"Sixty years after the Cultural Revolution began, a writer looks back to her childhood in Beijing during its peak, and the banned books that sustained her through the tumult."
Russia has again attacked the Ukrainian capital Kyiv with ballistic missiles, killing at least one person and injuring more than 20. Earlier President Zelensky shared video on social media of a drone hunting down a man in the southern city of Kherson, saying it showed an ins...
I released LLM 0.32 this morning, the most significant new version of LLM since the initial launch of the project. The new version includes support for visible reasoning traces, server-side provider tools, redesigned content-addressable SQLite logs, new models, and new featu...
After shipping condense-json 1.0 I started integrating it into LLM, and found there were some desirable new features already:
Replacements object can now include values other than strings. These will be identified and used as structural replacements by condense_json() and uncondense_json(). #8
Objects can be used as the basis for merge operations. condense_json() will identify if there are objects that are a close match and will store instructions for keys to update or delete. uncondense_json() can then apply these merges.
I released LLM 0.32 this morning, the most significant new version of LLM since the initial launch of the project. The new version includes support for visible reasoning traces, server-side provider tools, redesigned content-addressable SQLite logs, new models, and new featu...
OpenAI published an unbylined blog post overnight, responding in public — but not yet in court — to Apple’s new motion for a preliminary injunction. It’s an unusual move to respond to a high-stakes legal filing with a blog post, but OpenAI is an unusual company. A few snippe...
In recent years, science has been learning more and more about how central the role of inflammation is to our health. “The paradox that often makes treating chronic inflammation so difficult: It can be vital and harmful at the same time.”
Release: llm-anthropic 0.26
Includes new features enabled by LLM 0.32:
New models: claude-fable-5, claude-sonnet-5, and claude-opus-5. #75, #76
Added server-side tools for WebSearch, WebFetch, CodeExecution, and AnthropicMCP, available through LLM's -T interface o...
I don’t know what sort of neurodiverse bucket this puts me in, but I think a lot about mowing the lawn1 relative to how much time I actually spend mowing lawns (~6-7 hours per year). And so I was completely fascinated by The Pudding’s latest post on optimal lawn mowing pat...
PipeNetwork/minimax-h3-mlx
MiniMax released MiniMax-H3 two days ago - they describe it as a "a general-purpose, omni-modal generative system", which in practice means it accepts text, images, audio and video and can use them to generate up to 15 second video clips with audio...
PipeNetwork/minimax-h3-mlx
MiniMax released MiniMax-H3 two days ago - they describe it as a "a general-purpose, omni-modal generative system", which in practice means it accepts text, images, audio and video and can use them to generate up to 15 second video clips with audio...