian-a-... It was an interesting explanation, of why LLMs talk the wa…
Comment linking /p/introducing-jamesian-a-claude-skill
on “Expansion Artifacts”Submitted Is the LLM response wrong, or have you just failed to iterate it? as a story · 2 points
HN discussionSubmitted The Elmer's Glue Pizza Error Is More Than You Think as a story · 2 points
HN discussionSubmitted Tilling the Garden: Use AI differently to make interesting and useful apps as a story · 1 points
HN discussionSubmitted A 400 Word Prompt That Makes LLM Paragraphs More Bearable as a story · 1 points
HN discussionSubmitted Hallucination Chains as a story · 1 points
HN discussion