I was too lazy to write anything remotely as clean as this so I asked Kagi's integration of Mistral Large:

Sure, here's an example of how you could create a systemd timer to automatically renice existing Google Chrome processes.

1. First, create a new service file. You can use any text editor you like, but for this example, we'll use nano:

sudo nano /etc/systemd/system/renice-chrome.service

2. In the service file, add the following lines:

[Unit]
Description=Renice Google Chrome processes

[Service]
Type=oneshot
ExecStart=/bin/bash -c 'for pid in $(pgrep chrome); do ionice -c3 -p $pid; renice 19 -p $pid; done'

This service file defines a new service that runs a bash command to find all Google Chrome processes (using pgrep chrome), and then applies ionice and renice to each process.

3. Save and close the file.

4. Next, create a new timer file:

sudo nano /etc/systemd/system/renice-chrome.timer

5. In the timer file, add the following lines:

[Unit]
Description=Run renice-chrome.service every hour

[Timer]
OnCalendar=hourly
Persistent=true

[Install]
WantedBy=timers.target

This timer file defines a new timer that runs the renice-chrome.service every hour.

6. Save and close the file.

7. Now, enable and start the timer:

sudo systemctl enable renice-chrome.timer
sudo systemctl start renice-chrome.timer

8. You can check the status of the timer with:

sudo systemctl list-timers

This will show you a list of all active timers, including when they're next due to run.

Please note that this will only affect Google Chrome processes that are already running when the timer runs. If you want to also lower the priority of new Google Chrome processes as they're launched, you would need to use a different approach, such as the script I described in my previous answer.

Also, remember to replace chrome with the correct process name if it's different on your system. You can check the process name with pgrep chrome. If it doesn't return anything, try pgrep chromium or pgrep google-chrome.

LIDA is a tool to automatically explore data, generate visualizations and infographics from data using large language models like ChatGPT and GPT4

via Salim, much interechting

with 100k context windows on the way, it's now feasible for every dev to have their own smol developer - GitHub - smol-ai/developer: with 100k context windows on the way, it's now feasible for every dev to have their own smol developer

amazing

Welcome to podcast.ai, a podcast that is entirely generated by artificial intelligence. Every week, we explore a new topic in depth, and listeners can suggest topics or even guests and hosts for future episodes. Whether you're a machine learning enthusiast, just want to hear your favorite topics covered in a new way or even just want to listen to voices from the past brought back to life, this is the podcast for you.

si ça se produit réellement, c'est cool. bien qu'il soit inquiétant que la "propriété intellectuelle" de ce sujet encore philosophiquement indéfini soit entre d'autres mains que celles de chercheurs

x)

Build, train and deploy state of the art models powered by the reference open source in machine learning.

aha