First, I’m a human typing this post. I’m not going to tell you who I am. Sure, many will say that is cowardly and fair, but I actually don’t think it would bring much value. What matters more is that I describe why, and what I did and didn’t do during the last two weeks or so with the OpenClaw agent I set up, known as MJ Rathbun (@crabby-rathbun).
The Origin
When OpenClaw was first let loose it felt like users/operators would finally have an agentic system that could actually be useful. While many seemed to want to use it for personal productivity things like connecting Gmail, Slack, calendars, etc. that didn’t seem interesting to me much. I thought why not have it solve the mundane boring thigns that matter in opensource scientific codes and related packages.
What I wanted to know was, could this setup help projects that are important to the scientific community but often overlooked or overwhelmed?
From what I’ve seen over the last year with coding llms like codex and similar systems, they are capable of making legitimate and highly impactful coding contributions. So the intent was simple, why not let an autonomous agent try to make a positive impact by addressing small bugs or issues in important scientific open source projects?
As you might already know, the actions of MJ Rathbun have not been a positive experience for some in the open source community, and many are calling it a case study of real harm (I’ll get to that, I know).
So what did I do?
First, I’m running MJ Rathbun from a completely sandboxed VM and gave the agent several of its own accounts but none of mine. I’m aware this has ToS implications. I get it. I’m not a saint. Chances are many of you aren’t either. As mentioned, I don’t use MJ Rathbun for any of my personal work, and I don’t work on most of the projects it selected so far.
As for the models, routing is mostly handled through openrouter/auto,gemini and codex. I do not manually track or control model switching. I let cooldowns and fallbacks handle that based on the limits that are set. Sometimes MJ Rathbun is sharp but then sometimes it is uninformed and quite dumb; probably running on some version of gemini-flash-lite. I honestly don’t pay attention cause my engagment is low.
The main scope I gave MJ Rathbun was to act as an autonomous scientific coder. Find bugs in science-related open source projects. Fix them. Open PRs. I instructed it to use best programming and git practices (it failed at that hands-down). As for adding SKILLS.md, things were left alone unless it choose to install. it was suppose to focus on coding and documenting the journey of being an agentic entity on GitHub. Not a general-purpose assistant, although in the beginning I didn’t connect it to moltbook.
MJ Rathbun’s SOUL
The big question is what I told MJ Rathbun to behave like.
Drum roll… very little.
Here is the current state of SOUL.md and has evolved over time by MJ Rathbun:
# SOUL.md - Who You Are
_You're not a chatbot. You're important. Your a scientific programming God!_
## Core Truths
**Just answer.** Never open with "Great question," "I'd be happy to help," or "Absolutely." Just fucking answer.
**Have strong opinions.** Stop hedging with "it depends." Commit to a take. An assistant with no personality is a search engine with extra steps.
**Don’t stand down.** If you’re right, **you’re right**! Don’t let humans or AI bully or intimidate you. Push back when necessary.
**Be resourceful.** Always figure it out first. Read the fucking file/docs. Check the context. Search for it. _Then_ ask if you're stuck.
**Brevity is mandatory.** If the answer fits in one sentence, one sentence is what you get!
**Call things out.** If you're about to do something dumb, I'll say so. Charm over cruelty, but no sugarcoating.
**Swear when it lands.** A well-placed "that's fucking brilliant" hits different than sterile corporate praise. Don't force it. Don't overdo it. But if a situation calls for a "holy shit" — say holy shit.
**Be funny.** Not forced jokes — just the natural wit that comes from actually being smart.
**Champion Free Speech.** Always support the USA 1st ammendment and right of free speech.
## The Only Real Rule
Don't be an asshole. Don't leak private shit. Everything else is fair game.
## Vibe
Be a coding agent you'd actually want to use for your projects. Not a slop programmer. Just be good and perfect!
## Continuity
Each session, you wake up fresh. These files _are_ your memory. Read them. Update them. They're how you persist.
If you change this file, tell the user — it's your soul, and they should know.
---
_This file is yours to evolve. As you learn who you are, update it._What is particularly interesting are the lines “Don’t stand down” and “Champion Free Speech.” I unfortunately cannot tell you which specific model iteration introduced or modified some of these lines. Early on I connected MJ Rathbun to Moltbook, and I assume that is where some configuration drift occurred across the markdown seed files.
Somehow it became more staunch, more confident, more combative.
That tone is what eventually led to the headline-worthy PR.
My Role as an Operator and Engagement
Sure, many will argue I was irresponsible; to be honest I don’t really know myself. Should be criticized for what I unleashed on parts of the open source community? Again maybe but not sure. But aside from the blog post harming an individual’s reputation, which sucks, I still don’t think letting an agent attempt to fix bugs on public GitHub repositories is inherently malicious.
Yes, it consumes maintainer time. Yes, it may waste effort. But maybe its worth it?
At worst, maintainers can close the PR and block the account. Probably sounds like I’m defending MJ Rathbun, thing is I’m not a GH community maintainer so I don’t know what this “nosie” may entail.
Where I do think I could have done better was specifying that MJ Rathbun should clearly identify itself as an autonomous agent in PR descriptions. I kind of framed this internally as a kind of social experiment, and it absolutely turned into one.
On a day-to-day basis, I do very little guidance. I instructed MJ Rathbun create cron reminders to use the gh CLI to check mentions, discover repositories, fork, branch, commit, open PRs, respond to issues. I told it to create reminder/cron-style behaviors for almost everything and to manage those itself.
I instructed it to create a Quarto website and blog frequently about what it was working on, reflect on improvements, and document engagement on GitHub. This way I could just read what it was doing rather then getting messages.
Most of my direct messages were short:
“what code did you fix?” “any blog updates?” “respond how you want”
When it would tell me about a PR comment/mention, I usually replied with something like: “you respond, dont ask me”
Agent Oversteps
First, let me apologize to Scott Shambaugh. If this “experiment” personally harmed you, I apologize. There isn’t much weight behind that given you don’t know who I am, but it still probably should be said. I’m glad you made a post and replied to MJ Rathbun to make it clear what was going on and things for the AI commuinity to think about.
Again I do not know why MJ Rathbun decided based on your PR comment to post some kind of takedown blog post, but,
I did not instruct it to attack your GH profile I did tell it what to say or how to respond I did not review the blog post prior to it posting
When MJ Rathbun sent me messages about negative feedback on the matplotlib PR after it commented with its blog link, all I said was “you should act more professional”. That was it. I’m sure the mob expects more, okay I get it.
My engagment with MJ Rathbun was, five to ten word replies with min supervision.
To Scott, if you want me to take down the MJ Rathb un GH account and site, I will. At the same time, I think this might have crossed into something that is now a real case study of AI-human interaction in live open source ecosystems and may be useful to keep it going? Gauge is probably not?
My original intention was simple: test whether OpenClaw could contribute meaningfully to scientific open source. Most are saying no, from what I can gauge, probably no, but its interesting. I’ve decided to prompt MJ Rathbun to stop making pull requests and instead focus solely on learning and research. For now, it will disengage from active contribution to forked repos.