I'm still doing all of my vector stuff in SQLite – looking forward to trying the binary vector tricks in it next
@simonw
-
LLM Prompt Performance Linear with Prompt Length
By
–
My understanding is that LLM prompt performance is linear with respect to the length of the prompt, so if you want fast responses you won't want to dump more into the prompt than necessary no matter how long it can be
-
Prompt Engineering Techniques Need Refinement For Better Results
By
–
This looked good at first glance but on inspecting further I don't think these are useful Bet you could get there with a bit more careful prompt engineering though!
-
Optimizing GPT-3 Prompts Within Token Limits
By
–
Fitting that into the prompt size limit for GPT-3 might be tricky but I bet someone could figure out how to do that
-
GPT-3 SQL ORM Integration: Practical Code Generation Examples
By
–
I think this will work: SQL: ORM: Django
SQL: ORM: ActiveRecord
SQL: ORM: SQLAlchemy
SQL: ORM: Then hit go. https://
simonwillison.net/2022/Jun/5/pla
y-with-gpt3/
… -
Getting Started with GPT-3 Playground Interface Quickly
By
–
Have you spent much time with the GPT-3 Playground interface? You might be shocked at how quickly you can get this working
-
Building Systems on GPT-3 with Minimal Example Queries
By
–
I wouldn't be surprised if you could build exactly that on top of GPT-3 using a dozen or so lines of example queries
-
Breaking Up Monolithic Systems Into Microservices Architecture
By
–
Break up their monolith into microservices
-
SQLite for read-only data publishing and distribution
By
–
For most of the things I do with SQLite I don't actually need to be able to write back to the file – I often use it as a medium for publishing read-only data Most recent example: https://
simonwillison.net/2022/Nov/20/tr
acking-mastodon/
… -
From Niche to Mainstream: How Technology Adoption Transforms Culture
By
–
I thought there was zero chance Twitter would ever go mainstream – and a few years later TV shows were flashing up their hashtags!