[Schiendelman]

The reason it's showing you what's in the text is to show you a search result. The text is essentially the proof. When the user asks what plant she was telling you about, they don't have the text in front of them. It could be 200 texts back.

[kennywinker]

> It could be 200 texts back.

Ok? But if I search for something just show me the thing I searched for (the proof). There is literally no need to repeat it in a slightly different tense. Who is that helping?

[usef-]

If I asked you over voice what Mike said he wanted for his birthday, it's usually less confusing if you just answer the question ("he wants snow boots") rather than started reading out words from another person ("I love it here at the snow, ...")

[kennywinker]

If that’s the story you’re trying to tell, where is the query in the image? The image alone doesn’t tell that story.

But also:

a) do you trust the llm to get it right 100% of the time? Because i’m gonna always read the original message to make sure.

And b) just excerpt the message “mike says i love it here at the snow … but i need snowboots” if you’re so desperate to shoehorn LLMs into everything, that’s just as easy a task for them as summarizing is.

[Schiendelman]

The query isn't in these screenshots you're seeing online because it was in the video. This particular one I think was missing the query but the others like it had a presenter talking through what they were doing. Complaining about an image pulled off the internet out of context… Come on.

[kennywinker]

It’s not “pulled off the internet with no context”. It’s the second slide in their marketing presentation about what’s new in siri. The context they chose for it is all around it.