Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

GPT-4o with scheduled tasks (jawbone) is available in beta

chatgpt.com

Post reply on HN
Print view View original

111–120 of 141 posts

Re: GPT-4o with scheduled tasks (jawbone) is available in beta

#111

Post by paul7986 »

ttul wrote: post #28

Amazon had an insane number of people working on just the alarms feature in Alexa when they interviewed me for a position years ago. They had entire teams devoted to the tiniest edge case within the realm of scheduling things with Alexa. This is no doubt one of the biggest use cases in computing: getting your computer to tell you what to do at a given time.

Open AI just needs to create & release their own phone with Microsoft's help! H.E.R. the movie phone.

Apple has not innovated in years and a GPT Phone where your lock screen is a FaceTime call like UI/UX with your AI Agent who does everything for you would give Apple a run for it's money! Pick up your phone & see your agent waiting to assist & it could be skinned to look like a deceased loved one (mom still guiding your through life).

To get things done it would interface with other AI Agents of businesses, companies, your doctor, friends & family to schedule things & used as a knowledgebase.

Maybe this is their step towards creating said agents?

Re: GPT-4o with scheduled tasks (jawbone) is available in beta

#112

Post by runeblaze »

halamadrid wrote: post #102

This is interesting, although I am a little confused about the purpose of ChatGPT with this feature. We already have many implementations where at a cron interval one could call the GPT APIs for stuff. And its nice to monitor it and see how things are working etc. So I am curious whats the use case to embed a schedule inside the ChatGPT infrastructure. Seems like a little off its true purpose?

I think we all agree this feature seems broadly of use, and given that presumably a professional full-time 1P team was behind this feature I am gonna use this product over the other implementations

Re: GPT-4o with scheduled tasks (jawbone) is available in beta

#113

Post by notachatbot123 »

imsotiredspacex wrote: post #54

This is the prompt describing the function call parameters: When calling the automation, you need to provide three main parameters: 1. Title (title): A brief descriptive name for the automation. This helps identify it at a glance. For example, "Check for recent news headlines". 2. Prompt (prompt): The detailed instruction or request you want the automation to follow. For example: "Search for the top 10 headlines from…

What is the source for that claim?

Re: GPT-4o with scheduled tasks (jawbone) is available in beta

#114

Post by frontalier »

delichon wrote: post #30
danpalmer wrote: post #17

Earlier quoted context omitted.

Glad to see that the thriving 2010 market of TODO list apps will see a resurgence in the AI era.

A todo app that you can write and modify by editing a natural language prompt, and that can parse inputs from the whole web with flexibility and nuance, is not a small thing.

> a todo app that you can write and modify by editing a natural language prompt

no.

"a todo app that you can interact with by writing natural language input?"

okay.

> nuance

really?!

Re: GPT-4o with scheduled tasks (jawbone) is available in beta

#115

Post by frontalier »

how does it handle timezones?

i saw no mention of them on the help article, or the ui

if i ask for a daily early morning news summary will it show up in the middle of the night or around lunch time? will it get updated when i travel? seems interesting if what you're looking for is a reminder that is not time relevant, just a thing that should happen at some point with a time precision of about 1 day.

https://help.openai.com/en/articles/10291617-scheduled-tasks...

Re: GPT-4o with scheduled tasks (jawbone) is available in beta

#116

Post by siquick »

cma wrote: post #97
practice9 wrote: post #84

Earlier quoted context omitted.

Well none of the labs have good frontend or mobile engineers or even infra engineers Anthropic is ahead in this because they keep their UIs simplistic so the failure modes are also simple (bad connection) OpenAI is just pushing half baked stuff to prod and moving on (GPTs, Canvas). Find it hilarious and sad that o1-pro just times out thinking on very long or image-intense chats. Need to reload page multiple times aft…

> because they keep their UIs simplistic How do I edit a sent message in the Claude Android app? It's so simplistic I can't find it.

You can’t edit on iOS either

Re: GPT-4o with scheduled tasks (jawbone) is available in beta

#118

Post by uncomplexity_ »

qgin wrote: post #35
ttul wrote: post #28

Amazon had an insane number of people working on just the alarms feature in Alexa when they interviewed me for a position years ago. They had entire teams devoted to the tiniest edge case within the realm of scheduling things with Alexa. This is no doubt one of the biggest use cases in computing: getting your computer to tell you what to do at a given time.

Recurring schedules across time zones is an unbelievably maddening thing to implement. At first glance it seems simple, but it gets very weird very quickly.

this.

some people cant even wrap gheir heads around it, taking hours and hours of discussions. still my favourite problem though.

Re: GPT-4o with scheduled tasks (jawbone) is available in beta

#119

Post by worldsayshi »

ldjkfkdsjnv wrote: post #24
worldsayshi wrote: post #22

Earlier quoted context omitted.

Sure but do they have a moat here? Anyone that can connect to an LLM could make that app.

Does AWS have a moat on cloud computing?

Yes that requires huge infrastructure investments. Creating an LLM requires huge investments. Running an LLM requires medium to big investments but using one remotely require very little investment.

Re: GPT-4o with scheduled tasks (jawbone) is available in beta

#120

Post by sunaookami »

ben_w wrote: post #53
PittleyDunkin wrote: post #2

Where are the release notes? Edit: I suppose they'll be here at some point: https://help.openai.com/en/articles/9624314-model-release-no... These seem like extremely shitty release notes. I have no clue why anybody pays for this model.

You might want this? It's more technical than the one you linked to: https://platform.openai.com/docs/changelog

Does this show "Invalid DateTime" only for me? Kinda ironic! https://i.imgur.com/ZAcwhxT.png
Post reply on HN