hekec

I built an app called Readstack to manage the pile-up of articles and webpages I had saved for later reading. The app shuffles your reading list randomly and requires you to delete the current article before moving to the next.

This one-by-one approach forces a decision: read now or discard, which significantly helped me clear my backlog. It has no users except me, but I'm glad I created something that effectively solved my problem

https://apps.apple.com/nl/app/readstack-read-later/id1558413...

I'm shocked at how bad the presentation video is.

Almost the entire beginning of the video is about which colors are available and how the battery snaps, with zero hints about why I would need a cringe projector on me.

I can't believe this was shipped by ex-Apple people. Imagine Steve Jobs introducing the iPhone like this: "We are introducing a revolutionary new device. The first thing you should know about it is that it has a charger and an Apple processor. The second most important thing: here is how the battery works."

How do you adapt it on Wikipedia? Do you just add it to the dataset and continue training?

This was the game of my childhood. I really hope someone creates a remake

A couple of weeks ago, I built an ChatGPT-powered recommendation engine for everything.

You begin by entering what you want to get recommended, and some examples of what you like and don’t like. After this it lets you swipe cards with suggestions to like/dislike them and further train the program.

https://apps.apple.com/nl/app/ai-suggester/id6447003073?l=en

I developed a simple read-later app called Readstack to tackle this problem. The idea is that it forces you to go through pages one-by-one, without postponing. So, if you want to read something, you will have one item on the top of the list, and you need to read it or remove it before you can go to the following items. It helped me reduce my read-later pule to zero.

You can find it here: https://apps.apple.com/nl/app/readstack-read-later/id1558413...

Hope they will finally be able to work on a good product.

Kvass is delicious

Are there other countries with good remote worker visas? I heard they have it in Portugal

Omg, I loved this game. Played for several days until I saw that my journey will probably be quite long and complex. Still want to give it another shot, so thanks for mentioning this gem! I was thrilled when I realized I could travel to other planets

> It applies to everyone, including Apple

Which is false as Apple tracks you across apps without showing you this new prompt.

> That isn’t about Apple destroying anyone.

Could you elaborate on what are you implying here?

Are you saying Apple doesn’t damage anyone with this policy? It is obviously false.

Are you saying damaging competitors and building its own ads ecosystem is not Apple’s primary motivation here? It also seems false, as they build their own ad system, which tracks users.

Why this isn’t about Apple, if they literally use their market power to destroy competition? They could have done tons of features to benefit users, but they implement those which damage competitors.

I still hope some indie dev will build something similar to Spore. Probably my favorite videogame as a kid.

Love this!

I am doing a chat app and I need to generate answers to 1000 prompts. Can anyone recommend the simplest method to achieve it without Kubernetes and training my own model etc?

Love this!

Could anyone recommend a tutorial how to run this? I need to generate answers to 1000 questions for my app. Still waiting for GPT-3 invite for months

On their website they say that "GitHub Copilot is a code synthesizer, not a search engine: the vast majority of the code that it suggests is uniquely generated and has never been seen before. We found that about 0.1% of the time, the suggestion may contain some snippets that are verbatim from the training set."

So it won't copypaste your code. It had just read code from open sources and learned from it - similar to what humans do. So I don't see any problem with this.