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

> "open safari" (safari opens, voice says: "I opened safari") "navigate to google.com in safari" (nothing happens, voice says: "I navigated to google.com")

So you’re describing a core broken feature. Application breaking at easiest test.


Fair criticism. The action executed on the LLM side but didn't translate to the correct macOS action, the model hallucinated success instead of routing to the open_url tool.

This is a known limitation with small LLMs (0.6B-1.2B) doing tool calling. They sometimes confuse "I know what you want" with "I did it." Upgrading to a larger model improves tool-calling accuracy significantly.

We're also working on verification, having the pipeline confirm the action actually succeeded before reporting back. Thats a fair expectation and we should meet it.


> This is a known limitation with small LLMs (0.6B-1.2B) doing tool calling.

To me this is this nut to crack, wrt tool calling and locally running inference. This seems like a really cool project and I'm going to dive around a little later but if it's hallucinating for something as basic as this makes me think it's more of POC stage right now (to echo other sentiment here).


That's a fair read. Tool calling reliability with sub-4B models is genuinely the hardest unsolved problem in on-device AI right now.

The inference engine (MetalRT) is production-grade, the pipeline architecture is solid, but the models at this size are still the weak link for complex tool routing. Larger model support (where tool calling is much more reliable) is next on the roadmap. Please stay tuned!


Sorry, I scrolled through some of the rest of the comments on this thread and can’t stay tuned.

What do you think happens to a cow, when she stops producing milk? She is kept constantly pregnant, what do you think happens to most of her male offsprings? In the end, almost every single cow’s life ends in violence.

As unethical as purposefully murdering animals?

I don’t think you can call it a compassion when you own an animal with sole purpose of efficiently growing it and then killing it so its body can be dismembered and sold off. This is treating animals as property, that produces profit.


not any more unethical than any other animal that "murders" to eat

Do other animals have moral agency?

Why wouldn't they? Animals definitely have moral sense. Monkey for example react violently to social injustice against them. Animals also take compassionate actions that bring them no benefit or even incur cost. Straightly moral act.

Which is more unethical:

Raising animals compassionately, slaughtering them for meat as painlessly as possible after a healthy, happy life

OR

Letting people who require meat in their diet to live (there are a number of reasons this may be the case) die slow, painful deaths as their bodies fail around them?

It's real easy to say that "no one should ever kill an animal to live" when you ignore the disabilities and chronic conditions that make surviving on plants alone impossible, or prohibitively expensive.


This is whitewashing to make consumers happy and less concern. Nothing is humane about murdering an animal to sell its body parts for profit. Thats just marketing.

Sorry, does the truck picks up dirty diapers? Or what’s the point of the pickup? How do you package them for pick up?

The truck would come by once a week to pick up all of our dirty diapers and drop off a new set of clean diapers. The service provided a bucket with a cloth bag inside of it that had enough capacity for one kid for a week. Packaging up = closing the lid of the bucket and leaving it outside the door of our apartment. They would drop off a new one of these buckets full of clean diapers each week (visiting many other people at the same time). Beyond all the environmental benefits, living in the city this was actually super convenient.

The worker who’s put on this reduced salary instead of being fired doesn’t have orders nor he has a product. He works for a wage.

Just write the text yourself, not many people enjoy reading AI-generated posts, even edited.

It’s not even just about threats, you as an individual are in potential danger of being detained without due process by ICE

We had a great candidate for a job decline to relocate to the US for precisely this reason. I really do not blame anyone for making that decision

No, we won’t be in fact doing that. Machine parsable, readable for other tools - yes.

A lot of people won’t be dealing with a customer that may be using their product to inflict bodily harm or murder someone. A lot of people are also displeased with the current head of Ministry of Defense, and with his actions, e.g. that he allegedly ordered people killed after their boat has been destroyed

Politics with a sprinkles of hypocrisy, got it.

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

Search: