Hiskias
- Karma
- 3
- Created
- 6 years ago
Recent Submissions
- 1. ▲ Building a System One Model for Prompt Injection (stackone.com)
- 2. ▲ Show HN: Open-Source Lightweight Prompt Injection Safety (github.com)
- 3. ▲ Open Sourced R-Lens (github.com)
- 4. ▲ The Interpretability Illusion – Why we should train models to be interpretable (hisku.substack.com)
- 5. ▲ Show HN: Stop Babysitting Your Agents (github.com)
- 6. ▲ Training a 22MB prompt injection classifier that runs inline in a Lambda (stackone.com)
- 7. ▲ Stack-nudge – Stop babysitting your AI agent's terminal (github.com)
- 8. ▲ Training a 22MB prompt injection classifier (stackone.com)
- 9. ▲ Defender – Local prompt injection detection for AI agents (no API calls) (npmjs.com)
- 10. ▲ Defender – Local prompt injection detection for AI agents (no API calls) (npmjs.com)