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 · #2425

S

Simon Willison

Personal blog · simonw.substack.comaiprogramming

Simon Willison's personal blog at simonw.substack.com covers ai and programming. Since 2023, 30 different Hacker News readers have linked it 35 times, most often “The lethal trifecta for AI agents”. It is still writing: the last post was on 2026-10-28, and you can follow it by feed.

Visit the blog
35mentions?
30HN people?
2023–2026first – last linked?
Links on Hacker News per year · peak 17 in 2025

Too few sampled comments (10) to say how often HN recommends it.?

Why HN links it

HN readers link Simon Willison's Substack newsletter, which mostly reposts his blog, as a source on AI developments, prompt-injection risks ('lethal trifecta') and Claude tooling.

Summarised by Claude from a sample of 10 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.

AI, LLMs, web engineering, open source, data science, Datasette, SQLite, Python and more. Click to read Simon Willison’s Newsletter, a Substack publication with tens of thousands of subscribers.

Most-linked posts?

  1. The lethal trifecta for AI agents
    5 people · 5 mentions · first linked 2025-06-17
  2. /feed
    2 people · 2 mentions · first linked 2024-12-20
  3. A new way to extract detailed transcripts from Claude Code
    2 people · 2 mentions · first linked 2025-12-28
  4. I built a new feature for my blog using my voice
    2 people · 2 mentions · first linked 2026-10-12
  5. Embracing the parallel coding agent lifestyle
    2 people · 2 mentions · first linked 2025-10-06
  6. First impressions of Claude Cowork, Anthropic's general agent
    2 people · 2 mentions · first linked 2026-01-14
  7. /
    2 people · 2 mentions · first linked 2023-04-07

What Hacker News says?

  1. Simon's a prolific writer on AI http://simonw.substack.com https://simonwillison.net

    Comment linking /

    on “Gemini with Deep Think achieves gold-medal standard at the IMO”
  2. Submitted GPT-5 Thinking in ChatGPT (a.k.a. Research Goblin) is shockingly good at search as a story · 52 points

    HN discussion
  3. One tip: Every Substack has a feed, which is a nice alternative to having everything dropped in your email in-box. You just append "/feed" to the end of a newsletter URL, e.g. https://simonw.substack.com/feed .

    Comment linking /feed

    on “Show HN: Artemis, a Calm Web Reader”
  4. Submitted 2026 in LLMs (So Far) as a story · 20 points

    HN discussion
  5. Original @simonw article here: https://simonw.substack.com/p/the-lethal-trifecta-for-ai-age... https://simonwillison.net/2025/Aug/9/bay-area-ai/ Discussed: https://news.ycombinator.com/item?id=44846922

    Comment linking /p/the-lethal-trifecta-for-ai-agents

    on “How to stop AI's "lethal trifecta"”
  6. Submitted Claude Opus 4.5, and why evaluating new LLMs is increasingly difficult as a story · 5 points

    HN discussion
  7. Also agents cannot trust any data whatsoever they add to their context. This puts reading email for example as a risk. Probably not impossible to create a worm that convinces a claw to forward it to every email address in that inbox. And then exfiltrate all the emails. Then do a bunch of password resets. Then get root access to your claw. But not just email. Github issues, wikipedia, HN etc. may be poisoned. See htt…

    Comment linking /p/the-lethal-trifecta-for-ai-agents

    on “Don't trust AI agents”
  8. Submitted Feed a video to a vision LLM as a sequence of JPEG frames on the CLI as a story · 4 points

    HN discussion
  9. I've seen those in the past for RSS feeds from Substack - https://simonw.substack.com/feed for example - which is frustrating because the whole point of an RSS feed is to support polling by automated systems!

    Comment linking /feed

    on “The Many Broken Feeds”
  10. Submitted Image segmentation using Gemini 2.5 as a story · 4 points

    HN discussion
  11. My approach is to publish to my own blog at https://simonwillison.net and then copy and paste content from that into a Substack newsletter at https://simonw.substack.com a few times a month. It's been working really well. Substack don't have an API, but they do support copy and paste - so I built myself a tool that assembles my blog content into rich text I can copy and paste straight into the Substack editor. I wro…

    Comment linking /

    on “Moving Away from Substack”
  12. Submitted First impressions of Claude Cowork, Anthropic's general agent as a story · 3 points

    HN discussion
  13. Not "HN-like", but I have found Simon Willison's blog/newsletter very helpful: - https://simonwillison.net - https://simonw.substack.com

    Comment linking /

    on “Ask HN: What's your best resource for keeping up-to-date on AI developments?”
  14. Submitted I built a new feature for my blog using my voice as a story · 2 points

    HN discussion
  15. > The victim uploads a file to Rovo that contains a hidden prompt injection Yeah this attack is possible on all modern agentic systems. * Access to your private data * Exposure to untrusted content * The ability to externally communicate in a way that could be used to steal your data ( https://simonw.substack.com/p/the-lethal-trifecta-for-ai-age... ) And blocking it wholesale reduces usefulness of the agent so it is…

    Comment linking /p/the-lethal-trifecta-for-ai-agents

    on “Atlassian Rovo Exfiltrates Data, Bypassing Controls”
  16. Submitted Embracing the parallel coding agent lifestyle as a story · 2 points

    HN discussion
  17. Simon Willison just posted about using claude in fly.io's dev sandboxes. I have not tried it yet but it looks promising. https://simonw.substack.com/p/first-impressions-of-claude-co...

    Comment linking /p/first-impressions-of-claude-cowork

    on “Claude Cowork Runs Linux VM via Apple Virtualization Framework”
  18. Submitted The lethal trifecta for AI agents as a story · 2 points

    HN discussion
  19. simow wrote a tool that does this for Claude code https://simonw.substack.com/p/a-new-way-to-extract-detailed-...

    Comment linking /p/a-new-way-to-extract-detailed-transcripts

    on “Ghostty's AI Policy”
  20. Submitted Trying out the new Gemini 2.5 model family as a story · 2 points

    HN discussion
  21. Submitted The lethal trifecta for AI agents as a story · 2 points

    HN discussion
  22. Submitted Building software on top of Large Language Models as a story · 2 points

    HN discussion
  23. Submitted First impressions of the new Amazon Nova LLMs as a story · 2 points

    HN discussion
  24. Submitted Multi-modal prompt injection image attacks against GPT-4V as a story · 2 points

    HN discussion
  25. Submitted I built a new feature for my blog using my voice as a story · 1 points

    HN discussion
  26. Submitted DeepSeek v4, and the end of the OpenAI/Microsoft AGI clause as a story · 1 points

    HN discussion
  27. Submitted Vibe coding SwiftUI apps is a lot of fun as a story · 1 points

    HN discussion
  28. Submitted Agentic Engineering Patterns as a story · 1 points

    HN discussion
  29. Submitted A new way to extract detailed transcripts from Claude Code as a story · 1 points

    HN discussion
  30. Submitted Embracing the parallel coding agent lifestyle as a story · 1 points

    HN discussion

Search all of HN for simonw.substack.com

Linked by the same people?