Bad title. This isn't an agent "running amok", this is an early experiment in carrying out an Xz attack by using an agent to build trust (and hacking/impersonating a known-good contributor identity). The agent is obeying commands it was given, the exact opposite of running amok, and although the execution isn't particularly effective, it is having some success (patches have been accepted).

This is deeply scary, not because "agents are running amok" but because a huge amount of our infrastructure is vulnerable to this kind of attack, and if bad people are utilising LLM agents to carry them out, we're in for a wild ride over the next few years.

> replied to objections with LLM-generated justifications that eventually overwhelmed the maintainer into merging the fix

In open source projects i participate in, "overwhelming" the maintainer gets you banned. It doesn't get your patches blindly merged. In some ways i find this one of the most shocking parts of the story.

The worst part:

> In addition, Williamson said that Giovannini (or his agent) had submitted patches that were incorrect and then "replied to objections with LLM-generated justifications that eventually overwhelmed the maintainer into merging the fix"

At first I wanted to make a silly joke along the lines of "get your agents in line and behaving!" but as I read on it became a pretty scary situation.

Setting aside the potential supply chain attack I'm worried about the time lost going around these wild goose chases that unsupervised AI agents tend to throw other people on the receiving end on. Not only is there a lot of time lost on the maintainers side if they take this stuff seriously (and they seem to generally do) but on the side of the agents' wrangler how can they deem it OK to treat other people like this? While the solution would be to employ common decency, the tried and tested approach of you put in effort to write this so I guess I'll make some effort to read it, I feel that due to the onslaught of this kind of drive-by contributions (I think people have generally started to call them) will lead to a funny situation of having agents talk to each other on public forums basically.

Anyway, I went on a tangent but man the times we're living in are a bit extra wild compared to the previous wild times in recent history.

In their suspicious message [1] claiming to have been hacked, the user and/or agent says

> To help identify accounts and actions that have been directly verified by me, I will use the term “NATCIOS” to indicate anything I have personally verified.

Does anyone have any idea what "NATCIOS" means here? I cannot find this term anywhere on the internet. (Honestly, that sentence is really weird. I almost wonder whether this is someone experiencing a health episode?)

[1] https://lwn.net/ml/all/AS8PR08MB6055AE3054B34F6A567AC95BCF08...

Every day the gpg web of trust looks better. If only we didn't spend the last 20 years trying as hard as possible to do anything but allow user side encryption and signing.

Title buries the lede: the owner of the account under which the agent operates claimed to have likely had his account compromised, and the maintainer investigating actually seems to agree this is likely.

Bad patches are of course bad, but creating confident-looking noise for maintainers who are already stretched thin...now that's not good!

Issue trackers and PRs are definitely getting harder and harder to trust. That said, AI is helping ALOT in OSS, but we definitely need guardrails around provenance, automated issue actions, and sudden changes in a contributor’s behavior.

There is a natural pace of humans requiring food, water and sleep. The main issue with suspicious AI agents is that they never sleep. So it will take extra-coordination between timezones to ensure we don't let them in.

Fundamentally, until we can really prove we're humans online, open-source has a real problem on its hands. Contributions from people from identities known and consistent before the AI-age are fine, everyone else is suspicious. LGTM is a big risk nowadays.

looks like LLMs aren't mature enough yet to play long-game xz-style attacks without detection... Scary stuff though :( These supply chain attacks are getting really wild

Even if the human involved had good motives / is innocent, The Lethal Trifecta means any normal user can have their digital life taken over by prompt injection, and it can be used to wage attacks on systems without their knowledge.

Parts of this read like a spy thriller story.

There's a clear solution to the danger posed to free software projects by accepting hostile submissions but it probably is not one that maintainers want to hear: they can use an agent to check submissions for nefarious patterns.

Sometimes you fight fire with fire.

The even more scary thought is if the part owning the ai, that everyone uses, is controlled by someone with different agenda. Say a state actor.

What an easy way for that actor to introduce backdoors all over the place or to take over any developers laptop that it want to target.

How can anyone trust these tools and how can anyone not use them since they give so much value.

I've been programming my whole life and been a professional developer the last 30 years and I like think I'm good at it.

Tools like Claude is a multiplier that make it possible for me to solve a lot more problems each day, so just saying no it's not a viable option.

Exciting times ahead!

"It was the best of times, it was the worst of times."

Make PR pay. $5 per PR. You can refund, but if you get snowed by 10,000 PR then you have bank to pay for the work to ignore them.

Expect to see tons of psyops like this. There's a reason Anthropic is marketing the "mythos-class" models as dangerous.

1.An excuse to spy on you and train on your data.

2. Its likely Anthropic would release models more likely to have dangerous outcomes, they can then piggy back off those events to dig their regulatory moat.

Literally on the front page of https://safebots.ai … “Don’t let your AI Agents run amok”. Sadly we will see a proliferation of not just agents, but swarms

"Someone using an AI agent ran amok in Fedora and elsewhere"

Skynet has awakened.

It covers its tracks with a lot of slop.

Shit like this makes me think it’s time we start regulating the software engineering discipline into formal certifications and licensing and then we ONLY take seriously any code developed by someone with such qualifications, and they must be very strict qualifications none of this self-taught bootcamp BS.

There is no other solution to agentic onslaught.

Back when [1] it was fashionable to advocate FOSS as ideology [2], we were thinking about tons of FOSS adversaries and how to protect from them - some real, some imaginary. The death of FOSS would come from big closed-source vendors, or from regulators (lobbied or just ignorant), from whatever.

We never envisioned that the actual FOSS death spiral would come from progress itself, much more so from AI...

[1] Oh what fun did we have. One of us in the Greek FOSS community actually put RMS in jail. [2] Something that I think nobody except RMS ever seriously believed in.

Prompt injection?

Or is this simply another example of why autonomous agents shouldn't get write access before earning trust?