conditioning

Introduces State-Grounded Conditioning (SGC), a design principle for user-facing LLM agents to condition on live state, reducing direction drift and improving latency and accuracy in in-game coaching scenarios.

A new paper argues that text-to-image models benefit less from longer prompts and more from explicitly organized visual structure, proposing structured prompts over natural-language prose.

This paper proposes that the iterative loop of human-AI agent interaction (request, response, appraisal, revision) is a high-frequency neuroplastic training environment that can reinforce negative psychological patterns through repetition, and suggests it can be leveraged for beneficial cognitive training.

This paper identifies and analyzes 'location leakage' in LLMs, where geographic conditioning causes models to over-index on location metadata even in location-agnostic prompts, revealing structural conditioning effects beyond content.