AI
LLM 0.37
Publication: Simon Willison's Weblog
Author: Not available in collected metadata
Source published: 02/11/2026, 23:49:30 UTC
Briefing created: 03/11/2026, 03:21:07 UTC
Based on a feed excerpt; full article content has not been acquired. Source evidence retrieved 03/11/2026, 00:12:24 UTC.
Briefings
The LLM CLI tool released in November 2026 includes two new models (gpt-6.1-sol and gpt-6.1-terra) and a new endpoint configuration command. The default model switched to gpt-6-luna, which costs half the price of the previous default, gpt-5.6-luna. A key feature is support for different content types in embeddings, addressing issues with models like Gemini Embedding 2. The release involved contributions from 12 authors, with the project author noting that AI-assisted contributions were manageable.
Key points
- The LLM CLI tool released in November 2026 includes two new models: gpt-6.1-sol and gpt-6.1-terra.
- The default model was switched to gpt-6-luna, which costs half the price of the previous default, gpt-5.6-luna.
Context
This release represents approximately two months of accumulated features and fixes for the LLM CLI tool and Python library. It addresses a specific technical issue where LLMs previously failed to embed different binary content types (text, audio, images, video) correctly, which was a known problem for models like Gemini Embedding 2.
Limitations
The evidence is a single snapshot from November 2026. It does not provide data on long-term model performance, user adoption rates, or specific bug fixes beyond the release notes. The author explicitly states that the review process was not difficult, but does not quantify the impact of the new models or the specific number of contributors beyond the 12 named authors.
Generated by Bittrees-hosted qwen35-2b sha256:aaf42c8b7c3c on 03/11/2026, 03:21:07 UTC. Based on publisher-provided feed evidence; may not cover the full original article. Check the source for details.
View archived briefing on IPFS
bafybeidwfetz2kwfmpk564kf3556bdnkhb5gj4hrd6j7dmhxwwvivxwq2a