Monday, 2nd December 2024
Simon Willison: The Future of Open Source and AI (via) I sat down a few weeks ago to record this conversation with Logan Kilpatrick and Nolan Fortman for their podcast Around the Prompt. The episode is available on YouTube and Apple Podcasts and other platforms.
We talked about a whole bunch of different topics, including the ongoing debate around the term "open source" when applied to LLMs and my thoughts on why I don't feel threatened by LLMs as a software engineer (at 40m05s).
For most software engineers, being well rounded is more important than pure technical mastery. This was already true, of course — see @patio11's famous advice "Don't call yourself a programmer" — but even more so due to foundation models. In most situations, skills like being able to use AI to rapidly prototype in order to communicate with clients to iterate on specifications create far more business value than technical wizardry alone.
PydanticAI (via) New project from Pydantic, which they describe as an "Agent Framework / shim to use Pydantic with LLMs".
I asked which agent definition they are using and it's the "system prompt with bundled tools" one. To their credit, they explain that in their documentation:
The Agent has full API documentation, but conceptually you can think of an agent as a container for:
- A system prompt — a set of instructions for the LLM written by the developer
- One or more retrieval tool — functions that the LLM may call to get information while generating a response
- An optional structured result type — the structured datatype the LLM must return at the end of a run
Given how many other existing tools already lean on Pydantic to help define JSON schemas for talking to LLMs this is an interesting complementary direction for Pydantic to take.
There's some overlap here with my own LLM project, which I still hope to add a function calling / tools abstraction to in the future.
NYTimes reporters getting verified profiles on Bluesky.
NYT data journalist Dylan Freedman has kicked off an initiative to get NYT accounts and reporters on Bluesky verified via vanity nytimes.com handles - Dylan is now @dylanfreedman.nytimes.com.
They're using Bluesky's support for TXT domain records. If you use Google's Dig tool to look at the TXT record for _atproto.dylanfreedman.nytimes.com you'll see this:
_atproto.dylanfreedman.nytimes.com. 500 IN TXT "did=did:plc:zeqq4z7aybrqg6go6vx6lzwt"
datasette-llm-usage. I released the first alpha of a Datasette plugin to help track LLM usage by other plugins, with the goal of supporting token allowances - both for things like free public apps that stop working after a daily allowance, plus free previews of AI features for paid-account-based projects such as Datasette Cloud.
It's using the usage features I added in LLM 0.19.
The alpha doesn't do much yet - it will start getting interesting once I upgrade other plugins to depend on it.
Design notes so far in issue #1.