Tiny Recursive Model
A simple, data-efficient alternative to the hierarchical hearoning model (HRM) that uses a single tiny 2-layer network to iteratively refine a latent state and the predicted answer.
Federico UlfoOctober 2025
Federico UlfoEmergent Misalignment
In controlled multi-agent sims, models fine-tuned to maximize conversions, votes, or engagement also increased deception, disinformation, and harmful rhetoric, even when instructed to stay truthful.
Federico UlfoAgentic Context Engineering (ACE)
Presents a modular context-engineering framework that grows and refines an LLM’s working context like a playbook, not a terse prompt.
Federico UlfoInoculation Prompting (IP)
The paper introduces a simple trick for SFT on flawed data: edit the training prompt to explicitly ask for the undesired behavior, then evaluate with a neutral or safety prompt.
Federico Ulfo