I've been wanting this for ages! Means you can accurately account for the cost of streaming API calls to the OpenAI APIs
@simonw
-
Google Infrastructure Maintenance Challenges Impact Product Lifecycle
By
–
I imagine it also fell victim to the thing where everything at Google needs to be upgraded to the latest infrastructure every few years, and nobody wanted to do the work
-
Datasette Enrichments Tool Demonstration Platform
By
–
Actually this is a more relevant demo https://
simonwillison.net/2023/Dec/1/dat
asette-enrichments/#demonstrating-enrichments
… -
datasette-enrichments-gpt: AI-powered CSV data enrichment in SQLite
By
–
My datasette-enrichments-gpt plugin is good for that – you can import CSV into SQLite and then use that plugin to run different prompts against the tabular data and store the results Demo here: https://
simonwillison.net/2024/Apr/17/ai
-for-data-journalism/#enriching-data-in-a-table
… -
GitHub Actions TODO List System for Daily Task Management
By
–
I have a daily TODO list system I built on top of GitHub Actions and GitHub Issues
-
RAG versus fine-tuning: Understanding key AI training approaches
By
–
That sounds like RAG, not fine-tuning
-
SQLite-utils tool for extracting strings into lookup tables
By
–
I wrote a tool for pulling strings like that out into a lookup table https://
sqlite-utils.datasette.io/en/stable/cli.
html#cli-extract
… -
Fine-tuning Models with New Data: Demonstrating Practical Capabilities
By
–
I'm ready to believe fine-tunes can do useful things with new facts from their fine-tuning data… but I need to first interact with a working demo to get there!
-
Selective Model Weight Updates for Production AI Systems
By
–
Definitely a promising direction, but it doesn't look to me like that technique is useful for production scenarios yet Being able to selectively update model weights to tell a model "the new CEO of Fiat is X" would indeed be incredibly useful if it was fully reliable
-
Gorilla: Fine-tuning LLM capabilities for improved function calling
By
–
This Gorilla? That looks like fine-tuning for improved capabilities like function calling, not for baking in extra knowledge https://
gorilla.cs.berkeley.edu