News for hackers. Stuff that matters.

glth

glth on Hacker News

Re:Why XML Tags Are So Fundamental to Claude on Sunday March 01, 2026 @11:40AM (#47208228)
Author here: I have just fixed the typo. Thank you.

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

Re:Switch to Claude without starting over on Sunday March 01, 2026 @03:40AM (#47204884)
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).
Re:Ask HN: Could you share your personal website here? on Wednesday January 14, 2026 @01:19PM (#46620026)
https://glthr.com/
Re:The Myst Graph: A New Perspective on Myst on Wednesday April 02, 2025 @05:09AM (#43554896)
Author here: good catch, thank you! I have fixed the two errors.
Re:The Myst Graph: A New Perspective on Myst on Wednesday April 02, 2025 @01:22AM (#43553869)
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!
Re:Ask HN: What are you working on? (March 2025) on Sunday March 30, 2025 @06:54PM (#43528576)
Interesting: I would love to read this article when it is published.
Re:Ask HN: What are you working on? (March 2025) on Sunday March 30, 2025 @06:52PM (#43528556)
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.
Re:I Built a Mechanical Calculator [video] on Thursday March 13, 2025 @02:33AM (#43350832)
Great video! Very instructive.
Re:Ask HN: What Are You Working On? (February 2025) on Monday February 24, 2025 @04:46AM (#43157633)
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.

Re:Ask HN: Who Wants a Penpal? on Thursday July 04, 2024 @03:32PM (#40877430) 

  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)

Show HN: K4nundrum – An open-source tool to investigate Kryptos K4

Posted by glth on Saturday March 30, 2024 @10:38AM
from the show-hn dept.

https://github.com/glethuillier/K4nundrum

Hi HN.As a hobby, I have been studying Kryptos K4, a classic unsolved code. Kryptos is a puzzle sculpture dedicated by its creator in 1990. It contains four encrypted messages. Three have been decoded (K1 to K3), and the last one, K4, remains undeciphered.Like many others, my attempts to solve it using classic cryptanalysis attacks have failed. However, I have recently discovered a pattern that...

( Read More... | no comments | on HN )

Older »