meet.hn/city/51.3406321,12.3747329/Leipzig Socials: - github.com/rixed - grixed@gmail.com ---
I solve this issue (agent looking at too much and changing too much) with the best abstraction ever invented : files and permissions.
One task is usually composed of 2 input files, a specification and a header file, and the task is to output the implementation and nothing more. Agent user has no other permissions in the file system, has no tools, just output the code that's directed into a file. I run ´make' whenever I update a specification. Token count is minimal.
Do I save time? Not much, but having to specify and argue about everything is interesting, and I trust myself that I'm not loosing any knowledge this way; be it the why or the how.
Still working on my network monitoring tool.
Since last time, added a "landing-page" kind of website [0], added annotations with BGP events, support for IPv6, and finishing TLS for every communication between probes and central servers.
About to open for beta testers, and still very much interested in comments esp. regarding the UI.
This project is an enhanced reader for Ycombinator Hacker News: https://news.ycombinator.com/.
The interface also allow to comment, post and interact with the original HN platform. Credentials are stored locally and are never sent to any server, you can check the source code here: https://github.com/GabrielePicco/hacker-news-rich.
For suggestions and features requests you can write me here: gabrielepicco.github.io