AI News/#LLM
TOPIC FOCUS
20 curated stories

#LLM News.

Curated coverage, model releases, technical papers, and engineering updates tagged with #LLM.

Weekly AI Digest

Sundays

Technical digest synthesizing the week's key AI breakthroughs & models.

No spam. 1-click unsubscribe anytime.

RSS feed
Showing 20 stories tagged #LLM
Simon Willison AI
Top StorySimon Willison AIsimonwillison.net

datasette-maplibre 0.1a0

Visualize geospatial data in Datasette using MapLibre GL and OpenFreeMap

#Developer#LLM
Simon Willison AI
Simon Willison AIsimonwillison.net

datasette-agent 0.6a0

An LLM-powered agent for Datasette

#Developer#LLM
Simon Willison AI
Simon Willison AIsimonwillison.net

datasette-llm 0.1a11

LLM integration plugin for other plugins to depend on

#Developer#LLM
Simon Willison AI
Simon Willison AIsimonwillison.net

llm-gemini 0.37

LLM plugin to access Google's Gemini family of models

#Developer#LLM#Gemini
HuggingFace
HuggingFace

LLMON: An LLM-Native Markup Language, now in Granite 4.1 3B and 8B

A Blog post by IBM Granite on Hugging Face

AWS Machine Learning
AWS Machine Learning

Building a self-service LLM gateway with Amazon Bedrock and LiteLLM

Build a self-service LLM gateway with LiteLLM on AWS Fargate that puts Amazon Bedrock foundation models behind an OpenAI-compatible API. Developers get instant access through a single API key, while platform teams gain per-user cost controls, quota isolation, and observability.

#Cloud#Advanced (300)#Amazon Bedrock
Simon Willison AI
Simon Willison AIsimonwillison.net

Gemini Decisions API

Google join Jev and OpenAI in the decision model category with "Gemini Decision 1". This new model API is almost identical to Jev: it supports the same three types of …

#Developer#LLM#OpenAI
Simon Willison AI
Simon Willison AIsimonwillison.net

aws-emulator

Finally, an official emulator from AWS to run tests against a local clone of their many different services without having to provision a paid API key to do so. It's …

#Developer#LLM
Simon Willison AI
Simon Willison AIsimonwillison.net

Browse tools.simonwillison.net by tag

I've been wanting a better way to browse my collection of vibe-coded tools (244 and counting) for a while. I had a few Fable 5.2 credits left over before my …

#Developer#LLM
Simon Willison AI
Simon Willison AIsimonwillison.net

Anthropic's IPO roadshow video

Anthropic kicked off their IPO roadshow yesterday, and their roadshow video has some previously unreleased information about how their business works. The section on "Approach to compute" with co-founder Tom …

#Developer#LLM#Anthropic
24
HackerNewsgithub.com

Compress any LLM 3x in one click, near-lossless, in under 50 MB RAM

Hacker News discussion about "Compress any LLM 3x in one click, near-lossless, in under 50 MB RAM".

30
HackerNewsarxiv.org

The Surprising Effectiveness of Deleting Weights in LLM Post-Training

Abstract page for arXiv paper 2611.10866: The Surprising Effectiveness of Deleting Weights in LLM Post-Training

Simon Willison AI
Simon Willison AIsimonwillison.net

llm-gemini 0.36

LLM plugin to access Google's Gemini family of models

#Developer#LLM#Gemini
34
HackerNewsneuracryption.com

Compress any LLM 3x in one click,near-lossless,in under 50 MB RAM

Explore the official SPECTRA research paper (Zenodo DOI: 10.5281/zenodo.24058202). A complete architectural deconstruction of Shannon entropy bounds, calibration-free Group-32 microscaling, register-fused Triton kernels, and 82.53 tok/s edge decoding...

Simon Willison AI
Simon Willison AIsimonwillison.net

Introducing Our Smallest, Most Efficient Model: Muse Ember

Meta AI just launched their entry in the Claude Haiku/GPT Luna category: Muse Ember, which they describe as: [...] our smallest and most efficient model designed for complex reasoning execution …

#Developer#LLM#GPT
Simon Willison AI
Simon Willison AIsimonwillison.net

Quoting Prompting Claude Fable 5.2

Claude Fable 5.2 responds closely to what the prompt says about who owns the code it works on. In Anthropic’s testing on small coding tasks, when a prompt said nothing …

#Developer#LLM#Anthropic
Simon Willison AI
Simon Willison AIsimonwillison.net

Yonkers Rises

Yonkers Rises is an animated 3D diorama of New York City in which a giant mech, cut from the Yonkers boundary, rises from the ground and walks through Manhattan, Brooklyn, …

#Developer#LLM
Apple ML
Apple ML

Evaluating the Evaluators: Investigating LLM Judges for Personalized Writing Style Assessment

This paper was accepted at the Can We Trust AI Evaluation? Workshop at NeurIPS 2026. We evaluate how good large language model (LLM) judges are for personalized writing tasks. This is important when a user’s preferred writing style is known (e.g., “upbeat”) and an LLM judge is used to evaluate whether generated text ad...

Simon Willison AI
Simon Willison AIsimonwillison.net

llm-anthropic 0.31

LLM access to models by Anthropic, including the Claude series

#Developer#LLM#Anthropic
Simon Willison AI
Simon Willison AIsimonwillison.net

Locating the source of a mysterious beep with Claude

Our house has a box room, full of boxes that we still haven’t unpacked from our last move. A couple of weeks ago something in that room started intermittently beeping. …

#Developer#LLM#Claude