Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

MDN can now automatically lie to people seeking technical information

github.com

Post reply on HN
Print view View original

41–50 of 83 posts

Re: MDN can now automatically lie to people seeking technical information

#41

Post by feoren »

gAI wrote: post #27
feoren wrote: post #21

Earlier quoted context omitted.

> The submitter knows the AI isn’t lying You've somehow internalized something as "obvious to everyone" that's actually very wrong and dangerous about AI. Of course the AI is lying. Or, perhaps a better term would be "bullshitting", defined as "sounding convincing while having no regard for the truth". By that definition, bullshitting is all LLMs ever do .

That's an ungenerous way of describing direct access to semantic space. gAI is creative. Rules-based AI is logical. We need them both.

But MDN's "AI Explain" is just straight LLM output, right? It's neither generative (LLMs are transformers, not GANNs, right?) nor rules-based: it's predictive. We need that too. But not for technical documentation! Not on its own!

Re: MDN can now automatically lie to people seeking technical information

#42

Post by gAI »

feoren wrote: post #41
gAI wrote: post #27

Earlier quoted context omitted.

That's an ungenerous way of describing direct access to semantic space. gAI is creative. Rules-based AI is logical. We need them both.

But MDN's "AI Explain" is just straight LLM output, right? It's neither generative (LLMs are transformers, not GANNs, right?) nor rules-based: it's predictive. We need that too. But not for technical documentation! Not on its own!

Aye, I agree this sounds like a strange and ill-fitting implementation. And it bums me out, because the more LLMs are used incorrectly, the harder it is to get people to use them at all.

Re: MDN can now automatically lie to people seeking technical information

#44

Post by rurp »

thesnide wrote: post #15

This just looks like the poster child of "hell is made of good intentions". It may look seemingly harmless at first, even a good idea. But you'll seed doubt. As that will erode the value of the whole site. Which was its main asset.

Is this being driven by good intentions? It looks like they are jamming the latest AI hotness into a feature without taking much time at all to think it through or implement things well.

Re: MDN can now automatically lie to people seeking technical information

#45

Post by andrewfong »

Even if the AI didn't make stuff up, it's unclear to me what value it adds over...

- The existing human edited text already on the page

- The playground to run the code in question

- One of the many existing autocomplete / static analysis tools for HTML / CSS / JS out there. If you want a tooltip explaining what the second argument to a built in JS function in a code snippet does, this is a solved problem!

Re: MDN can now automatically lie to people seeking technical information

#46

Post by brasic »

gAI wrote: post #42
feoren wrote: post #41

Earlier quoted context omitted.

But MDN's "AI Explain" is just straight LLM output, right? It's neither generative (LLMs are transformers, not GANNs, right?) nor rules-based: it's predictive. We need that too. But not for technical documentation! Not on its own!

Aye, I agree this sounds like a strange and ill-fitting implementation. And it bums me out, because the more LLMs are used incorrectly, the harder it is to get people to use them at all.

You’re worried about people not using LLM’s _enough_???

Re: MDN can now automatically lie to people seeking technical information

#47

Post by netsharc »

Hey ChatGPT, please generate a Firefox Corp-style apology for this snafu... Be sure to use some bullshit blah blah for our original aim of wanting to enhance user experience and listening to the users' feedback, and some more bullshit blah blah about doing better in the future.

Re: MDN can now automatically lie to people seeking technical information

#48

Post by Ukv »

brickteacup wrote: post #43
joshka wrote: post #36

@dang: Title is clickbait. Perhaps replace with something like: Bug report: MDN's AI Explain feature generates false explanations

not really, it is in fact generating lies automatically

IMO "lying" implies intent, and "MDN" misses that it's specifically an LLM "AI help" assistant that most people won't yet be aware of.

From the title I was thinking along the lines of MDN automatically swapping out an article on encryption to falsely claim a function doesn't exist depending on country to comply with local laws, for example.

Re: MDN can now automatically lie to people seeking technical information

#49

Post by tough »

missblit wrote: post #30
tough wrote: post #13

Earlier quoted context omitted.

Im pretty sure they use a vector storage database against their docs/resources so when you query they can just parse those sources and produce a free hallucination response to it. No need to make things up if you have the sources anyways.

The linked bug report has four examples of it being wrong. And the bug reporter mentions there's no workflow to submit corrections. Also hallutination was probably the wrong word to use for LLMs being incorrect since it might imply they could be correct if they would only just focus on the right input data rather than, say, simply not understanding complex technical concents, but I guess that ship has sailed.

stand corrected, didnt read TFA

Re: MDN can now automatically lie to people seeking technical information

#50

Post by Ygg2 »

Ukv wrote: post #48
brickteacup wrote: post #43

Earlier quoted context omitted.

not really, it is in fact generating lies automatically

IMO "lying" implies intent, and "MDN" misses that it's specifically an LLM "AI help" assistant that most people won't yet be aware of. From the title I was thinking along the lines of MDN automatically swapping out an article on encryption to falsely claim a function doesn't exist depending on country to comply with local laws, for example.

You're right. It should be: "MDN LLM assistant generates bullshit to people seeking technical information".
Post reply on HN