Ford's battery "Important" socked by ...
Makes no more sense.
What they wanted to say was "Ford's flagship battery plant" or something else. Flagship is an adjective unless it's meant to denote a ship that carries an admiral's flag.
Makes no more sense.
What they wanted to say was "Ford's flagship battery plant" or something else. Flagship is an adjective unless it's meant to denote a ship that carries an admiral's flag.
My brain automatically disambiguated it to be "flagship ford battery factory".
Because it is obviously an article about a factory that makes batteries.
Maybe a sloppy typo. But the negative feedback about the article because of this is pretty extreme.
You're right, once is a typo. But the consistent pattern is quite rare in good writing.
Also, you make a good point re: OP's comment was not so much focused on grammar --- they had an interesting observation re: style I'm, and I wanna see I'm familiar with from labour-focused news publications. Which I support!! But, in a sentence, there's a sort of forced first-person, emotional, lengthy narrative that is quite appealing, but you're also not quite sure what actually happened.
> Prompt: I saw a headline titled "Ford's Battery Flagship Socked by Mold Sickness, Workers Say". What do they mean by "flagship", a literal ship?
> Claude Opus: No, in this context, "flagship" is not referring to a literal ship. In business and marketing, the term "flagship" is often used to describe the most important or leading product, location, or division of a company.
> In the headline you mentioned, "Ford's Battery Flagship" likely refers to the company's primary or most advanced battery manufacturing facility or division. This facility or division is considered the "flagship" because it plays a crucial role in Ford's strategy to develop and produce batteries for their electric vehicles.
> So, when the headline states that the "Battery Flagship" is "Socked by Mold Sickness," it means that this important battery facility is facing issues related to mold growth, which is reportedly causing health problems for the workers.
But Claude Opus is a remarkable LLM. Very powerful. Mixtral 8x7B quantized down to 4 bits is also a remarkable LLM, but much smaller and runs on my laptop. I gave it the same prompt.
> Mixtral 8x7b: "Flagship" in this context refers to the main facility or center of operation for a certain activity or product. In this case, it refers to Ford's main battery production plant.
That was generated in 1.2 s. Not bad. Checking the actual article, it appears that is what the article is about. In a world-modeling and text-comprehension sense these models appear to beat many human beings on meaning inference in ambiguous contexts. Quite cool! One can imagine a future where humans without this inference skill can use a rapid-response text model to auto-translate things down to their comprehension level.
After all, this entire discussion tree is a discussion about communication breakdown. It would be entirely obviated if these LLMs were placed in the comprehension path. Then we'd be operating at a higher level of discussion: talking about the referent rather than the reference, so to speak!
To give you another example: if I read "Uniqlo flagship in Berlin is plagued by mold" I immediately understand the implied term (flagship STORE) but if the title say omits "in Berlin" I would try to figure out if maybe there is a new type of mold that destroy... what? Heattech? Pima cotton?
I know what "flagship" means, and I did correctly assume that the article was trying to convey importance of _something_ related to Ford (my first thought was a flagship car model, but after reading the article I can infer it's about some sort of factory). My gripe with the title is that the article doesn't actually explain why or how it is important, and just assumes you will take the "Ford's Flagship..." description at face value and trust the author that it's important. It's unsurprising to me that an LLM would interpret it this way, because you asked it to just interpret the headline, which it did.
However, in _my_ reading of the article, I'm skeptical of the "Flagship" claim in the article because 1) it is never really explained and 2) the article seems to be going extra hard (too hard) to imply this is a big deal by attaching a bunch of other names (Joe Biden, Department of Energy, Inflation Reduction Act, multiple contracting companies, a SK investment company, state of Kentucky) to the project, but again never really explains why or how. It's almost like the journalistic equivalent of an appeal to authority, I guess.
Complaining that "flagship" has to be an adjective unless it's literally a ship is silly.
I have some issues with the title, but not flagship-as-noun.
We think about the technology as accelerating development of other stuff purely through generation: code, images, video, sound. But it could actually accelerate comprehension of text because in many cases its skill at teasing out value outstrips ours.
The future is bright!
- OP didn't say they didn't know what it meant
- it doesn't help improve human-to-human comms to have someone:
-- take up 80% of my screen
-- with a copy-and-pasted obvious take
-- unedited
-- from a text generator
-- that has been RLHF'd to chain of thought
I love LLMs and quit my job to work with them, but this ain't it, or an opportunity to extol about bright futures and stuff.
They said it makes no sense, so yes they did say that.
> it doesn't help improve human-to-human comms to have someone:
It's what the comment deserved for saying it makes no sense. Showing the dumb AI understands instantly.
And the conversation was already an overly large tangent.
No, they didn't
If they weren't saying "flagship" makes no sense as a non-ship noun, then they used the wrong words.
Oh unless by OP you meant someone other than jvanderbot, but jvanderbot is the person that prompted the claude reply. It wasn't a reply to duxup, who didn't even mention the headline.
Given that, do you still believe the huge, unedited, LLM explanation of "flagship" was responding to someone?
If so, who?
If not, I'd like to avoid normalizing spamming long, child-like, auto-generated, explanations of things to prop up straw-men in service of condescending.
A message board where that was mundane, everyday, behavior wouldn't be fun to be on.
I might enjoy it if I think someone deserved it, but I'd still balance that with the long view, because that sort of behavior is extremely corrosive.
I'm not lying. I stand by the claim that jvanderbot was saying it didn't make sense.
> Given that, do you still believe the huge, unedited, LLM explanation of "flagship" was responding to someone?
> If so, who?
Is this a real question? Do you not see how it's a reply to jvanderbot...?
> Is it helpful to normalize spamming long child-like auto-generated explanations of things to prop up strawmen? Would that be a fun board to be on?
The ship comment is just as child-like, and it came first. So while I don't think AI comments are good in general, I think in context it wasn't egregious. If we're trying to filter toward good discussion, then jvanderbot's comment should not be treated as much better than the claude comment.
2. They demonstrated they understood, via note on part of speech and reworded example.
3. You're happy to lie about it. ("I stand by the claim that jvanderbot was saying it didn't make sense")
4. LLM spam is good because it proves what they didn't say is wrong.
I think we all agree on #1, I and the spammer agree on #2, and I alone believe #3, and you alone believe #4.
With that, best to leave it at our interests differ: I'd prefer a forum that wasn't overrun by people making up things other people said* and posting LLM responses to the made up thing.**.
* aka, a strawman.
** aka, spam
And I still say the way they insisted on flagship being the wrong word while using the phrase "no more sense" was a form of not understanding. Doing it on purpose doesn't mean not doing it.
If that's not what you meant by "understanding" then I'm sorry for not reading your mind. It doesn't make me a liar. And you don't seem to have made any attempt to understand what I meant.
And you're doing your own strawman with 4. You know that, right?
1. Type in "I saw this comment on Hacker News:"
2. Hit `>` to start a blockquote.
3. Paste in my entire previous comment
4. Type in "Is this person saying that we should copy-and-paste LLM output as comments to others? Could you explain what he is suggesting I should do if I misunderstand?"
5. Hit Enter
I just tried it and the explanation is right on the money. Not everyone can pick up on human language well, even if they're skilled at other stuff.
You can repeat that with the original sequence of comments as well.
0. Type in "I saw this sequence of Hacker News comments:"
1. Paste in Arrakeen's comment in a blockquote starting with "FWIW I agree with you"
2. Create a nested blockquote with the next response '"Flagship" means important.'
3. Create a third level of nesting with the next response Ford's battery "Important"
4. Exit the nesting and ask: "Does it appear that these people understand what "Ford's battery flagship" means or are they confused by the term?"
And it will correctly detect that they were confused as they said:
> FWIW I agree with you. The title hardly makes sense to me as well. "Ford's Battery Flagship" - even after reading the article I'm still not sure what this is.
See, he does not know what it means, but if he had asked a high-powered LLM it would immediately have gotten him there and saved him some time commenting. And it looks like you could have too! It's really pretty good stuff. Thanks for working on them.