Basically, where do you go online or on your phone when you just need a distraction and don't have the energy or mental bandwidth to read something in-depth? Games and apps are okay, too.

I appreciate the community and the quality of discussions that are had here on Tildes, but sometimes, I just want to veg. I basically want to scroll through a large supply of pictures, memes, short-form videos, but without the toxicity and manipulation that comes with the main social media platforms. I don't think I need to create a whole list, I think we all know what the main social media sites are to avoid.

And I also want to distinguish this topic from other "where do you get your news from" or "what are some interesting feeds you're subscribed to" topics. I'm looking for easily digestible and mostly positive/happy/funny things to consume. Where do you regularly turn to when you just want a distraction?

Let me start off by saying that I'm exhausted by AI hype. Being interested in LLM agent technology (AI agent hereafter for brevity) means skimming over a lot of hype for one or two useful, semi reality based, bits of information. Maybe the part that I find the most frustrating is how effective the hype is. I don't know if there's ever been a hype cycle like this. Probably a big part of the reason for that is the internet has already proven, within living memory for most people, that technological revolutions really can change everything. Or mess everything up. Either way they generate a lot of economic activity.

So this post is not that. I'm not going to tell you about how AI agents are the second coming for Christ. I'm not selling anything.

Fairly early into learning about AI agents I wanted a way to connect to the agent remotely without hosting it somewhere or exposing ports to the internet. I settled on tailscale and a remote terminal and moved on, I rarely used it. Somehow the tiny friction of "Turn on tailscale, open terminal app, connect, run agent" was enough to make it not feel worth it.

I know I'm far from the only person who had the same "I want it remote" thought, the best evidence: OpenClaw. It's just one of those things that everyone naturally converges on.

If you're not familiar with OpenClaw, the TLDR is: Former founder with more money than he'll ever need vibecodes a bridge between instant messenger apps and LLM APIs. Nothing about it is technically challenging or requires solving any particularly hard problems. It almost immediately becomes the fastest growing GitHub repo of all time and is currently at number 14 for number of stars. It blew up the (tech) internet like very few things ever have. Within months he was hired by Open AI.

OpenClaw now does more than just connect messaging and agents, but I believe that one piece is the killer feature. My tailscale terminal solution, combined with a scheduled task or a cron job and some context files could already do all of the things that OpenClaw can do, and countless people had already implemented similar solutions. But I think it was the tiny bit of friction OpenClaw removed that was responsible for a lot its popularity.

I thought that was interesting but I have no interest in the security nightmare that is OpenClaw, or the "sentience" vibe for that matter, so I built my own tool.

Essentially it's just a light secondary harness combined with a bridge between Signal and Claude Code. It does some other things too, things I wished existing harnesses did, some memory and guidelines, automated prompts and reminders to wake the agent up and have it do stuff, some context to give the agent some level of persistence, make it less LLMy, less annoying. None of that is particularly interesting though.

Once I got it working (MVP took less than a day) and started playing with it, the OpenClaw phenomenon made a lot more sense. Somehow having the agent in a chat interface, with almost zero friction (just open the chat and send something) was cooler than it had any reason to be.

I can't explain it any better than that at the moment. Not only was it kinda fun, it lent itself to a whole range of "what ifs". What if it could do X? What if I wrote a tool that gave it Y capability? I've been experiencing that for some time, but somehow agent in your pocket has a different feeling.

Here's an example of a "what if". What if it could do our grocery shopping? I definitely want that. I already had a custom browser tool that I built for agent coding assistance so I was most of the way there. It was just a matter of teaching the agent to login and navigate a website, something they're already trained to do. Some hand holding, a few helper scripts, and an evening's worth of hours later and I had it working. The agent can respond to a shopping request by building a shopping list based on our most recent orders, presenting it to us for approval/edits in a Signal group chat, doing searches for any additional product requests and adding the finalized order to the cart. It could also checkout the order and schedule the delivery time but I'm doing the last 2 clicks manually for the time being. It's an idiot savant, it seems like a bad idea to give it access to my credit card. Maybe eventually.

The fact that I can handle shopping with a couple of signal messages feels effortless in a way that handling shopping by connecting to my PC terminal remotely via tailscale terminal wouldn't have. Especially when I can include people in the loop who have no interest in tailscaling anywhere. Everyone can use messaging apps.

I imagine before long solutions like this will be built in, either in the grocery websites and apps, or into the frontier harnesses themselves. There will probably be agents everywhere, for better or worse. Probably I'll wish that the agents would all fuck off. In the meantime it's exciting how easy it is to get these tools to do useful things.

Kind of an XY problem, so I'm hoping that I'm just missing something stupid simple.

I found this tool (which is super cool) rss-librarian and I'm looking to make it stupid simple to send things I find on my phone to the url associated with my "account". I already have a bookmarklet set up in firefox on my laptop.

First thought was that I could use the "share" ability to simply share a cool link with a URL, but that seems to require some dev work. Second thought was to use Tasker to script something out, but that's looking to be a medium level of complicated. So, hopefully, there is something simple that I'm missing or don't know about that I could do to use this functionality from my phone.

Any suggestions? If not, I'll have to learn tasker :(

Back in the relatively recent years of 2017(or maybe not, that's nine years ago already), smartphone standards were far below what they are today. You could find phones configured with less than a gigabyte of RAM and 16GB of storage could be considered reasonable. Granted, these weren't going to be considered spec beasts during their time, but they were serviceable for the price. However, as compute power increased, these stragglers failed to hold on after being cluttered by user activity like bottlenecked storage or simply higher spec requirements. Thusly, Android Go was born around the tail end of 2017.

I don't intend to make this a history post, but just for the sake of comprehensiveness, Android Go really took stride by doling out optimizations for barebones cellphones and limiting some features like picture in picture and split screen. It really hit it's stride around Android 11 to 12, when phones were still transitioning to modernly reasonable specs.

Mayhaps the most surprising part is that the main constituent of Android Go is essentially a hard-bound toggle set by the manufacturer. But what may be overlooked is that Android Go still exists in the present day. So some developers still end up using it! But why does it still see use in the present day?

In the current iteration of Android Go, phones with 4GB of RAM or less by default are required to use Android Go. But nowadays, we can utilize virtual RAM extensions by allocating some storage space as quick read memory in settings. So this gives manufacturers the power to provide 8GB Android Go phones, making them honestly ovespecced for their on paper capabilities. Often times, these phones have to tone down their bloatware too, so that they don't sap the phone of too much power.
It isn't all upside though, as the aforementioned limitations on multitasking features are arguably the biggest deal breaker.

Manufacturers that use Android Go today are those that have models that cater to ultra-budget and emerging markets. Lower end Motorola and Redmi phones are the ones that are widely available. A notable example are all the phones of Transsion, whose main target market is in Africa and emerging SEA countries.

What's the experience of using it today though?
Aside from the PiP and split screen, The biggest difference isn't really all that strict: the Android Go apps. These can even be downloaded on regular Android and are often just stripped down and more data efficient versions of official Google apps that haven't been given the fresh do-over of Android Go itself. The notable exception is that Android Go will always have Google Assistant, for Google doesn't have plans to release a version of Gemini for Go. Which is ironic as EoL Android phones with lower spec than the current maximum of Android Go(4GB RAM) actually do have Gemini OTA updated on them. Go phones are trying to modernize, so they nowadays have 120hz screens, punch-hole cameras, and enough compute power for everyday. And yet they still compromise by having SD card slots and headphone jacks. The rest is really in the hands of your OEM. Samsung, Redmi, and the Transsion phones all have their little tweaks on the software, some being a little more egregious than most (cough Samsung cough). Motorola should be mostly stock though.

All in all, I just wanted to spread the word that Android Go still exists. Honestly, considering the world RAM crisis, we might actually see more devices on the horizon that utilize Android Go. What're your thoughts?

Does anyone here use a tablet for note taking?

I've always used pen and paper for note taking when working or in/around the house. At one point when phones got bigger I did try moving to notes apps but they never clicked. Something about the glossy screen and the levels of fuss to take a note just didn't work.

I recently found out that there's e-ink tablets which try to emulate real note taking, like the Supernote which runs a custom firmware to make note taking as easy as possible. Or the Boox which is Android based, so it has way more apps, but it's got amazing reviews.

There's quite a lot, I'm curious if anyone here has actually used anything like this and what their thoughts are?
Looking at reviews, I'm drawn to the Supernote. But I'd love to hear some real use cases!