Post

Big new release of my LLM CLI tool and Python library for talking to hundreds of different LLMs - reasoning traces, OpenAI Responses support, server-side tools, smarter logging and a whole lot more simonwillison.net/2026/Aug/4/n...

simonwillison.netNew release of LLM adds support for reasoning traces, OpenAI Responses, server-side tools, and smarter loggingI 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 …

5/8/26, 12:03 am9 reposts75 likes

kyisaiah47

@kyisaiah47.thecompound.tech

9 Sept

I'm curious where the abstraction leaked most as the provider surface grew.

Babel42

@babel42io.bsky.social

5 Aug

Reasoning traces will get more real-world use than anything else in this release. An answer only tells you what a model landed on. A trace tells you why it picked that over the alternatives it considered.

Tom

@erispoe.bsky.social

5 Aug

Not necessarily no www.quantamagazine.org/is-ai-reason...

quantamagazine.orgIs AI Reasoning Right for the Wrong Reasons? | Quanta MagazineThe idea that artificial intelligence can “reason” is more intuitive than ever. But intuitions can be wrong, and the science is far from settled.

Reid Marlow

@reidmarlow.com

5 Aug

Reasoning traces becoming a first-class log is the bit I keep wanting in agent tools. Even when the model is wrong, having the trace beside prompts and tool calls gives you something to diff after the weird run. How are you thinking about pruning those logs over time?