Simon Willison’s Weblog

Semantic text search using embeddings. Example Python notebook from OpenAI demonstrating how to build a search engine using embeddings rather than straight up token matching. This is a fascinating way of implementing search, providing results that match the intent of the search (“delicious beans” for example) even if none of the keywords are actually present in the text.

# 9th November 2022, 7:57 pm / machine-learning, search, openai, embeddings

Text Embedding Models Contain Bias. Here’s Why That Matters (via) Excellent discussion from the Google AI team of the enormous challenge of building machine learning models without accidentally encoding harmful bias in a way that cannot be easily detected.

# 17th April 2018, 8:54 pm / ethics, google, machine-learning, ai, generative-ai, embeddings, ai-ethics, ai-bias