Keeping with the erosion of humanity, I watched Villeneuve’s Blade Runner 2049 (2017). My bias is at play, but it did a good job of exploring LLM-like intelligence. The way Joi would follow commands, inferring what K Joe wanted and instantly pivoting: “I don’t want to read either”.

Another deep theme in the context of the LLMs, one well dissected by 2049, is reproduction. Neither the replicants nor LLMs are able to procreate, and I believe has profound impacts on their “values”. We’re shaped by natural selection and it’s harsh demands. The movie specifies birth, not intelligence, as a point of transcendence.

Some useful LLM access

OpenAssistant has whipped up the most impressive LLaMa derivative I’ve interacted with so far. Here’s to them pushing the envelope with an open approach, and here’s their interface.

Also, Azure OpenAI is available if you apply, and offers GPT-4 via an API with excellent documentation. I see what the Microsoft $10B is paying for.

Exercise

I’m going to stop tracking each exercise here. It’s totally redundant with the strong android app I use, and is still too manual to write. It’s working for me as a tracking app and while I’d like to build my own, this is one I can save for the AI’s

Watched the Azerbaijan F1 quali this morning. Ooolala Leclerc snatching pole from the Red Bulls – fellow loves his Baku.

I got access to OpenAI’s GPT-4 API and an alpha of the plugin interface today. The plugins tools seem to 1) use a custom model, and 2) still be incredibly [alpha] slow. I’ll be looking to develop a plugin of my own to get smart with the technology, though still figuring out what’d be the best integration 🤔

Driving back home tomorrow after work – returning to snoot and berry and some beautiful weather.

I’ve done a good job getting workouts in every morning this week, though the ribs are still blocking bench press. The early wakeups are because I have roomies but getting the whole morning is full early bird.

My curiosity is well-piqued to g

LLM: Using GPT-4 to query a site

Here’s a quick incantation to use GPT-4 to ask questions about a site.

First off, you need a Python environment with these dependencies installed (assuming an environment is set up using poetry):

poetry add langchain beautifulsoup4 nest_asyncio ipython
poetry run ipython

Using langchain, load all pages referenced in this site’s sitemap.xml into a vector index.

import os
from langchain.document_loaders.sitemap import SitemapLoader
from langchain.indexes import VectorstoreIndexCreator

os.environ["OPENAI_API_KEY"] = "..."

sitemap = "https://jtmoulia.srht.site/sitemap.xml"
sitemap_loader = SitemapLoader(web_path=sitemap)
index = VectorstoreIndexCreator().from_loaders([sitemap_loader])

# And now the site's vector index can be queried
index.query("When was I last in LA?")

Note: this will cost ~0.14c using OpenAI’s GPT-4 interface. The index can be persisted.