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. https://x.com/deedyd

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. h

Presents a modular context-engineering framework that grows and refines an LLM’s working context like a playbook, not a terse prompt. https://x.com/omarsar0/status/1976746822204113072

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. https://x.com/saprmark