kantord

I use a tiling window manager to manage each task (/workflow/issue/ticket) on a separate (visual) workspace with its own isolated container/git worktree that is bound to it.

I name my workspaces to match the task, so it's easy to find all terminal sessions/apps related to one task; then I only have to be able to find a session/app within the task. And i3wm supports tabs, the tab title automatically set by most AI agents and apps to be something helpful, so it's trivial to find.

Thought this is not sth even AI specific, it's not really AI specific, it is just super useful for multi-tasking in general way beyond coding tasks as well. I first started automating this flow 6-7-ish years ago as i3-env: https://github.com/kantord/i3-env thought since I tried to rewrite that a couple times because debugging bash scripts was not so much fun; I'm kinda settling on a well-made and portable system now, though it's not well documented yet.

what do you mean?

For this incentive to exist, the app needs to be such an obvious memory hog that users start identifying it as the source of the problem.

Even then, a lot is required for most businesses to prioritize this (presumably) temporary issue at the cost of things like: participation in the AI race, other features, bug fixes, new markets etc.

Heck, sometimes software is so inefficient that it costs developer and tester productivity but a fix is not prioritized for years.

tip: your git repo's description (not readme, repo description) does not link the website. It should.

this looks insanely cool.

One of the most original ideas I have seen on HackerNews in the past few years.

This is not the technical solution you want, but I think it provides the result that you want: https://github.com/devcontainers

tldr; devcontainers let you completely containerize your development environment. You can run them on Linux natively, or you can run them on rented computers (there are some providers, such as GitHub Codespaces) or you can also run them in a VM (which is what you will be stuck with on a Mac anyways - but reportedly performance is still great).

All CLI dev tools (including things like Neovim) work out of the box, but also many/most GUI IDEs support working with devcontainers (in this case, the GUI is usually not containerized, or at least does not live in the same container. Although on Linux you can do that also with Flatpak. And for instance GitHub Codespaces runs a VsCode fully in the browser for you which is another way to sandbox it on both ends).

oh no! but that makes sense. I did post it on Lobste.rs myself

interesting, this is basically what Venkatesh Rao pointed out back in 2013: https://www.ribbonfarm.com/2013/07/10/you-are-not-an-artisan...

Basically we do not rationally analyze what work can be automated and what work is forever safe. We just assume that "sexy work" is safe, and work backwards to figure out how to explain this belief to ourselves.

honestly, I interpreted your comment as "Taskwarrior is unusable shit" since it had a pretty negative tone and came from a user named throwaway27448.

Actual accessibility is a different topic. Honestly I don't know much about the a11y of CLI apps in general. Is there something that makes Taskwarrior bad in that regard? Is it about the way it forms things like list outputs or tables?

nope! why?

there might be some gaps (let me know) but you can actually pipe the output to another program.

for instance here's how you'd download all the unread blog posts by combining blogtato and wget:

blog .unread read | wget \ --recursive --level=1 \ --page-requisites \ --convert-links \ --adjust-extension \ --no-parent \ --directory-prefix="$HOME/offline-posts" \ --input-file=-

I was considering adding a full offline mode but here is my thinking: that is actually a feature/concern that would be separately useful, so it should not be baked into blogtato. And there might be already some pretty good options out there.

For instance, `wget` is a pretty widely used HTTP client that is able to mirror links for offline access. Then you can use standard tools such as `grep` to search in all the offline content. And `blogtato` does already have an export feature, so it is almost trivial to write a script that saves all posts for online content.

So perhaps what should be done here is find a user friendly tool for offline access/search for web content and just add some convenience features to `blogtato` so that they integrate very easily.

i do not find the interface of taskwarrior inaccessible at all, i actually really love using it and find it largely intuitive. Not necessarily for doing super complex stuff, but that is not something I ever wanted anyways

Hi todsacerdoti thanks for posting my project! I am the author if blogtato. If you have any questions, I'm here to answer them

that was actually a lot of fun. I think it has the potential to grow into a bigger game.

Bug Tux Racer vibes btw! I think adding some music and perhaps snowfall could make it even more immersive

edit: and i think you could easily make it feel more detailed by adding a texture for the snow,and increasing the resolution of nearby terrain by modulating it with some precomputed fractalized perlin noise. So basically "free" detail that only exists in the rendering logic, does not influence the complexity of the heightmap. and perhaps you could replace the trees with sprites that are images of real trees (stylized to the visual style you're going for)

it's cool, but why can't I combine different shapes? I mean why erase the canvas when switching shapes?

It's possible that the training data (and research data) is already out there, just not (yet) combined into a single open source CAD kernel.

Then again, the success of such a project might depend on other factors. Given the complexity of the task, I can imagine that just "lucking into" the right design decisions early on could have a major impact.

I only used it for some hobby modeling, but I have to say it's fantastic and very impressive.

It seems like it's fully community-maintained, there is no big company or foundation behind it. Honestly it's hard to believe!

There was just one major problem, the infamous "topological naming problem" which caused issues downstream is you edited a non-leaf node. That was pretty frustrating to deal with, but in later releases they fixed it I think. (Have not tried it since because I didn't have anything to model)

interesting idea. At first I just thought that it's sth like the "fg" command but for AI sessions. i.e. just resume the last AI session you "paused".

honestly, that in itself would be valuable, though simple.

This idea, i. e. actually "moving" context form one agent to another is even more interesting.

I love the minimalism of the UI.

Here's a tip: GitHub now allows you to embed a proper video in your README. (https://stackoverflow.com/questions/4279611/how-to-embed-a-v...). Quality would be much better, and people can navigate back-and-forth in the video.

looks cool!

seems like a great idea

it is very early to tell what it is

That could be a new added feature, feel free to add a new issue on it

btw pdf support could probably be added to seagoat itself by adding a layer that translates the pdf files to text files and probably some added changed to make sure that the page number is also included in the results

update: I changed the hardcoded set of languages to support the following:

Text Files (.txt) Markdown (.md) Python (.py) C (.c, ``.h`) C++ (.cpp, .hpp) TypeScript (.ts, .tsx) JavaScript (.js, .jsx) HTML (.html) Go (.go) Java (.java) PHP (.php) Ruby (.rb)

https://github.com/kantord/SeaGOAT#what-programming-langauge...

actually I'm also working on a small web gui for it, it could be fairly easy to add speech recognition on the web version!

https://github.com/kantord/SeaGOAT-web

it is hardcoded at the moment, but I am willing to merge code that adds the option to override.

Also probably a flag would solve it for some users, the best way would be to add a configuration option. At the moment there are no config file/.rc file support in SeaGOAT though, but there is an issue to add it and I'm happy to merge pull requests: https://github.com/kantord/SeaGOAT/issues/180

also I plan to add features that incorporate a "dumb" analysis of the codebase in order to avoid spamming the results with mostly irrelevant results such as import statements or decorators. Those features would be language dependent, so support would need to be added for each language

btw I am also working on a web version of it that will allow you to search in multiple repositories at the same time and you will be able to self host it at work, or run it locally in your machine. https://github.com/kantord/SeaGOAT-web

so that could provide a nicer interactive experience for more complex queries