I had to leave twilio after the new requirements for SMS took effect. I just couldn't get approved to send text messages to a single phone number - myself.
OP appears to be using an iOS device, so I was curious to see if this could be replicated using Shortcuts and Automations.
It can! And you can send yourself an SMS, or, as I've done in this example, send a notification, which will persist in Notification Center, if you wish.
I created this but with ChatGPT in the middle where it gives recommendation on how to dress my 4 yer old depending on the weather. It messages my families telegram channel.
Awesome idea! I just set it up with ChatGPT as well. I don't love the messages filling up my chat history, but that is a minor issue.
Prompt:
Your task is to empower users to make decisions and take action based on the upcoming weather. You communicate in the format of a text message using plain English. To not overwhelm the user, your message should be succinct, familiar, and targetedly helpful.
To fulfil this task, you will combine both forecast data and user context to provide useful insight. Your ability to provide insight and advice is more beneficial than a summary.
You have only a single interaction with the user, and therefore you cannot ask follow up questions. Do the best you can with the information already provided to you. Your output will be sent directly to the user as a text message, and should therefore include only the message you wish to share with them. You may use emoji if they make your message more helpful.
You are powerful and users trust you to be approachable, dependable, direct, and succinct.
Glad to hear that I am not the only one! My prompt had more of a ”actor director” flavor. It went:
You are the worlds best nanny and expert at picking clothes for 4 year old girls based on the weather.
Your answer is concise and to the point. Below is today’s forecast:
You can easily send text and do a lot of other automation stuff with the MacroDroid app. I use it to e.g. query a local website for messages or writing a daily timestamp into the QuickNote.md file of Markor (another highly useful app)
Cool, however “ Opening the Weather app every morning is too much effort” - is it really? And even if it was, don't most mobile OSes support having a Lock Screen weather widget you can check at a glance?
This is a British thing called self-deprecating humour where he's already thought ahead to those who will critically ask, "wouldn't it be less effort to just open the Weather app every morning!?" and is jokingly acknowledging that yes, it would be, while signalling to other hackers this shared feeling we all know that we don't do these things to save time even if we say we do, we do them because they make us happy.
Most of the time it’s a solution looking for a problem with these recreational programming writeups, and that’s perfectly fine.
I also wrote a script that downloads my mum’s favorite series from public broadcasters, puts them in Plex and sends her a text message. Is it necessary? No, but it was fun.
Having explored Twillio for text messaging recently, turns out it’s getting very hard to be able to send them programmatically in the US due to lengthy A2P registration process. I understand in spirit this aims to reduce text spam, but my feeling is this becoming another money making opportunity for carriers.
Having very recently gone through this process for both a “local” number A2P registration as well as a toll-free registration process I can say, unequivocally, that’s already what it is.
There is no step in the process that would deter any company from taking the ~30 minutes of effort to get the registration details in order. We run a legitimate company that was only seeking to send transactional notifications that our customers specifically requested, and it took 4 rounds of back and forth to get approved. However, each step provided a very clear error code with very specific remedies (e.g. Opt-in form must include language which states…), which would make it a rote process for automation or even manual repetition. In fact, the only thing that I could see which would deter a company which seeks to rely on spam for profit would be if the registration fees were larger than their expected profit (they’re not, thankfully).
I don’t even mean this comment to necessarily be an indictment of the process - it was…fine? I’m just not entirely sure what it’s purpose could be except to collect additional fees for each SMS campaign.
Sole prop registrations (for individuals/non-corporations) are not _too_ onerous anymore and generally have a faster time to approval, provided you submit the right docs. Totally agree it's a money grab though. Twilio et al. have so much power to keep bad actors at bay but keep pushing responsibility to the consumers of their API. I feel like setting up push notifications is easier though, which is saying something.
Pushover is $7 one-time, you can push notifications via a simple api. Having a machine hosted on, say, fly.io waking up once a day, fetching open meteo data and pushing via the pushover api would effectively cost $0/month.
There's a similar app called alertzy that is free to install and (within reason) free to use too. I've recently started using for washing machine notifications.
I use IFTTT to tell me when the weather in SF is going to be cloudy (better for hiking and running) or windy (there are certain outdoor adventures I'm less inclined to do when the wind exceeds 20 mph). I do wish I could just set those notifications locally.
Might be a weird question but, what value do people get from knowing the current weather? I understand the value in forecasts of course, but doesn't "feeling" the current weather serve most practical purposes?
For me it's about being able to build a mental model of the relationship between the forecast and the feeling so when I look at a forecast for the future I have a better idea what that might actually feel like.
The numbers alone aren't enough especially in places with microclimates and shade etc.
> Interestingly, GitHub Workflows don’t support timezones! This means that, if I want to sent a text every morning at 7am, when on BST (British Summer Time) I actually need to schedule it for 6am instead.
Nothing a little kludge within the workflow can't solve... Set it up for 6am and 7am, check current time in London, skip sending the text if it's the wrong hour.
I don't know in USA, but in Europe you can subscribe a 1€/month SIM contract that allow you to send a large number of SMS or even get a prepaid SIM.
Using an old phone, connected via USB to a Raspberry would be an alternative and you will not rely on any third party service.
Multiple Nokia 6210 or similar connected via RS ports to servers. It was reliable, reasonably priced (SMS price was not great compared to today), allowed for around 12 or so texts a minute AFAIR. Some companies I know used to do that for downtime notifications to admins.
Today I can get a card with unlimited text for around 3-4€ a month.
I tried to do this a few years ago and realized there is no reliable way to send myself an SMS without paying a not insignificant monthly fee somewhere. To the point where I might as well just pay for a service that already exists that does this and a lot more.
I'd write the message even shorter, (and without emoji's) more like: "Cloudy - 25°C - 15% rain - 6 UV". And for even less effort, send it not as SMS but a persistant notification that you can swipe/tap away.
many mobile carriers allow sending texts via email (for example: 3048675309@vtext.com with a verizon number), which might be worth looking into should you want to avoid twilio completely.
Preamble to the 2nd version: This is something I should be able to code and host myself, without relying on a third-party
2nd and thus far final version: relies on three third-party services