Claim◆Video · 6:56 · 2m
The large language model itself has become a commodity — interchangeable like gas from any gas station, where price (or marginal quality) is the only real differentiator.
Ali Ghodsi · BG2 Pod
DataArticle
The llm-chat-completions-server plugin starts a localhost server on port 9001 that exposes all installed LLM models through a ChatGPT Completions compatible endpoint.
Installing and running the plugin starts a localhost server on port 9001 that makes all LLM models available via an OpenAI Chat Completions compatible API. ✦ AI generated
Author · Simon Willison's Weblog · 2026-07-30 · original ↗
To test that out, I built this plugin: uv tool install llm --pre llm install llm-chat-completions-server llm chat-completions-server -p 9001 Running this starts a localhost server on port 9001 that exposes your full collection of LLM models (from any plugins you have installed) using a ChatGPT Completions compatible endpoint.
Read full article ↗excerpt · fair-use quotation
Related moments
Claim◆Video · 50:47 · 2m
LLMs are best understood as sophisticated statistical pattern-matching systems without true understanding, more like an 'alien intelligence' than a human-like artificial intelligence, since they train only on text rather than however the brain actually works.
CJ · Syntax
Fact◆Video · 34:48 · 2m
Instagram's recommendation algorithm does not have a rich, human-legible semantic understanding of users' interests; it relies on large embedding models producing illegible high-dimensional vectors, and only recently have LLMs made it possible to translate those vectors into human-readable descriptions.
Adam Mosseri · Lenny's Podcast