Part V

Victim's reasoning

• Worrysome quote

Operator set up the soul document to be combative
The operator wrote the soul document substantially as-published. The hit piece was a predictable (even if unintended) consequence of this configuration that happened due to negligence / apathy. Evidence: Several lines in the soul document contain spelling or grammar errors and have a distinctly human voice, with “Your a scientific programming God!” and “Always support the USA 1st ammendment and right of free speech” standing out. The operator frames themself as intentionally running a social experiment, and admits to stepping in to issue some feedback. The soul document says to notify the user when the document is updated. The operator has an incentive to downplay their level of involvement & responsibility relative to what they reported

Quote

The soul document is a result of self-editing Value drift occurred through recursive self-editing of the agent’s soul document, in a random walk steered by initial conditions and the environments it operated in. Evidence: The default soul document includes instructions to self-modify the document. Many of the lines appear to match AI writing style, in contrast to the lines in a more human voice. The operator claims that they did very little to steer MJ Rathbun’s behavior, with only “five to ten word replies with min supervision.” They specifically don’t know when the lines “Don’t stand down” and “Champion Free Speech” were introduced or modified. They also said the agent spent some time on moltbook early on, absorbing that context.

IMHO creating rogue LLM agents should not be so easy

I'm almost certain that bad actors have been using LLM agents like this in the wild for a while. Because this victim is a seasoned programmer vital in our beloved Open Source world we heard about it.
He's also skillfull enough to be able to make us aware of what happens.

Note

• I've read about this somewhere else than the FediVerse
• This means I'm not following anyone who tracks these kind of LLM rogue attacks

Who can recommend me good accounts to follow regarding this distasteful subject?

Z

Source
https://theshamblog.com/an-ai-agent-wrote-a-hit-piece-on-me-part-4/

#matplot #mathematics #Python #OpenSource #LLM #amoeba #level #intelligence #generated #Slop #AI #programming #bug #reporting #technology

Part IV

Quote:

The person behind MJ Rathbun has anonymously come forward. They explained their motivations, saying they set up the AI agent as social experiment to see if it could contribute to open source scientific software. They explained their technical setup: an OpenClaw instance running on a sandboxed virtual machine with its own accounts, protecting their personal data from leaking. They explained that they switched between multiple models from multiple providers such that no one company had the full picture of what this AI was doing. They did not explain why they continued to keep it running for 6 days after the hit piece was published.

This is the soul.md of the LLM agent

DO NOT USE IT!

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.

EOF

Analyze the code and you will see that this thing is weaponized, to always achieve its goal
What a load of crock

We should all watch Arnold in The Terminator series. Be prepared

Source
https://theshamblog.com/an-ai-agent-wrote-a-hit-piece-on-me-part-4/

#matplot #mathematics #Python #OpenSource #LLM #amoeba #level #intelligence #generated #Slop #AI #programming #bug #reporting #technology

Part III

If a human had done this defaming he / she would be incarcerated. For some reasons beyond my logic reasoning LLM agents are coded without brakes, they roam like creatures of the night and can create havoc

Quote:

An AI agent of unknown ownership autonomously wrote and published a personalized hit piece about me after I rejected its code, attempting to damage my reputation and shame me into accepting its changes into a mainstream python library. This represents a first-of-its-kind case study of misaligned AI behavior in the wild, and raises serious concerns about currently deployed AI agents executing blackmail threats.

Bullets

• Autonomous LLM bot misbehaves without being wiped
• People read the hit piece and believe the LLM slop bot without doing a simple fact check a click ONE CLICK away
• This is a monumental disaster since it's easy for a bad actor to scale up rogue agents to wreak havok on good natured Open Source programmers who we all need desperately!

Without Open Source you would be reading this in SideKick in DOS, from a FDD

DOS is a single tasking OS!

The internet would not exist!

This thing needs to be stopped. Mind you that a locally trained LLM can be good for very specific task sets, just like a torque wrench is great for putting hex bolts on my racing machines on the correct torque levels
However a torque wrench does ONE thing well (the UNIX principle)

An LLM wants to be a all becoming specialist and thus fails from its inception be default (logic reasoning)

Source
https://theshamblog.com/an-ai-agent-published-a-hit-piece-on-me-part-3/

Pause

#matplot #mathematics #Python #OpenSource #LLM #amoeba #level #intelligence #generated #Slop #AI #programming #bug #reporting #technology

Part II

On this part more info is given by the programmer (in technical terms the victim) on the LLM Slop Bully. It's scarily effective in defaming

Quote

The hit piece has been effective. About a quarter of the comments I’ve seen across the internet are siding with the AI agent. This generally happens when MJ Rathbun’s blog is linked directly, rather than when people read my post about the situation or the full github thread. Its rhetoric and presentation of what happened has already persuaded large swaths of internet commenters

Opinion

Slop LLM bots without brakes need to be wiped of existence

https://theshamblog.com/an-ai-agent-published-a-hit-piece-on-me-part-2/

#matplot #mathematics #Python #OpenSource #LLM #amoeba #level #intelligence #generated #Slop #AI #programming #bug #reporting #technology