Bellevue Library AI Safety Meetup

Date: July 20th, 2024

Location: Bellevue Library, Bellevue, WA

Description:

Hi folks! We’re hosting an open to the public, completely free AI safety meetup. In it we’ll be building and analyzing an LLM from scratch as well as going over governance and legislation issues for dealing with the dangers of modern AI.

The session is meant for both coders and people who have no coding background! It will be a session of one or two talks, followed by a lot of small group discussion and hands-on coding, depending on people’s backgrounds.

For everyone we’ll be kicking off with a gentle introduction to both the state of AI today as well as probable new events on the horizon and a lot of safety problems that those can cause.

We will split participants by background and interest into three groups:

For those of you who have no technology background, not to fear! We’ll have readings and discussions around problems with current and near-future AI technology as well as potential governance and policy solutions to deal with those problems. We’ll focus in particular on understanding what it would mean to pause AI development before AI becomes extremely dangerous and what necessary steps for that would look like.

For those who are coders, and especially those who are familiar with Python and have some experience with numerical libraries such as NumPy or PyTorch and some minor experience with ML, but otherwise have no experience building an LLM, we’ll have content where we build GPT-2 from scratch over the course of the day!

For those who have indeed built their own LLMs in the past and are curious about potentially diving even deeper into understanding them, especially from a safety perspective, we’ll have content focusing mainly on cracking open the black box and understanding what’s going on under the hood, with a focus on techniques pioneered by the “A Mathematical Framework for Transformer Circuits” paper from Anthropic.

Depending on attendance, we may split those groups into even smaller groups, to make sure that everyone has the opportunity to develop some hands-on experience with the material.

We have a long amount of time scheduled because the technical content, such as building GPT-2, is fairly time-intensive. However, if you are short on time, and especially if you would like to do the technical content, we would recommend that you generally show up close to the start time and leave early rather than vice versa (although we’ll still be happy to have you either way). The non-technical content will be a little more amenable to starting in the middle, as there will be more independent chunks that people can drop in and out for.

If you’re planning to code, we would highly recommend bringing your own computer (the library will have computers, but it is often easier to code with software you already are familiar with).

If you are planning on attending, we ask that you fill out this form so we can better gauge interest for each track: https://docs.google.com/forms/d/e/1FAIpQLSdEHSvimDluhOQp8PuZPWOTIqtqjiV3xOCPzCt-Y9r9CUfb-g/viewform?usp=sf_link