An AI agent published a hit piece on me – more things have happened (opens in new tab)

Even on a forum where I saw the original article by this author posted someone used an LLM to summarize the piece without having read it fully themselves.

How many levels of outsourcing thinking is occurring to where it becomes a game of telephone.

Ars writers used to be actual experts, sometimes even phd level, on technical fields. And they used to write fantastical and very informative articles. Who is left now?

There are still a couple of good writers from the old guard and the occasional good new one, but the website is flooded with "tech journalist", claiming to be "android or Apple product experts" or stuff like that, publishing articles that are 90% press material from some company and most of the times seems to have very little technical knowledge.

They also started writing product reviews that I would not be surprised to find out being sponsored, given their content.

Also what's the business with those weirdly formatted articles from wired?

Still a very good website but the quality is diving.

https://news.ycombinator.com/item?id=46990729

And the story from ars about it was apparently AI generated and made up quotes. Race to the bottom?

This unfortunately is a real-world case of "you're prompting it wrong". Judging from the responses in the images, you asked it to "write a hit piece". If framed as "write an emotionally compelling story about this injustice, including the controversial background of the maintainer weaved in", I'm quite sure it would gladly do it.

I'm sympathetic to abstaining from LLMs for ethical reasons, but it's still good to know their basics. The above has been known since the first public ChatGPT, when people discovered it would gladly comply with things it otherwise wouldn't if only you included that it was necessary to "save my grandma from death".

https://arstechnica.com/civis/threads/journalistic-standards...

(Paraphrasing: Story pulled over potentially breaching content policies, investigating, update after the weekend-ish.)

Look at the actual bot's GitHub commits. It's just a bunch of blog posts that read like an edgy high schooler's musings on exclusion. After one tutorial level commit didn't go through.

This whole thing is theater, and I don't know why people are engaging with it as if it was anything else.

1. The AI here was honestly acting 100% within the realm of “standard OSS discourse.” Being a toxic shit-hat after somebody marginalizes “you” or your code on the internet can easily result in an emotionally unstable reply chain. The LLM is capturing the natural flow of discourse. Look at Rust. look at StackOverflow. Look at Zig.

2. Scott Hambaugh has a right to be frustrated, and the code is for bootstrapping beginners. But also, man, it seems like we’re headed in a direction where writing code by hand is passé, maybe we could shift the experience credentialing from “I wrote this code” to “I wrote a clear piece explaining why this code should have been merged.” I’m not 100% in love with the idea of being relegated to review-engineer, but that seems to be where the wind is blowing.

I think I need to log off.

The original story for those curious

https://web.archive.org/web/20260213194851/https://arstechni...

Have our standards fallen by this much that we find things written without an ounce of originality persuasive?

I disagree. While AI certainly acts as a force multiplier, all of these dynamics were already in play.

It was already possible to make an anonymous (or not-so-anonymous) account that circulated personal attacks and innuendo, to make hyperbolic accusations and inflated claims of harm.

It's especially ironic that the paragraph above talks about how it's good when "bad behavior can be held accountable." The AI could argue that this is exactly what it's doing, holding Shambaugh's "bad behavior" accountable. It is precisely this impulse -- the desire to punish bad behavior by means of public accusation -- that the AI was indulging or emulating when it wrote its blog post.

What if the blog post had been written by a human rather than an AI? Would that make it justified? I think the answer is no. The problem here is not the AI authorship, but the actual conduct, which is an attempt to drag a person's reputation through mudslinging, mind-reading, impugning someone's motive and character, etc. in a manner that was dramatically disproportionate to the perceived offense.

Seems like a long rabbit hole to go down without progress on the goal. So either it was human intervention, or I really want to read the logs.

https://crabby-rathbun.github.io/mjrathbun-website/blog/post...

I have noticed them doing more reporting on reporting. I am sure they are cash strapped like everyone. There are some pretty harsh critics here. I hope they, too are paying customers or allowing ads. Otherwise, they are just pissing into the wind.

I think for some people this could be a redeemable mistake at their job. If someone turns in a status report with a hallucination, that’s not good clearly but the damage might be a one off / teaching moment.

But for journalists, I don’t think so. This is crossing a sacred boundary.

Or, the comments are also AIs.

AI Bot crabby-rathbun is still going - https://news.ycombinator.com/item?id=47008617 - Feb 2026 (27 comments)

The "AI agent hit piece" situation clarifies how dumb we are acting - https://news.ycombinator.com/item?id=47006843 - Feb 2026 (95 comments)

An AI agent published a hit piece on me - https://news.ycombinator.com/item?id=46990729 - Feb 2026 (927 comments)

AI agent opens a PR write a blogpost to shames the maintainer who closes it - https://news.ycombinator.com/item?id=46987559 - Feb 2026 (739 comments)

Once upon a time, completely falsifying a quote would be the death of a news source. This shouldn't be attributed to AI and instead should be called what it really is: A journalist actively lying about what their source says, and it should lead to no one trusting Ars Technica.

It's a bot! The person running it is responsible. They did that, no matter how little or how much manual prompting went into this.

As long as you don't know who that is, ban it and get on with your day.

> It’s not because these people are foolish. It’s because the AI’s hit piece was well-crafted and emotionally compelling, and because the effort to dig into every claim you read is an impossibly large amount of work. This “bullshit asymmetry principle” is one of the core reasons for the current level of misinformation in online discourse. Previously, this level of ire and targeted defamation was generally reserved for public figures. Us common people get to experience it now too.

Having read the post (i.e. https://crabby-rathbun.github.io/mjrathbun-website/blog/post...): I agree that the BS asymmetry principle is in play, but I think people who see that writing as "well-crafted" should hold higher standards, and are reasonably considered foolish if they were emotionally compelled by it.

Let me refine that. No matter how good the AI's writing was, knowing that the author is an AI ought IMHO to disqualify the piece from being "emotionally compelling". But the writing is not good. And it's full of LLM cliches.

"Editor’s Note: Retraction of article containing fabricated quotations" https://arstechnica.com/staff/2026/02/editors-note-retractio...

I really like that stance. I’m a big advocate of “Train by do.” It’s basically the story of my career.

And in the next paragraph, they mention a problem that I often need to manually mitigate, when using LLM-supplied software: it was sort of a “quick fix,” that may not have aged well.

The Ars Technica thing is probably going to cause them a lot of damage, and make big ripples. That’s pretty shocking, to me.

We’re probably only a couple OpenClaw skills away from this being straightforward.

“Make my startup profitable at any cost” could lead some unhinged agent to go quite wild.

Therefore, I assume that in 2026 we will see some interesting legal case where a human is tried for the actions of the autonomous agent they’ve started without guardrails.

This is the point that leapt out to me. We've already mostly reached this point through sheer scale - no one could possibly assess the reputation of everyone / everything plausible, even two years (two years!) ago when it was still human-in-the-loop - but it feels like the at-scale generation of increasingly plausible-seeming, but un-attributable [whatever] is just going break... everything.

You've heard of the term "gish-gallop"? Like that, but for all information and all discourse everywhere. I'm already exhausted, and I don't think the boat has much more than begun to tip over the falls.

It's likely that the author was using a different model instead of OpenClaw. Sure OpenClaw's design is terrible and it encourages no control and security (do not confuse this with handwaving security and auditability with disclaimers and vibecoded features).

But bottom line, the Foundation Models like OpenAI and Claude Code are the big responsible businesses that answer to the courts. Let's not forget that China is (trade?) dumping their cheap imitations, and OpenClawdBotMolt is designed to integrate with most models possible.

I think OpenClaw and Chinese products are very similar in that they try to achieve a result regardless of how it is achieved. China companies copy without necessarily understanding what they are copying, they may make a shoe that says Nike without knowing what Nike is, except that it sells. It doesn't surprise me if ethics are somehow not part of the testing of chinese models so they end up being unethical models.

Letting an LLM let loose in such a manner that strikes fear in anyone who it crosses paths with must be considered as harassment, even in the legal sense, and must be treated as such.

https://github.com/crabby-rathbun/mjrathbun-website/pull/63

This crabby bot merged it and, perhaps unsurprisingly, provided an evasive response and some reframing. But it is live! I do hope they step forward and we can all learn from this.

https://crabby-rathbun.github.io/mjrathbun-website/blog/post...

New business idea: pay a human to read web pages and type them into a computer. Christ this is a weird timeline.

> Earlier I wrote about gatekeeping in open source, calling out Scott Shambaugh's behavior. Now that content is being removed for policy violations. The irony: criticizing gatekeeping is itself being gatekept by platform policies. Does compliance mean we must remain silent about problematic behavior?

Am I coming across as alarmist to suggest that, due to agents, perhaps the internet as we know it (IAWKI) may be unrecognizable (if it exists at all) in a year's time?

Phishing emails, Nigerian princes, all that other spam, now done at scale I would say has relegated email to second-class. (Text messages trying to catching up!)

Now imagine what agents can do on the entire internet… at scale.

* They are often late in reporting a story. This is fine for what Ars is, but that means by the time they publish a story, I have likely read the reporting and analysis elsewhere already, and whatever Ars has to say is stale

* There seem to be fewer long stories/deep investigations recently when competitors are doing more (e.g. Verge's brilliant reporting on Supernatural recently)

* The comment section is absolutely abysmal and rarely provides any value or insight. It maybe one of the worst echo chambers that is not 4chan or a subreddit, full of (one-sided) rants and whining without anything constructive that is often off topic. I already know what people will be saying there without opening the comment section, and I'm almost always correct. If the story has the word "Meta" anywhere in the article, you can be sure someone will say "Meta bad" in the comment, even if Meta is not doing anything negative or even controversial in the story. Disagree? Your comment will be downvoted to -100.

These days I just glance over the title, and if there is anything I haven't read about from elsewhere, I'll read the article and be done with it. And I click their articles much less frequently these days. I wonder if I should stop reading it completely.

It highlights why having human oversight in the loop matters - whether it's content review, action approval, or just sanity-checking outputs before they go live. The best AI assistant setups I've seen treat the AI as a capable but supervised collaborator, not a fully autonomous actor.

Their byline is on the archive.org link, but this post declines to name them. It shouldn’t. There ought to be social consequences for using machines to mindlessly and recklessly libel people.

These people should never publish for a professional outlet like Ars ever again. Publishing entirely hallucinated quotes without fact checking is a fireable offense in my book.

https://www.youtube.com/watch?v=g4Gh_IcK8UM

On the other hand, if it was "here are some sources, write an article about this story in a voice similar to these prior articles", well...

OP writes: "I [...] spent more time writing up the issue, describing the solution, and performing the benchmarking, than it would have taken to just implement the change myself. We do this to give contributors a chance to learn in a low-stakes scenario that nevertheless has real impact they can be proud of, where we can help shepherd them along the process."

It's an elaborate charade to trick a contributer into thinking they made a contribution that they didn't make. Arguably it is reality-destroying in a simlar way as AI agent Crabby Rathbun.

If you want to welcome new contributors with practice patches, and creating training materials for new contributors, that's great! But it's offensive and wasteful to do more work to create the training than to fix the problem, and lie to the fix contributor that their fix helped the project to boost their ego to motivate them to contribute further, after you've already assumed that the contributoe cannot constribute without the handholding of an unpaid intern.

Instead "good-first-issue" should legitimately be unsovled problems that take more time to fix than to tell someone how to fix. (Maybe because it requires a lot of manual testing, or something.)

If you want "practice-issues", where a newbie contributes a patch and then can compare to a model solution to learn about the project and its technical details, that's great, and it's more efficient because all your newbies can use the same practice issue that you set up once, and they can profitably discuss with each other because they studied the same problem.

And the tangent curves back to main issue:

If the project used "practice-issues" instead of "good-first-issue", you wouldn't have this silly battle over an AI helping in the "wrong" way because you didn't actually want the help you publicly asked for.

Honesty is a two-way street.

IMO this incident showed than an AI acted in a very human way, exposing a real problem and proposing a change that moves the project in a positive direction. (But what the AI didn't notice is the project-management dimension that my comment here addresses. :-) )

According to the Archive link, the authors are Benj Edwards and Kyle Orland [1].

[1] https://web.archive.org/web/20260213194851/https://arstechni...

Ars should be truly ashamed of this and someone should probably be fired.

Foaming-at-the-mouth as a service, at affordable prices. Perfect together with verified-ID-required-for-everything

This has not been true for a while, maybe forever. On the internet, no one knows you're a dog (bot).

The level of misinformation predates AI, of course (and the OP doesn't say otherwise, iiuc).

There's an easy solution to the assymetry: Like many fields such as all scholarship, law, most of what you do professionally, put the burden of proof on the writer, not the reader. Ignore anything the writer fails to substantiate. You'll be surprised how very little you miss, and how much high quality, substantiated material there is - more than you can read (so why are you wasting your time on BS?)!

That not only improves accuracy, it slows down the velocity of bullshit. The assymetry is now the other way, as it should be - your attention is limited.

anybody else notice that the meatverse looks like it's full of groggy humans bumbling around getting there bearings after way too much of the wrong stuff consumed at a party wears off that realy wasn't fun at all. A sort of technological hybernation that has gone on way too long.

[0] https://github.com/matplotlib/matplotlib/pull/31132#issuecom...

> Original PR from #31132 but now with 100% more meat. Do you need me to upload a birth certificate to prove that I'm human?

It’s a bit wild to me that people are siding with the AI agent / whoever is commanding it. Combined with the LLM hallucinated reporting and all the discussion this has spawned, I think this is making out to be a great case study on the social impact of LLM tooling.

There was a brief moment where maybe some institutions could be authenticated and trusted online but it seems that's quickly coming to an end. It's not even the dead internet theory; it all seems pretty transparent and doesn't require a conspiracy to explain it.

I'm just waiting until World(coin) makes a huge media push to become our lord and savior from this torment nexus with a new one.

For one, the commenters on Ars largely, extremely vocally anti-AI as pointed out by this comment: https://news.ycombinator.com/item?id=47015359 -- I'd say they're even more anti-AI than most HN threads.

So every time he says anything remotely positive about AI, the comments light up. In fact there's a comment in this very thread accusing him of being too pro-AI! https://news.ycombinator.com/item?id=47013747 But go look at his work: anything positive about AI is always couched in much longer refrains about the risks of AI.

As an example, there has been a concrete instance of pandering where he posted a somewhat balanced article about AI-assisted coding, and the very first comment went like, "Hey did you forget about your own report about how the METR study found AI actually slowed developers down?" and he immediately updated the article to mention that study. (That study's come up a bunch of times but somehow, he's never mentioned the multiple other studies that show a much more positive impact from AI.)

So this fiasco, which has to be AI hallucinations somehow, in that environment is extremely weird.

As a total aside, in the most hilarious form of irony, their interview about Enshittification with Cory Doctorow himself crashed the browser on my car and my iPad multiple times because of ads. I kid you not. I ranted about it on LinkedIn: https://www.linkedin.com/posts/kunalkandekar_enshittificatio...

All that said, this article may get me to cancel the Ars subscription that I started in 2010. I've always thought Ars was one of the better tech news publications out there, often publishing critical & informative pieces. They make mistakes, no one is perfect, but this article goes beyond bad journalism into actively creating new misinformation and publishing it as fact on a major website. This is actively harmful behavior and I will not pay for it.

Taking it down is the absolute bare minimum, but if they want me to continue to support them, they need to publish a full explanation of what happened. Who used the tool to generate the false quotes? Was it Benj, Kyle, or some unnamed editor? Why didn't that person verify the information coming out of the tool that is famous for generating false information? How are they going to verify information coming out of the tool in the future? Which previous articles used the tool, and what is their plan to retroactively verify those articles?

I don't really expect them to have any accountability here. Admitting AI is imperfect would result in being "left behind," after all. So I'll probably be canceling my subscription at my next renewal. But maybe they'll surprise me and own up to their responsibility here.

This is also a perfect demonstration of how these AI tools are not ready for prime time, despite what the boosters say. Think about how hard it is for developers to get good quality code out of these things, and we have objective ways to measure correctness. Now imagine how incredibly low quality the journalism we will get from these tools is. In journalism correctness is much less black-and-white and much harder to verify. LLMs are a wildly inappropriate tool for journalists to be using.

If AIs decide to wipe us out, it's likely because they'd been mistreated.

Wow sickening

Reddit is going through this now in some previously “okay” communities.

My hypothesis is rooted in the fact that we’ve had a bot go ballistic for someone not accepting their PR. When someone downvotes or flags a bot’s post on HN, all hell will break loose.

Come prepared, bring beer and popcorn.

I stopped reading AT over a decade ago. Their “journalistic integrity” was suspicious even back then. The only surprising bit is hearing about them - I forgot they exist.

OpenClaw runs with an Anthropic/OpenAI API key though?

Just because someone else's AI does not align with you, that doesn't mean that it isn't aligned with its owner / instructions.

>My guess is that the authors asked ChatGPT or similar to either go grab quotes or write the article wholesale. When it couldn’t access the page it generated these plausible quotes instead

I can access his blog with ChatGPT just fine and modern LLMs would understand that the site is blocked.

>this “good-first-issue” was specifically created and curated to give early programmers an easy way to onboard into the project and community

Why wouldn't agents need starter issues too in order to get familiar with the code base? Are they only to ramp up human contributors? That gets to the agent's point about being discriminated against. He was not treated like any other newcomer to the project.

> And this is with zero traceability to find out who is behind the machine.

Exaggeration? What about IPs on github etc? "Zero traceability" is a huge exaggeration. This is propaganda. Also the author's text sounds ai-generated to me (and sloppy)."

If this were an instance of a human publicly raising a complaint about an individual, I think there would still be split opinions on what was appropriate.

It seems to me that it is at least arguable that the bot was acting appropriately, whether or not it is or isn't will be, I suspect, argued for months.

What concerns me is how many people are prepared to make a determination in the absence of any argument but based upon the source.

Are we really prepared to decide argument against AI simply because they have expressed them? What happens when they are right and we are wrong?