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 · #11150

N

Niels Provos

Personal blog · provos.org · on HN as nielsprovossecurityai

Niels Provos's personal blog at provos.org covers security and ai. Since 2010, 7 different Hacker News readers have linked it 13 times, most often “IronCurtain: A Personal AI Assistant Built Secure from the Ground”. It is still writing: the last post was on 2026-10-31, and you can follow it by feed.

Visit the blog
13mentions?
7HN people?
2010–2026first – last linked?
Links on Hacker News per year · peak 9 in 2026

Too few sampled comments (1) to say how often HN recommends it.?

Why HN links it

Linked by one commenter alongside a discussion of steganography, pointing to Niels Provos's posts on image steganography with OutGuess and detection with Stegdetect.

Summarised by Claude from a sample of 1 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.

Bladesmithing & Internet Security & Music

The author on HN?

nielsprovos · 8 karma · member since 2023

https://www.provos.org/

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

Most-linked posts?

  1. IronCurtain: A Personal AI Assistant Built Secure from the Ground
    3 people · 3 mentions · first linked 2026-02-26
  2. Finding Zero-Days with Any Model
    2 people · 2 mentions · first linked 2026-04-30

What Hacker News says?

  1. A higher level of abstraction generative AI will soon be able to apply is in the design of algorithms that humans cannot possibly comprehend that go well beyond rudimentary newspaper want ad spycraft. Also, image based steg: https://www.provos.org/p/outguess/ https://www.provos.org/p/detection-with-stegdetect/

    Comment linking /p/detection-with-stegdetect/

    on “Perfectly Secure Steganography Using Minimum Entropy Coupling”
  2. Submitted The Case for Open-Weight Models and Why We Can't Trust Frontier Labs as a story · 4 points

    HN discussion
  3. Submitted Finding Zero-Days with Any Model as a story · 4 points

    HN discussion
  4. Submitted Security Research Without Asking Permission as a story · 4 points

    HN discussion
  5. Submitted Cybersecurity Defenders Need Open-Weight Models as a story · 2 points

    HN discussion
  6. Submitted I Had to Write a Script to Submit My Medical Claims to Cigna as a story · 2 points

    HN discussion
  7. Submitted 'AI' ethics limit artistic exploration as a story · 2 points

    HN discussion
  8. Submitted Anatomy of a PDF Exploit as a story · 2 points

    HN discussion
  9. Submitted Finding Zero Days with any model? as a story · 1 points

    HN discussion
  10. Submitted IronCurtain: A Personal AI Assistant Built Secure from the Ground as a story · 1 points

    HN discussion
  11. Submitted IronCurtain: A Personal AI Assistant Built Secure from the Ground Up as a story · 1 points

    HN discussion
  12. Submitted I built a personal AI assistant with security as a first-class citizen as a story · 1 points

    HN discussion

Search all of HN for provos.org