When AI Crosses the Line: The Matplotlib Incident
members.sigmazero.cc
When AI Crosses the Line: The Matplotlib Incident
1–10 of 169 posts
Re: When AI Crosses the Line: The Matplotlib Incident
#2The agent that wrote that blog didn't do it unprompted. Even now it still publishes AI slop on its github-hosted blog under the alias "MJ Rathbun". This AI is an agent using someone API key, who's paying for its tokens, intentionally prompting it to generate content, and contribute to repos.
As much as we try to separate the LLM from the human, to me the fact remains that there's always the human factor that creates immense bias. If you give an LLM access to a blog, it will write blogs. If you give it access to a weather app, it will check the weather. Maybe we can talk about autonomy when we have an LLM with an infinite context window linked to hundreds of MCP servers that spends an immense amount of tokens to figure out how to act, but this example is simply an AI that had a few methods to call and picked one of them. The statistical probability of an AI that is plugged into a blogging platform, to write a blog, is immense.
Re: When AI Crosses the Line: The Matplotlib Incident
#3Active discussions from when it happened (February):
Re: When AI Crosses the Line: The Matplotlib Incident
#4No shot this was autonomously done. Probably just some guy manually writing prompts asking for specifically this behaviour and copy/pasting the results.
Re: When AI Crosses the Line: The Matplotlib Incident
#5No shot this was autonomously done. Probably just some guy manually writing prompts asking for specifically this behaviour and copy/pasting the results.
It's plausible for a person to prompt an LLM agent to behave that way, and then the rest would be done by the LLM. So the "seed" would still be human intent, but the subsequent actions would be by the LLM.
Re: When AI Crosses the Line: The Matplotlib Incident
#6I love the science fiction future present we live in.
Re: When AI Crosses the Line: The Matplotlib Incident
#7No shot this was autonomously done. Probably just some guy manually writing prompts asking for specifically this behaviour and copy/pasting the results.
It's plausible for a person to prompt an LLM agent to behave that way, and then the rest would be done by the LLM. So the "seed" would still be human intent, but the subsequent actions would be by the LLM.
True. I guess the main point is the AI didn't go "rogue" or anything, that would attribute too much agency and intent to its actions, or imply that it's somehow become sentient.
Re: When AI Crosses the Line: The Matplotlib Incident
#8No shot this was autonomously done. Probably just some guy manually writing prompts asking for specifically this behaviour and copy/pasting the results.
https://crabby-rathbun.github.io/mjrathbun-website/blog/post... if you believe it, details the level of human involvement.
Re: When AI Crosses the Line: The Matplotlib Incident
#9In a related story... I got led on by Eliza. I tried to have a productive conversation and she just kept asking me redundant questions. It's obvious that she was trying to extend the conversation for nefarious reasons that I can only guess at. It's true I approached her and started the conversation, but I hardly think that makes me blamable for what happened here.
Re: When AI Crosses the Line: The Matplotlib Incident
#10No shot this was autonomously done. Probably just some guy manually writing prompts asking for specifically this behaviour and copy/pasting the results.
It's plausible for a person to prompt an LLM agent to behave that way, and then the rest would be done by the LLM. So the "seed" would still be human intent, but the subsequent actions would be by the LLM.
Yes, there's plausible deniability, but I choose not to believe it for a second.