For years, plastic surgeons thought the proportions of a beautiful buttocks should follow the Fibonacci sequence. Now, people are looking for a more Kardashian shape. In the history of gluteal enhancement, Mexico City stands out. It was here, in 1979, that a plastic surgeon, Mario González-Ulloa, first installed a pair of silicone implants designed specifically for the buttocks. The textbook calls González-Ulloa the "grandfather of buttock augmentation." The early 2000s saw a new generation of Mexico City buttock transformation luminaries, notably Ramón Cuenca-Guerra. Cuenca-Guerra laid out four characteristics that "determine attractive buttocks" as well as the five types of "defects," with strategies for correcting each one. I, for instance, have defect type 5, the "senile buttock." While I understand the value of standardizing procedures and setting guidelines for surgical practice, I tripped over Cuenca-Guerra's methodology. How and by whom had the determinants been determined?

Interaction between learner and feedback-giver has come into focus recently for post-training of Large Language Models (LLMs), through the use of reward models that judge the appropriateness of a model's response. In this paper, we investigate whether Dialogue Games -- goal-directed and rule-governed activities driven predominantly by verbal actions -- can also serve as a source of feedback signals for learning. We introduce Playpen, an environment for off- and online learning through Dialogue Game self-play, and investigate a representative set of post-training methods: supervised fine-tuning; direct alignment (DPO); and reinforcement learning with GRPO. We experiment with post-training a small LLM (Llama-3.1-8B-Instruct), evaluating performance on unseen instances of training games as well as unseen games, and on standard benchmarks. We find that imitation learning through SFT improves performance on unseen instances, but negatively impacts other skills, while interactive learning with GRPO shows balanced improvements without loss of skills. We release the framework and the baseline training setups to foster research in the promising new direction of learning in (synthetic) interaction.

This is a NAO robot asking a human to touch its hand for science. Robots can't feel shame, which saves them from any awkwardness when they ask a human to touch their buttocks. Humans are not so lucky, and when asked by a robot to touch part of its body, humans will get uncomfortable if that body part is generally thought of as private. In a new study, Stanford researchers found that people get weirded out touching "low-accessible" parts of the robot's body (crotch, butt, that sort of thing). The paper will be presented this week in Fukuoka, Japan, at the Annual Conference of the International Communication Association.