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

> Dishwasher rinse aid in beverages happened yesterday but I’ve also had makeup remover in condiments

I am sorry but could you explain the meaning of this sentence?


There is a setting in the “Reminders” app where Siri will automatically categorize your reminders into certain categories. If you have a shopping list and you add chickpeas and red beans for example it might put them into a category of “pulses and grains”. I think the idea is you probably buy all the things in a particular category from the same kind of store (or the same section of a supermarket or whatever).

For me yesterday I needed to buy dishwasher rinse aid so when I added it to my shopping list siri put it into the “beverages” category, and when my wife on a different occasion asked me to buy some makeup remover for her siri put that into a “condiments” section.

I have not done anything (on purpose) to make the classification like this by mistraining it or whatever - it’s just been that bad out of the box.


Dishwasher rinse aid - the tablets you put into the machine containing chemicals

Beverage - another word for drink

Makeup remover - for women

Condiments - something added to food to enhance its flavor

iOS tries to put shopping list items into AI named groups but doesn't seem to understand what objects actually are so it makes mistakes.


Agent technology labs are likely exempted of this due to the significance ascribed to their work.

> Yes I still vibe unit test and integration test,

False sense of security. What's stopping the agents from doing an elaborate form of "Assert.IsTrue(true)" in some/most/all of the tests since you are vibing it and not reviewing it?


Exactly what happened in a PR from a few months ago, from the beginning it felt wrong, pytest was moved from the dev group to the main import section. Then imported in our models. To add ignores everywhere.

Agreed. If you don’t want to read the code that’s fine, but you have to read the testing code. Otherwise you have no idea what’s going on.

Yeah, you have to have some level of involvement. It's crazy that we are actually talking of 100% dev involvement to literally 0% involvement.

If you're working with agents that severely misaligned you'll probably have issues way beyond fake tests.

It seems to me that chances of misalignment are a function of accumulated usage time. Eventually, it will happen.

Look at the COBOL devs. They are been called in their retirement years. You don't want that to be you. Life is short

Have you seen what they charge per hour? Let’s just say it’s not Upwork rates.

my uncle is 70+ years old and he's one of those haha

I saw him starting at a monitor at midnight, back all hunched up and thought "nope, not what I envision"


Because safety isn't a priority at OpenAI and they had (have?) been falling behind Anthropic in the LLM race? Big fans of the saying: move fast and...


Arguably, if the website does not have a positive value and only negative, the logical thing is to shut it down and keep the Google Business profile imo. I assume she has been paying for the domain name all this years too or is it a subdomain?


I think the new version is a net positive value as creates a better "vibe" to prospective patients than just a Google Business listing would, and I expect will age well.

The domain's used for email anyway and is on a very cheap local hosting plan, probably all-in-all like ZAR 84 per month and ZAR 200 per year for the domain, so ZAR ~1200 (USD ~75) per year.

Old website was built in a different era, Google Business didn't exist, "HTML5" wouldn't be a thing for another 5 years, web design styles were completely different and was before iPhone meaning that modern day "mobile friendly" was not even a thought.

When my father started running guest suites over 10 years-ago I made a single page website with essentially the same goals but using a Hugo template. The website still feels "modern" today, so I expect this new one of my mother's will age well too.


> It takes four years of education before becoming a taxi driver in London

That doesn't apply to private hire vehicle drivers afaik.


Private hire is technically not a taxi. They can't pick someone up at a rank or on the street.


Or Uber drivers in London


(In case you're not aware) It's the same thing. Uber operates in London as private hire operator, so their drivers are mini cab drivers. Same rules (now: basic English and rules test, yearly car inspections, MOT every 6 months, cars must have TFL badges, etc).


... who are obviously not taxi drivers, so ... your point?


> Food should be prepared with love

You forgot about the sentient non-veg elements that also get added to it. Is that done with love too?


> I can't tell the difference so what does it matter?

Eternal September. Just like the usenet groups


Eternal September. Just like the usenet groups

And CB radio before that.


> it's advancing fast

Actually, it (LLM models) has been advancing slower for a while. This is pretty much in the mainstream. And the current approach is facing all sorts of obstacles that are not exclusively technological. The compute needs are no longer sustainable. Financially, big labs are drowning in debt and backlash against data centres has grown so much that it has become an electoral topic in at least one major country.


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

Search: