But now instead of swinging back to local resources, apparently we're proposing to add a second layer of remote access (phone -> computer -> Claude servers).
But now instead of swinging back to local resources, apparently we're proposing to add a second layer of remote access (phone -> computer -> Claude servers).
FWIW, I'm not a big fan of AI coding. I use AI (including LLMs) and I am an AI researcher, but the vibe coding just hasn't clicked despite constant efforts. I guess it can make more sense to do it if you're programming from your phone because while normally typing isn't the bottleneck it definitely is on the phone (or at least far less comfortable)
> And there's no way this thing would handle a useful local model
So if you have a setup like mine then it is fairly trivial to incorporate that (or anything else). Either way you'll need a machine that can do the local AI though. Either that is on your "work machine" or you run the AI on a separate machine. You could even rent a machine and as long as you add it to your Tailscale network then you're connected.I strongly suggest having a workhorse machine and then let other devices be your terminal into it. Your terminals can be very cheap (or an old machine) or as suggested, your phone.
I have an old used Dell Latitude that I use as a pseudo thin client. I ssh into my PC, and everything just works.
I really like this setup because I only have one environment, so everything is there, and I don't have to install anything in the laptop
> I really like this setup because I only have one environment, so everything is there, and I don't have to install anything in the laptop
Yeah that's one of my favorite parts. Same about living in the terminal. I can be effective anywhere nearly instantly. I carry everything around in my dotfiles and keep it small (keep the .git folder small and don't add anything except text files)[0].On that note, one thing I highly recommend to people is to add some visual clues to tell you which machine you're on. I use starship and have a few indicators but I also have some PS1 exports that I've used in the past or use in new tmp instances (I HIGHLY recommend also doing this for when you're using the root account). It can get confusing when you have different tabs on different machines and it is easy to mistake which one you're on.
[0] I also recommend keeping notes there if you like writing in markdown. Files are so tiny that it's worth having them. It's benefited me more times than I can count.
Thanks in advance!
Lately I have migrated some of that to Guix Home because the other half of the problem is having all the dependent programs necessary for the dotfiles installed automatically at the appropriate versions.
The latter one especially falls into the realm of tinkering. :)
[1]: https://github.com/RichiH/vcsh [2]: https://systemcrafters.net/craft-your-system-with-guix/guix-...
find "${DOTFILE_DIR%/}/configs/" \
-maxdepth 1 \
! -name "*.md" \
-exec bash -c 'ln -Fis "${0}" "${CONFIG_DIR%/}/${0##*/}"' {} \;
It baffles me that people are so unorganized in their dotfiles. A little goes a long way to making your life easier. But then again people suck at bash so they're probably not thinking of using find this way. You could also use xargs to parallelize if you want but there'd be no practical speed difference for meAnother key component is to break out files. For example I have the directory ~/.dotfiles/rc_files/zsh. My zshrc file sources different files from that location. So I have a Linux file and OSX file there for anything that is specifically system dependent. If you want different configs on different machines you can check the hostname and use the same pattern!
Speaking of which, use functions! At first this is going to sound crazy but it's worth the effort and let's be honest, the effort is very low (though the initial rebase might not be depending on how messy you are)
function _exists() {
command -v "$1" &> /dev/null
}
alias_ls() {
alias_lsd() {
alias ls='lsd'
alias la='lsd -A' # A drops . and ..
alias ll='lsd -l' # h is automatic
}
alias_base_ls() {
alias ls='ls -v --color=auto -h' # numerical sort, color, human readable
alias la='ls -A' # ignore . and ..
alias ll='ls -lh'
}
if ( _exists lsd );
then
alias_lsd
else
alias_base_ls
fi
}
main() {
alias_ls || echo -e "\033[1;31mls aliasing fucked up!\033[0m"
}
main
Yeah, it is a bit more cumbersome but it's really not that bad and 1) debugging gets so much easier
2) you know where everything is and what everything does.
3) trying new aliases, command tools, scripts, etc also becomes a lot easier.
Following Unix philosophy has more advantages than disadvantages. I also strongly suggest adding comments because you'll forget why you did something. I'll often link to posts for this and for giving credit.Since we're speaking of bash, bookmark this website: https://mywiki.wooledge.org/BashPitfalls
Fwiw, my main language is Python but for pretty much everything in the terminal I write in bash. You can often make oneliners that would traditionally be a lot of lines in Python. Not to mention it's usually faster. It's a good way to help you learn bash too! ^__^
Nothing could possibly go wrong, those guys are always 100% trustworthy and reliable, contracts and NDAs with them are ironclad and easily enforceable… … o_o