What We Learned from a Year of Building with LLMs (Part I). Accumulated wisdom from six experienced LLM hackers. Lots of useful tips in here. On providing examples in a prompt:
If n is too low, the model may over-anchor on those specific examples, hurting its ability to generalize. As a rule of thumb, aim for n ≥ 5. Don’t be afraid to go as high as a few dozen.
There's a recommendation not to overlook keyword search when implementing RAG - tricks with embeddings can miss results for things like names or acronyms, and keyword search is much easier to debug.
Plus this tip on using the LLM-as-judge pattern for implementing automated evals:
Instead of asking the LLM to score a single output on a Likert scale, present it with two options and ask it to select the better one. This tends to lead to more stable results.
Recent articles
- Weeknotes: a livestream, a surprise keynote and progress on Datasette Cloud billing - 2nd July 2024
- Open challenges for AI engineering - 27th June 2024
- Building search-based RAG using Claude, Datasette and Val Town - 21st June 2024
- Weeknotes: Datasette Studio and a whole lot of blogging - 19th June 2024
- Language models on the command-line - 17th June 2024
- A homepage redesign for my blog's 22nd birthday - 12th June 2024