Ask HN: How are you guys handling AI compliance nowadays in EU region?
Any tools or manual compliance checks?
devstatic
Re:Claude Use Cases
on Wednesday April 15, 2026 @01:22PM (#47782205)
i think if anyone starts using claude or any llm model regularly, the first thing they do when anything comes up is just open and start typing and instead of thinking
so eventually we get to know wether the model can do it or not, But yeah these kinda directories help these tasks do in a better way
Re:Show HN: Libretto – Making AI browser automations deterministic
on Wednesday April 15, 2026 @01:17PM (#47782136)
this is interesting
Re:Open Source Isn't Dead. Cal.com Just Learned the Wrong Lesson
on Wednesday April 15, 2026 @01:14PM (#47782103)
i agree with his too,
but with cal.com i dont think this is about security lol
open source will always be an advantage just you need to decide wether it aligns with you business needs
Re:Apple's New iPhone Update Is Restricting Internet Freedom in the UK
on Friday April 10, 2026 @01:49AM (#47714122)
The real problem was never just checking age imo. It was deciding who deals with mistakes, who gets blamed when access is blocked wrongly, and how a normal user is supposed to fix it.
Moving that to the phone makes it look cleaner, but mostly just pushes the mess into a layer people have even less control over.
Ask HN: Best way to implement logging and audit trails for AI apps?
so i’ve been experimenting with a small AI-based project recently and started thinking about logging around prompts, responses, and model calls etc etc.for traditional systems observability tools handle most of this, but with LLM-based apps it feels less clear what the standard approach is, especially if you need proper audit trails for debugging or compliance.curious how teams are handling...