You’re an experienced software engineer who’s ready to start contributing to making AI go well. You’re unsure which of these three areas you’re best placed to leverage your engineering skills:
Scale AI safety research
Build tools for AI safety researchers
Contribute directly to AI safety research
This guide walks through a project you can complete in <1 week to make your first contribution.
This blog post was written for graduates of BlueDot’s Technical AI Safety course who want to contribute their software engineering skills.
Why do a project?
Projects also help you figure out where to apply your skills. Does your GPU experience apply to training infrastructure? Does your agent scaffolding experience translate to evals? You’ll learn more from trying than from months of deliberation.
If you find a gap you can fill, it could lead you to orgs doing that work — or inspire you to start something yourself.
When applying to AI safety roles, this project could also serve as a helpful signal for your skills and motivation. A well-executed project can help demonstrate clear reasoning, good communication, and high agency. I’ve spoken to several hiring managers who made offers or fast-tracked candidates because of excellent projects.
While you could complete a project through programs and fellowships which provide more structure, mentorship and stipends, you could also do it yourself!
You already have what it takes to start. Here’s how.
Getting started
Block out 20-40 hours in your calendar.
If you want to keep going after that, schedule more time later. Right now, focus on finishing something by the end of the week.
Schedule focused blocks.
Aim for 2-4 hour sessions where you can get “stuck in”. The more fragmented your time, the more time you’ll burn context switching.
Rope someone in to work on this with you or be accountable to.
Protect this time.
It’s easy to let social events or work meetings eat up your project hours. If this matters to you, treat these blocks like any other important commitment.
Make a calendar event for yourself!
Build a routine.
Work at the same time each day if possible.
Set a clear intention and put it somewhere you can see it. E.g. “Every day for the next 5 days, I’ll spend 4 hours working on my project at my desk.”
Choose your path
Option 1: Fix open issues in AI safety tools
Contribute to tools that AI safety researchers use every day.
Pick 2-5 good first issues to solve from an open source AI safety repo, like:
(email me if you know of more! anglilian@bluedot.org)
You can also message the maintainers, join their Discord / Slack communities or just try out the tools to figure out what needs improving.
For example, Anthony Duong looked at the issues on TransformerLens and spent a few weekends making PRs.
Option 2: Replicate and extend a research finding
Get closer to research by reproducing and extending a published result.
The goal is to reproduce and add a small tweak to ONE interesting finding from a paper.
Some ideas for picking a starting point:
Reviewing the resources from the Technical AI safety course
Replicate and extend Anthropic’s alignment faking demo
Pick an open problem in evals
If you want to spend closer to 20 hours on the project, pick papers that have code (and datasets if applicable) available for you to run. Otherwise, expect to spend a lot more time working out how to implement the code.
Replicating a finding from scratch is more feasible for papers like evals or elicitation techniques that don’t require deep ML expertise.
Don’t get too bogged down with trying to make a novel research contribution. It takes months to develop good research taste. Instead, follow where your curiosity leads you. Then, pick the smallest version of that question you can answer. Remember, this is meant to be a short project. You can always build on this in your next iteration.
If funding becomes a constraint, you can apply for a small grant as a BlueDot course graduate.
Option 3: Make research reproducible
Unblock other researchers by fixing what’s broken in the replication process
Many published papers are hard to replicate because the code is buggy, dependencies are missing, or the workflow is unnecessarily painful.
Your goal is to pick a paper with available code, try to run it, and fix whatever breaks or makes it painful to work with.
This could mean:
Fixing broken code or missing dependencies
Writing clearer setup instructions or documentation
Building micro-tooling for repetitive, manual steps (e.g., a script for dataset preprocessing, a config manager for hyperparameters, or a notebook that visualises results)
Packaging the reproduction in a way that “just works” for the next person
Focus on making it easy for everyone who comes after you to build on it. By the end, you should have opened a PR or created an issue that ideally gets merged! .
Document and share
As you work through your project, track:
What you set out to do
What you accomplished
What you learned
Where you’ll go next
Your final write-up doesn’t need to be formal, but it should be clear.
Then, pin this project on your GitHub, post it on a platform with reach (e.g. LessWrong, the Alignment Forum, LinkedIn) and start talking to people about it!
Many of our past graduates have found their co-founders, collaborators, roles, funding opportunities and friends from posting their projects.
So what are you waiting for? Let’s get started!
The open problems in mech interp blog from 2022 is now sadly out-of-date