Show HN: Open-Source Lightweight Prompt Injection Safety g github.com 1 Hiskias 1 month ago 0 comments
The Interpretability Illusion – Why we should train models to be interpretable h hisku.substack.com 1 Hiskias 2 months ago 0 comments
Training a 22MB prompt injection classifier that runs inline in a Lambda s stackone.com 3 Hiskias 5 months ago 1 comments
Stack-nudge – Stop babysitting your AI agent's terminal g github.com 1 Hiskias 5 months ago 0 comments