AI bots hallucinate software packages and devs download them
AI bots hallucinate software packages and devs download them
www.theregister.com
AI bots hallucinate software packages and devs download them
110 comments
-
-
Can we fucking stop anthropomorphising software?
-
"Hallucinate" is the standard term used to explain the GenAI models coming up with untrue statements
-
in terms of communication utility, it's also a very accurate term.
when WE hallucinate, it's because our internal predictive models are flying off the rails filling in the blanks based on assumptions rather than referencing concrete sensory information and generating results that conflict with reality.
when AIs hallucinate, it's due to its predictive model generating results that do not align with reality because it instead flew off the rails presuming what was calculated to be likely to exist rather than referencing positively certain information.
it's the same song, but played on a different instrument.
-
They don't come up with any statements, they generate data extrapolating other data.
-
What standard is that? I'd like a reference.
-
-
No?
An anthropomorphic model of the software, wherein you can articulate things like "the software is making up packages", or "the software mistakenly thinks these packages ought to exist", is the right level of abstraction for usefully reasoning about software like this. Using that model, you can make predictions about what will happen when you run the software, and you can take actions that will lead to the outcomes you want occurring more often when you run the software.
If you try to explain what is going on without these concepts, you're left saying something like "the wrong token is being sampled because the probability of the right one is too low because of several thousand neural network weights being slightly off of where they would have to be to make the right one come out consistently". Which is true, but not useful.
The anthropomorphic approach suggests stuff like "yell at the software in all caps to only use python packages that really exist", and that sort of approach has been found to be effective in practice.
-
-
I just want an LLM with a reasonable context window so we can actually write real working packages with it.
The demos look great, but it’s always just around 100 lines of code, which is beginner level. The only use case right now is fake packages.
-
Just use the AI Horde. iirc our standard is like 4K context and some people host up to 8K. Here's a frontend
-
8k context is nothing.
-
-
I use it for writing functions a lot, tell it the inputs and desired outputs it'll normally make what i want. Recently gpt has got good at continuing where it left off too.
-
I'm using Codeium for that. Works pretty well as a glorified autocomplete, but not much more. Certainly saves a lot of typing though, but I have to double-check everything it produces, because sometimes it adds subtle errors.
-
-
I'm not particularly interested. Some on my team are playing with it, but I honestly don't see much point since they spend more time fixing the generated code than they would writing it.
And I don't think it'll ever really work well (in the near-ish future) for the most common type of dev work: fixing bugs and making small changes to existing code.
It would be awesome if there was some kind of super linter instead. I spend far more time reading code than writing it, so if it can catch bugs, that would be interesting.
-
In my experience with Codeium, it sometimes works ok for three or four lines of code at once. I've actually had a few surprises where it nailed what I was going for where I didn't expect it. But most of the time, it's just duplicating code from elsewhere in the same file, which usually doesn't make sense.
It's also pretty good for stuff where I'd usually build some exotic regex to search/replace (or do it manually, because it'd take longer to come up with the expression), like transforming an enum into a switch construct for its members, or mapping said enum to a string of the member's name.
This is very far from taking over my job, though. I'd love to be more of a conductor than the guy playing all instruments in the orchestra at once.
-
-
I have tried the copilot integration in edge out of curiosity, and if you feed the ai the context of the page the response can be useful. There is a catch, tho:
- when opening a document the accepted formats are html, txt, pdf. The documentation of a software package can be summarized but thr source will be the context of the page and not a web search, which is good in this casr
- when generating new information, the model can be far too sintethic, cutting out potentially useful informations.
I still think you need to read the documentation yourself, maybe using the AI integration only when you need a general idea of the document.
What I do is first reading the summary of the documebt by bullet point, than reading the pdf file as a whole. By the time I do so, the LLM has given enough of a structure to facilitate my readings...
-
-
One of the first things I noticed when I asked ChatGPT to write some terraform for me a year ago was that it uses modules that don't exist.
-
The same goes for Ruby. It just totally made up language features and gems that seemed to actually be from Python.
-
I have this problem with ChatGPT and Powershell. It keeps referencing functions that do not exist inside of modules and when I'm like "that function doesn't exist" its like "try reinstalling the module" and then I do and the function still isn't there so I ask it for maybe another way to do it, and it just goes back to the first suggestion and it goes around in circles. ChatGPT works great sometimes, but honestly I still have more success with stack overflow
-
-
Yeah, had that on my very first attempt at using it.
It used a component that didn't exist. I called it out and it went "you are correct, that was removed in
<older version>
. Try this instead." and created an entirely new set of bogus components and functions. This cycle continued until I gave up. It knows what code looks like, and what the excuses look like and that's about it. There's zero understanding.It's probably great if you're doing some common homework (Javascript Fibonacci sequence or something) or menial task, but for anything that might reach the edges of its "knowledge", it has no idea where those edges may lie so just bullshits.
-
This is the best summary I could come up with:
In-depth Several big businesses have published source code that incorporates a software package previously hallucinated by generative AI.
Not only that but someone, having spotted this reoccurring hallucination, had turned that made-up dependency into a real one, which was subsequently downloaded and installed thousands of times by developers as a result of the AI's bad advice, we've learned.
He created huggingface-cli in December after seeing it repeatedly hallucinated by generative AI; by February this year, Alibaba was referring to it in GraphTranslator's README instructions rather than the real Hugging Face CLI tool.
Last year, through security firm Vulcan Cyber, Lanyado published research detailing how one might pose a coding question to an AI model like ChatGPT and receive an answer that recommends the use of a software library, package, or framework that doesn't exist.
The willingness of AI models to confidently cite non-existent court cases is now well known and has caused no small amount of embarrassment among attorneys unaware of this tendency.
As Lanyado noted previously, a miscreant might use an AI-invented name for a malicious package uploaded to some repository in the hope others might download the malware.
The original article contains 1,143 words, the summary contains 190 words. Saved 83%. I'm a bot and I'm open source!
-
so basically, given AI having full reigns, it'll take about 2 weeks before it all goes to complete shit, unreadable code, completely garbage software. Just an utter disaster waiting to happen. Cool.
-
-
From the article...
hallucinated software packages – package names invented by generative AI models, presumably during project development
-
It's 2024. No more quality control, no more double-checking, not in any industry at this point. We're all alpha testers. Not even beta testers.
As the old entertainment industry adage goes when anything goes wrong on the set, "we'll fix it in post."
-
Lie.. no hallucinate..they lie and make shit up... just like a real hooman!! :))
-
daily PSA that something like [insert number of packages] are deprecated on shipment of software.
Thanks guys, very cool.
-
I'm honestly starting to get tired about "people confuses advanced chatbot with Jarvis and bad things happen".
Specially when it's shitty/lazy devs that don't code review.
110 comments
*bad Devs
Always look on the official repository. Not just to see if it exists, but also to make sure it isn't a fake/malicious one
Or devs who don't give a shit. Most places have a lot of people who don't give a shit because the company does not give a shit about them either.
What's the diff between a bad dev and a dev that doesn't care? Either way, whether ist lack of skill or care, a bad dev is a bad dev at the end of the day.
You'd be surprised how well someone who wants to can camouflage their package to look legit.
True. You can't always be 100% sure. But a quick check for download counts/version count can help. And while searching for it in the repo, you can see other similarly named packages and prevent getting hit by a typo squatter.
Despite, it's not just for security. What if the package you're installing has a big banner in the readme that says "Deprecated and full of security issues"? It's not a bad package per say, but still something you need to know
Yeah, I’m confused on what the intent of the comment was. Apart from a code review, I don’t understand how someone would be able to tell that a package is fake. Unless they are grabbing it from a. Place with reviews/comments to warn them off.
That’s what my ex wife used to say
we just experienced this with LZMA on debian according to recent reports. 2 years of either manufactured dev history, or one very, very weird episode.
The official repositories often have no useful oversight either. At least once a year, you'll hear about a malicious package in npm or PyPI getting widespread enough to cause real havoc. Typosquatting runs rampant, and formerly reputable packages end up in the hands of scammers when their original devs try to find someone to hand them over to.