Building A Generative AI Platform

Chip Huyen · 25 Jul 2024 · huyenchip.com ↗

3 korrents from this piece

Chip Huyen did not write this page.

Every claim below was made in this piece, quoted word for word and numbered in the order the piece makes them, so you can read it there rather than take our word for it. The sentence above each quote is our reading of the claim, not their wording. Each quote was checked against a stored copy of the page at build time; where the two differ, the quote is the fact.

Our reading
Preparing context for a language model plays the same role that feature engineering played for classical machine learning models.

Their wordsContext construction for foundation models is equivalent to feature engineering for classical ML models.
Our reading
In-context learning is a form of continual learning for language models.

Their wordsIn-context learning, learning from the context, is a form of continual learning.
Our reading
The probabilistic nature of AI models makes their outputs inherently unreliable.

Their wordsAI models are probabilistic, making their outputs unreliable.