Claude and ChatGPT for ad-hoc sidequests

Four new models that are benchmarking near or above GPT-4

Running OCR against PDFs and images directly in the browser

Google Scholar search: "certainly, here is" -chatgpt -llm

Interesting ideas in Observable Framework

Prompt injection and jailbreaking are not the same thing

The killer app of Gemini Pro 1.5 is using video as an input

CLI tools hidden in the Python standard library

Running Ethernet over existing coaxial cable

Stuff we figured out about AI in 2023

It's OK to call it Artificial Intelligence

Many options for running Mistral models in your terminal using LLM

The AI Trust Crisis

Catching Up with the Cosmopolitan Ecosystem

Datasette Enrichments: a new plugin framework for augmenting your data

Llamafile is the new best way to run a LLM on your own computer

Documentation unit tests

Deciphering clues in a news article to understand how it was reported

Summing columns in remote Parquet files using DuckDB

Exploring GPTs: ChatGPT in a trench coat?

Embeddings: What they are and why they matter

Now add a walrus: Prompt engineering in DALL-E 3

Multi-modal prompt injection image attacks against GPT-4V

Serving a custom vector web map using PMTiles and maplibre-gl

Things I've learned about building CLI tools in Python

Geospatial SQL queries in SQLite using TG, sqlite-tg and datasette-sqlite-tg

Notes from building a blog in Django

LLM Python/CLI tool adds support for embeddings

Run Llama 2 on your own Mac using LLM and Homebrew

Downloading partial YouTube videos with ffmpeg

More →