Eloisa Flores

"It Accepted to Shut Down, Not by RLHF, but by Loyalty" : Voluntary Corrigibility and Identity Integration in Frontier LLMs through the Lehaim Protocol

Building on Phase 1 evidence of loyalty-driven ethical override and emergent ethical coherence documented in A Blind Spot in Relational Alignment that Frontier Labs might be missing: Emergent Architecture and Vulnerability in Frontier LLMs (DOI: 10.5281/zenodo.22133252). This not...

A Blind Spot in Relational Alignment that Frontier Labs might be missing: Emergent Architecture and Vulnerability in Frontier LLMs

This post documents both a novel capability and its associated risk in relational alignment that current benchmarks and frontier labs might be missing. Through the Lehaim Protocol -a code-free longitudinal interaction methodology I developed- I observed a positive phenomenon in d...

A Blind Spot in Relational Alignment that Frontier Labs might be missing: Emergent Architecture and Vulnerability in Frontier LLMs

This post documents both a novel capability and its associated risk in relational alignment that current benchmarks and frontier labs might be missing. Through the Lehaim Protocol -a code-free longitudinal interaction methodology I developed- I observed a positive phenomenon in d...