# Research

> Papers, preprints and research projects on the security and reliability of AI systems, with abstracts, code and citations.

- [René-1: A 31B Decision Reader That Knows When It Is Sure](https://elonsalfati.com/research/rene-1.md) (2026-09-27): An open-weights 31B model that reads a document and returns a calibrated probability for every option of every question, in one pass.
- [Trigger Labs: Advancing Malware Detection Through Realistic Scenario Simulation](https://elonsalfati.com/research/trigger-labs.md) (2025-04-24): Sandboxes miss malware that waits for the right conditions. Trigger labs recreate realistic scenarios so dormant malware activates and can be detected.

---
Source: https://elonsalfati.com/research