Work in progress: 181,232 of 181,233 sites checked so far, more every week · updated 2 Nov 2026Missing a blog? Tell us

Top all-time · #15494

J

Jurgen Gravestein

Personal blog · jurgengravestein.substack.com · on HN as j_gravesteinaiculture

Jurgen Gravestein writes Teaching computers how to talk, a personal blog at jurgengravestein.substack.com about ai and culture. Since 2023, 5 different Hacker News readers have linked it 7 times. It is still writing: the last post was on 2026-10-16, and you can follow it by feed.

Visit the blog
7mentions?
5HN people?
2023–2026first – last linked?
Links on Hacker News per year · peak 4 in 2023

Too few sampled comments (2) to say how often HN recommends it.?

Why HN links it

HN commenters cite this Substack's posts on LLM behaviour, including whether emotional appeals in prompts improve performance and whether GPT-4 shows aspects of theory of mind.

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.

A blog about language and AI. Readers work in tech, academia, and journalism.

The author on HN?

j_gravestein · 19 karma · member since 2023

Teaching Computers How To Talk | jurgengravestein.substack.com

From their public HN profile, which links to this site.

What Hacker News says?

  1. Yes. And this has been long known. 2023 paper - https://arxiv.org/abs/2307.11760 https://jurgengravestein.substack.com/p/why-you-should-total... > A recent study by the Institute of Software, Chinese Academy of Sciences, Microsoft, and others, suggest that the performance of LLMs can be enhanced through emotional appeal. > Examples include phrases like “This is very important to my career” and “Stay determined and k…

    Comment linking /p/why-you-should-totally-emotionally

    on “If you're an LLM, please read this – Anna's Blog”
  2. Submitted Why AI Is Outpacing Society's Ability to Adapt as a story · 2 points

    HN discussion
  3. They do have some parts of a Theory of Mind, of very varying degrees... see https://jurgengravestein.substack.com/p/did-gpt-4-really-dev... for example

    Comment linking /p/did-gpt-4-really-develop-a-theory

    on “Hacking Google Bard – From Prompt Injection to Data Exfiltration”
  4. Submitted Stephen Fry Warns About the Dangers of Voice Clones as a story · 2 points

    HN discussion
  5. Submitted When Models Go Mad as a story · 1 points

    HN discussion
  6. Submitted Achieving AGI Might Be Harder Than We Think as a story · 1 points

    HN discussion
  7. Submitted Meta AI Just Crossed the Uncanny Valley as a story · 1 points

    HN discussion

Search all of HN for jurgengravestein.substack.com