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

21–30 of 83 posts

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

#21

Post by feoren »

soared wrote: post #17

I don’t really understand viewpoints like these. The submitter knows the AI isn’t lying and the submitter is being purposefully obtuse in order to drive controversy.

> 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.

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

#22

Post by manquer »

tough wrote: post #13
osullip wrote: post #11

Earlier quoted context omitted.

I cannot see anywhere that MDN say the explanation might be wrong.

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.

“Hallucination free” or “Free hallucination”?

The latter would be very different interpretation and some here would probably agree with that accusation

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

#23

Post by manquer »

soared wrote: post #17

I don’t really understand viewpoints like these. The submitter knows the AI isn’t lying and the submitter is being purposefully obtuse in order to drive controversy.

The accusation is not that AI is lying it is that MDN is, especially given they are showing it at the same level as curated source with reputation for high degree of quality without full disclosure at error rates to expect

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

#24

Post by samtho »

Given the clear nature of GPT to simply spew things that sound “right”, why is a technically proficient organization such as this one jumping headfirst into integrating this with their products where it is clear that is not yet up to this task?

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

#25

Post by thorum »

I actually think this feature would be fine if implemented better. GPT-4 is perfectly capable of accurately explaining what a short code block does if you prompt it with relevant documentation… which MDN has in abundance, but isn’t using, for some reason.

The mistakes seem to be (1) using GPT 3.5 instead because it’s cost effective, even though GPT 3.5 has severe issues with hallucination, and (2) not including context from the surrounding article into the prompt.

Also, since I assume MDN has a finite number of things that need explaining, why not let users mark an AI explanation as wrong, and submit their own corrected versions?

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

#26

Post by mike_hock »

gAI wrote: post #9
cyanydeez wrote: post #5

Earlier quoted context omitted.

With placebos, the correct question is: does it displace more efficacious procedures. I'd say yes. Even if something is a placebo, it's ability to displace better solutions is the problem

I don't use MDN. I'm just asking if they removed something when they added this feature. Characterizing LLMs as placebos or "designed to produce gibberish" is inaccurate.

Relevant username.

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

#27

Post by gAI »

feoren wrote: post #21
soared wrote: post #17

I don’t really understand viewpoints like these. The submitter knows the AI isn’t lying and the submitter is being purposefully obtuse in order to drive controversy.

> 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.

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

#28

Post by drngdds »

I can't wait for this fad of people trying to use LLMs for things that require factual accuracy goes away (or the tech actually gets there, I guess)

Transformer models are capable of absurd sci-fi miracles when it comes to things that don't require truthfulness but this ain't it

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

#30

Post by missblit »

tough wrote: post #13
osullip wrote: post #11

Earlier quoted context omitted.

I cannot see anywhere that MDN say the explanation might be wrong.

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.

Post reply on HN