Simon Willison’s Weblog


Wednesday, 29th May 2024

In their rush to cram in “AI” “features”, it seems to me that many companies don’t actually understand why people use their products. [...] Trust is a precious commodity. It takes a long time to build trust. It takes a short time to destroy it.

Jeremy Keith # 11:06 am

Training is not the same as chatting: ChatGPT and other LLMs don’t remember everything you say

I’m beginning to suspect that one of the most common misconceptions about LLMs such as ChatGPT involves how “training” works.

[... 1543 words]

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.

# 8:59 am

Sometimes the most creativity is found in enumerating the solution space. Design is the process of prioritizing tradeoffs in a high dimensional space. Understand that dimensionality.

Chris Perry # 7:17 am