Hacker Newsnew | past | comments | ask | show | jobs | submit | jaredcwhite's commentslogin

I can't think of a single reason why you would need an LLM to search through PowerPoint files. We have traditional search technology which would be excellent for that!

> can't think of a single reason why you would need an LLM to search through PowerPoint files

Kati’s Research AI is genuinely great at search. It tries to answer your question, but also directly cites resources. This can help you when you’re not sure where the answer to a question lies, and it winds up being in multiple places.

Unless your query is super simple and of low consequence, you still need to open the files. But LLM-powered search is like the one domain (apart from coding) where these fuckers work.


I talk to tons of people in real life who are deeply troubled by the AI-pocalypse. I was at a dinner party just the other day where out of the blue (wasn't me, I swear!), the conversation turned to the horrors of genAI and its negative effect on our society.

AI slop. Flagged.

Poor analysis. Apple is doing quite well as a Big Tech company that simply doesn't need to "pivot to AI" like everyone else. Their missteps in "Apple Intelligence" have in fact demonstrated that they don't actually need to have much of a "strategy" here at all. In fact, if they simply link out to other people's chatbots and make it totally opt-in, that would be ideal.

The much bigger problem is that they've lost the wow factor in their software design, and in some regards the hardware as well even though the internals and build quality has never been better. Apple needs a design shakeup far more than it needs anything to do with AI, a poison pill which will bring the entire industry down in 2026.


I have intentionally withheld updating my daily drivers to iOS 26 because of Liquid Glass. But if I had to pick between two evils - diminishing UX quality and shoving AI into every corner where no one asked for it - I’d still pick Liquid Glass.

26.2 is looking a lot less glassy. If you want to avoid the glass, I’d wait for its full release.

The Apple Intelligence features are some of the more subtle ones overall compared to other companies like Google and Microsoft IMO

They absolutely are. And you can turn them off. My comment is more about the technology industry’s general insistence on shoving AI down your throat whether or not it’s useful, usable, or desired.

I’m hopeful that whatever combination of factors at Apple prevent that from happening remain. Otherwise I’ll have to start considering GrapheneOS and defaulting to my Debian-based MacBook.


And I love it! The ocr/vision models are a literal life saver here. Translating websites in Safari? Even text in images gets translated, super convenient! The only gripe i have is that it tries to be smart and tries to detect addresses, phone numbers. If the address or phone number is part of a text it is nearly impossible to copy the whole text since the phone number gets prioritised over the text (so you can only copy or call the number… )

A small nitpick: the translation and data detectors pre-date Apple Intelligence.

I do indeed love these features. They have definitely had some regressions in the data detectors over the past few years. I assume that they only test these automatically in “ideal” contexts that don’t account for real life. Not sure. They used to be more reliable.


I've used macOS these days, give them a few years and they'll "catch up" I'm certain.

Work is talking about upgrading our Macs to macOS 26. I'm holding off for now.

But I don't think the choice is quite as binary as "pivot to AI" vs "ignore AI entirely." What's changed in the last two years is that user expectations are shifting at the OS level, not just the app level

Yep. User expectations are leading people away from the slop-filled Windows 11 trainwreck and into the arms of Linux and macOS. Last thing we need is macOS to copy Redmond. (Used to be the other way around!)

> they've lost the wow factor in their software design

Software craftsmanship at large scale is dead, so we shouldn’t expect to see that make a return any time soon.

The last few decades of free market experimentation and evolution have revealed the playbook to maximize engagement+money: sell software as subscriptions, use every means possible (push notifications, full screen ads, etc) to monopolize the user’s attention, prevent users from importing/exporting data to keep them trapped in your walled off app…

In this kind of environment, the little touches and consideration that gave software its “wow” factor are a liability, since everything gets redesigned every 18 months anyway to keep up with the new trends and what A/B testing reveals.

The Apple of the 2000s could offer genuinely delightful experiences because software was in such a different, immature state back then and thoughtful design could be a meaningful differentiator. Similar to how the most successful+profitable games nowadays are filled with loot boxes and dark patterns, and have nothing to do with the masterpieces from a few decades ago.

Indie developers can still make delightful things that treat the customers’ wallet+time+attention with respect (thank God), but those will never make billions and billions the way Fortnite or TikTok or ads in the Settings app can.


> Similar to how the most successful+profitable games nowadays are filled with loot boxes and dark patterns, and have nothing to do with the masterpieces from a few decades ago.

That one actually hurts. I lost touch with games a while ago but it was a good run through the golden era. The cinema is on its way out. At least we have the memories.

Every generation has their stuff, there's new things to be excited about, but the turnover is getting crazy fast.


I agree that Apple is in a position where they don't have to and shouldn't go all in on AI yet. They can wait and watch and figure out the right move (though they will need someone with Jobsian vision).

But what's this about AI bringing the entire industry down?


Apple not having an AI strategy doesn't matter until it suddenly does.

Whether that is in 2 years or ten is anyone's guess.


Apple seems to have an AI strategy - throw $1 billion at Google for its models.

And if you believe the numbers from the press on Google’s AI spending, that’s an amazing deal.

https://www.indiatoday.in/technology/news/story/google-ai-bo...


And with the pipeline

Voice -> free text -> LLM -> standardized JSON -> call API to do stuff.

The only “hard” part in 2025 is the LLM. Everything after that is what I call a “10000 monkeys problem”. Just throw some developers at it.


It's also anyone's guess what direction it will matter. Will apple miss the boat on AI because it's the real deal? Or is it a bubble that will pop and apple will be left standing because they didn't bet the farm on AI

While we can agree that adding AI just to tick a box will win no awards, it will be a laughable proposition to suggest that Apple doesn't need to do anything on AI.

If anything its laughable and points to the unoriginality of product creators that we haven't fundamentally transformed how we interact with technology given how much AI offers as functionality. Anyone (I'll bet 20% on Ive) who figures this out will eat Apple's dinner.


If you're giving 5:1 against Ive I'll take that in a heartbeat. He has zero historical record to show he can somehow capitalize on AI; even his design contributions are overall meh. Apple will have to do "something" but the beauty of mountains of cash and a business that doesn't need AI everywhere is that they can wait and see what something is, and then execute. They've actually been really good at figuring out implementation after the conceptual heavy lifting is done; it's deep in their DNA

You are not a serious person.

Can you elaborate?

Hating AI in Portland too! :wave:

Stop trying to make ~~fetch~~ "AI Denialism" happen. It's not going to happen!

A side comment: I love that this is on Codeberg. I'm seeing more and more projects migrating there or originating there to begin with, and it's awesome. (And I've been doing that as well.)

More please! =)


My long-term bet on Node being "boring" and "stable" continues to pay major dividends. So glad I never invested any time and effort on this ecosystem…

That is the way, when one is long time around, there are these alternatives coming and going, while the reference platforms keep going.

must be nice to have a 1gb node_modules folder for hello world

Sounds neat, but I'm not installing a screen recorder browser extension that's not open source…

Fair point. I’m not open-sourcing it, but it doesn’t collect or send any data — everything runs locally.

Not sure about other folks, but I'd never trust a privacy-friendly tag on an indie software that's not open-source. Even for popular and trusted software (e.g., Obsidian) it gives me chills.

Totally get it — open source definitely helps build trust. That said, getting the Chrome Web Store Featured Badge means the extension passed their strict review, including privacy rules.

Privacy and Chrome are incompatible with one another.

Fair take. Everyone has different privacy thresholds, and that’s totally fine. Just sharing the tool for those who find it useful.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: