Hacker News Reader

glthon Why XML tags are so fundamental to Claude

Author here: I have just fixed the typo. Thank you.

And yes, these are screenshots from Anthropic’s documentation.

glthon Switch to Claude without starting over

On a related note, I have been experimenting with a small prototype for cross-agent, device-local active memory called brAIn (https://github.com/glthr/brAIn). It delivers a personalized agent experience with everything stored locally in a single file (agent.brain), and supports reusing semantic memory across projects. In practice, this means brAIn can identify and apply behavioral patterns you have used in other contexts whenever they are relevant. (I realize the repository should include a concrete example of this, and I will update it today to add one).

glthon Ask HN: Share your personal website

https://glthr.com/

glthon The Myst Graph: A New Perspective on Myst

Author here: good catch, thank you! I have fixed the two errors.

glthon The Myst Graph: A New Perspective on Myst

Author here: In a few weeks, I will publish the graph generator's source code and a DOT file encoding the Myst graph in this repository: https://github.com/glthr/DeMystify. I would love to see how others render the graph and how the generator can be improved. A follow-up article will also dive deeper into the technical details. Stay tuned!

glthon Ask HN: What are you working on? (March 2025)

Interesting: I would love to read this article when it is published.

glthon Ask HN: What are you working on? (March 2025)

I think that is a fantastic idea! I would be happy to see your blog take shape. Blogging is something I genuinely enjoy, as it allows me to put my thoughts into tangible form.

glthon I Built a Mechanical Calculator [video]

Great video! Very instructive.

glthon Ask HN: What are you working on? (February 2025)

I am currently exploring methods to detect and categorize undocumented special tokens (or: "delimiters") used by LLMs.

As part of this effort, I have developed a preliminary prototype (named deLLMiter) that I am refining.

This method is founded upon the hypothesis that there exists a correlation between first-order expressions and more complex, hierarchical forms of expression (https://glthr.com/llm-delimiters-and-higher-order-expression...).

With this project, my goal is to improve the security of LLM models.

glthon Ask HN: Who Wants a Penpal?

  alias: G.
  interests: computers, programming languages, programmatic puzzles, bacteriophages
  language(s): en, fr
  link to something you think is cool: https://google-research.github.io/self-organising-systems/2022/diff-fsm/
  contact info: moeie.gyj/btfgxnc (Vigenère cipher, the key is this website's name)

glthon A new old kind of R&D lab

This is a great initiative! Given what you want to achieve, I presume you will have a wide range of (atypical) profiles in your team.

glthon Ask HN: Any interesting books you have read lately?

The Good Virus by Tom Ireland (https://www.nytimes.com/2023/08/15/books/review/the-good-vir...).

This book introduces phages and their pivotal role in advancing human health through phage therapy. In my opinion, it illustrates the inevitability of phage therapy's integration into mainstream medical practices, underscoring its potential to effectively combat antibacterial resistance.

glthon Ask HN: Could you share your personal blog here?

https://www.glthr.com/

Programming and puzzles

glthon Scan iPhone backups for traces of compromise by “Operation Triangulation”

Do you mean `s/./-/g`?

glthon Ask HN: What are your goals for 2023?

- Help my family (new job, education)

- Learn more about software architecture

- Publish on my website the solution to a fantastic 20th-century literary puzzle (https://glthr.com/cj)