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

Creatinine not Creatine

After yesterday's keynote and the changes to Search, it became clear in the near future, Google will cease to direct any traffic to websites and the search results will just become a footnote in Gemini's response.

Wasn't that already clear 2 years ago, with introduction of AI Overview? And "Zero click search results" was a goal for Google for much longer.

Proton Mail Helped FBI Unmask Anonymous ‘Stop Cop City’ Protester https://www.404media.co/proton-mail-helped-fbi-unmask-anonym...


There is a Netflix documentary about Imfura, Gicurasi and the Pablo descendents narrated by David Attenborough. It just came out last month. Fantastic doc.


I'm literally working on an iOS app right now that needs to infer some input fields from free text typed by the user. Now to take into consideration typos, unstructured text (pricing, dates .. etc), I was pondering a cloud LLM or a basic local parser or even a local on-device LLM (ANE for 15+ devices and a different on-device LLM for the older models)

For the different on-device LLM, I literally went to HuggingFace and filtered by the smallest available models that can do the job, and Granite-4.0-h-1b works just fine, it corrects typos, infers dates, currencies all fields I need.

And it got me thinking how my first reflex was to rely on a cloud LLM which is waaay overkill for my need. Granted, an on-device LLM will need to be loaded on the devices on install or downloaded after the fact (which adds latency when the user needs it for the first time) but still, it's a better tradeoff than a cloud LLM.

I decided on a basic parser, and so far it seems to work fine. granted, it struggles with some words, but I just need to finetune it to have as much coverage as possible in terms of typos without triggering false positives.

A lot of developers have that reflex too and go along with it and then just pass the API costs to the customer. I could have gone that route too but turned out I don't even need an LLM for my usecase.


Apple includes a local LLM on all recent iPhones, https://developer.apple.com/documentation/foundationmodels. Seems like a bad idea to force your users to download a 3GB LLM just to parse a text field.


Yeah but I need broader coverage on older phones. No I'm not going for a 3rd party LLM. Foundation Models for iPhone 15 and newer, and a parser for the older ones. Currently training a Word Tagger in Create ML


People complain about token limits

Then spend their tokens on abominations like this

Make it make sense


I much prefer seeing tokens used for silly fun stuff, rather than sad get-rich-quick attempts like filling YouTube and Spotify with LLM crap.


Filling GitHub with LLM crap isn't on your list... I wonder why


Happy to include it, plenty of wannabe moneymakers making things worse for the rest there too.


> Make it make sense

It's not hypocrisy when different people do different things.


People use their tokens, and then complain of limits. Where's the incongruity?


Did this developer complain about token limits?


I mean... Why not?


Opus 4.6 was released between those dates


This and the crazy macro economic environment.


Yeah, Stuxnet was dormant for a year until execution.


> ... and counting reps in the gym

People need smart devices to count their reps !?


No, but it’s nice if the reps are automatically fed into my spreadsheet for keeping track of progress.


> Google strategy seems to be about scaling and distributing these models to their existing billions of users.

Yeah, part of that is installing a model in chrome to millions of users without consent.


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

Search: