Simon Willison’s Weblog

Subscribe

Items tagged aiassistedprogramming, datasette in 2023

Filters: Year: 2023 × aiassistedprogramming × datasette × Sorted by date


What’s in the RedPajama-Data-1T LLM training set

RedPajama is “a project to create leading open-source models, starts by reproducing LLaMA training dataset of over 1.2 trillion tokens”. It’s a collaboration between Together, Ontocord.ai, ETH DS3Lab, Stanford CRFM, Hazy Research, and MILA Québec AI Institute.

[... 1077 words]

sqlite-history: tracking changes to SQLite tables using triggers (also weeknotes)

In between blogging about ChatGPT rhetoric, micro-benchmarking with ChatGPT Code Interpreter and Why prompt injection is an even bigger problem now I managed to ship the beginnings of a new project: sqlite-history.

[... 1680 words]

I built a ChatGPT plugin to answer questions about data hosted in Datasette

Yesterday OpenAI announced support for ChatGPT plugins. It’s now possible to teach ChatGPT how to make calls out to external APIs and use the responses to help generate further answers in the current conversation.

[... 1801 words]