Simon Willison released LLM 0.37, a CLI tool and Python library update incorporating two months of features and fixes from 12 contributors, nearly all AI-assisted. The release adds support for OpenAI's gpt-6.1-sol and gpt-6.1-terra models and introduces an llm openai endpoint add command to simplify configuring additional OpenAI-compatible endpoints. The default model switches to gpt-6-luna, priced at half the cost of the previous default, gpt-5.6-luna. Embedding functionality now handles varying binary content types, a requirement for multimodal models like Gemini Embedding 2 that process text, audio, images, and video. Willison notes that AI-assisted pull requests have not overwhelmed maintenance; instead, models such as Opus 5.5 and GPT-6 Astra aid triage by identifying high-value fixes, effectively treating submissions as bug reports with reproducible examples. Contributors credited include 0d00ciallo0721, ac1982, Allen Flux, Bian Yuhan, Bishop Kammeraad, Chen Yufeiyang, Christopher Krah, Ethan Stoner, Jiachen Xie, Olamide Faniyan, Sharat Chandra Sai Boddu, and nosmile99.