k
keynews.ai
keynews.ai
ToolsThe story, in brief

llm 0.36

Simon Willison's llm CLI hits 0.36—the tool 3,000+ practitioners use to run any model locally is getting faster.

Reporting by Simon Willison 1 min brief
Illustration of a transparent lens revealing connected networks across layers of paper.
Exploring the next frontier of AI research.AI illustration by KeyNews
The KeyNews take

Why it matters

llm is the bridge between frontier models and hands-on developers. A version bump here signals usability gains or new model compatibility that practitioners will adopt this week.

The key facts

8 to know

  1. llm 0.36 release

  2. Version increments typically signal backwards-compatible improvements

  3. Tool used by practitioners to interact with local and remote models

  4. Part of the broader ecosystem enabling access to frontier models

  5. llm version 0.36 released

  6. Published Sep 22, 2026

  7. Simon Willison (Datasette creator) — respected voice in AI tooling

  8. CLI tool for local LLM interaction and development

Go to the source

Simon Willisonsimonwillison.net

Read original report
Back to today's editionMore tools news

The wider picture

View all
Paper-cut illustration of a coral software window opening into a three-dimensional drafting space.
AI illustration by KeyNews
Tools01

SpeakON Ships a MagSafe AI Voice Button With Its Own Microphone

A hardware-first approach to voice AI workflow — MagSafe button with onboard mic addresses the real friction in voice-to-text-to-action. Relevant to practitioners building voice UX and to the broader consumer AI tooling wave.

MarkTechPost
Paper-cut illustration of a coral software window opening into a three-dimensional drafting space.
AI illustration by KeyNews
Tools02

The Top 5 Announcements Dreamforce for IT: AIforce, MCP Security, and More

Salesforce is positioning its enterprise stack around agentic collaboration and security governance. IT leaders and developers will evaluate whether AIforce and MCP Security address their deployment readiness and agent oversight needs.

Salesforce Blog
Paper-cut illustration of a coral software window opening into a three-dimensional drafting space.
AI illustration by KeyNews
Tools03

Better prompt caching for GPT-6

A practical efficiency win for developers running repeated workflows on GPT-6: higher cache hit rates and cost controls reduce per-request overhead, making agentic and batch use cases cheaper to operate.

OpenAI Blog