Hacker Newsnew | past | comments | ask | show | jobs | submit | christoph123's commentslogin

A Substack for 80/20 life advice that gets repeated every year. We all know what to do, the idea of this is to remind us every week of one aspect of life and what best practices are for that area.

https://euzoia.substack.com The concept: https://euzoia.org

Tried to do this as low tech as possible, so website is just an off the shelf notion wrapper


Still an AI time tracker that watches your screen.

Currently experimenting with a proactive agent, Don, that pops up like clippy and also works over email.

https://donethat.ai All the data security measures here: https://donethat.ai/data And other tools out there: https://donethat.ai/compare


Hmmmm. I am not sure I would feel comfortable running this.

Totally understand that. I’m trying everything I can to make it as secure and private as possible, see https://donethat.ai/data but can never be 100% of course. At the /compare link I list some open source tools that try to do something similar fully local.

"Intricate as this mechanism appears, numerous components have been deliberately left out to avoid complete confusion" :D


Wise choice


A fully automated time-tracker that feeds screenshots into llms to help you spend your time where it matters to you.

https://donethat.ai

With lot's of built-in data privacy safeguards https://donethat.ai/data

Also made an overview of similar tools out there https://donethat.ai/compare

Recently broke on Linux with a Wayland security update, working on a fix! Using Electron for cross-platform.


Also: A mini-tool that estimates the value of an hour of your time https://donethat.ai/time-value-calculator


Shutting down Rewind completely, limitless not available anymore in EU, UK, Brazil, Israel, South Korea, Turkey, China, won't be HIPPA compliant anymore


I am right now building a proactive coach on top of my AI work capture app. Concept is very simple: It takes a screenshot every few minutes and analyzes what you're working on. From there it identifies task blocks, and checks if it should start a chat based on your intentions (eg to tell you to move out of your rabbit hole, take a break, help with a task, ...)

https://donethat.ai Passively processing screenshots is obviously pretty sensitive, it has an option to bring your own (local or remote) LLM, otherwise I process with gemini and never store any data.

It's in beta right now so if you want to try it you have to enable "proactive chat" in settings.

I also made a list of similar tools out there: https://donethat.ai/compare


The domain/name is fun.

The idea is controversial as proved by the resistance to Recall.

Morrissey should be your pet (stop me if you think you've heard this one before)

It should start doing what Instagram is doing and transform your activity into visual feedback that is fun to explore by you or the people that you want to show to, what you did throughout the day.


Been living in Amsterdam and six years in still don't speak Dutch. Maybe this is the moment... How to do you ensure quality in 90 languages? Seems impossible for a one-person-show if even Duolingo is only managing to do pretty basic examples?


From the get go, I was building it to be language agnostic. Almost all of the pipeline is built to work regardless of the language, and any language specific code is only run at the end of the pipeline. If I have issues with a language I don't know well, I'll work with academics in the language.

In terms of QA, I'm using the application to learn at least one language from every major language family, so I do reviews in about 15 language families every day.

That and constant communication with my users! :)


Not affiliated, just have been following development closely: Phrasing leverages existing content, e.g. subtitles from your favorite shows.

The quality depends on the source material you choose to give it.


An app to track my work automatically by feeding screenshots to LLMs and analyzing those. https://donethat.ai

Obviously this is quite sensitive data so architected it to never store raw data, allow for bring-your-own-key, and even in team settings be fully private by default, everybody keeps control of all their results.

Started about six months ago, have some first users, and always looking for feedback!


On your request 12

> A local screen recording app but it uses local models to create detailed semantic summaries of what I’m doing each day on my computer. This should then be provided as context for a chat app. I want to ask things like “Who did I forget to respond to yesterday?” I've been using Rewind for a year now, and it's nowhere near as useful as it should be.

I am building something like this but unfortunately not local because for most people's machines local LLMs are just not powerful enough or would take too much drain on battery. Work in progress, always curious for feedback! https://donethat.ai

If you want fully local, somebody did a post on HN on something related recently: https://news.ycombinator.com/item?id=45361268


iOS solves this problem by deferring processing until your phone is plugged in an locked. So it can sit there with full resources available to do whatever without impacting the user.


Working on https://donethat.ai - a fully automated work tracker and in the future also AI coach.

The concept is pretty simple: It takes screenshots every few minutes and reconstructs a calendar of what actually happened. On top of that features to set goals for how much time to spend on topics and a social feed.

This is obviously super sensitive data. I built it in a way that it never stores raw data and you can also bring your own Gemini key, plus a lot more privacy features. Tried to make it fully local but found that it takes too much energy and only works on high end machines.

I have a few first users, iterating with them, and right now exploring if it’s possible to make this work in team settings without sacrificing privacy.


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

Search: