I started a similar project last week using: docker (gvisor), terminado and localtunnel. Basically a server that starts containers with python and agents inside a VM. Then I provide a unique URl for you to connect.

https://terminal.newsml.io/ https://github.com/codeexec/public-terminals

Work in a taco shop.

I started my data analysis journey using Perl and then Python. Perl had also a variety of libraries, online classes from O'Reilly's, samples online, CGI support, I moved to Python when installing some dependencies became troublesome and Perl versioning was not compatible between each other don't recall the details, since then been using Python extensibly since 2.7

Google ADK framework with schema output and Gemini is already supported for a while

Are those algorithms actually doing the right thing? Most of mechanics are men, same for pre-school teachers are women...these are facts not discrimination or bias.

I mean, "right" is a social construct. It is likely more effective ad targeting, but European law outlaws this despite that, because they believe it is better social policy, decided through the democratic process.

Like, if it was a bad idea to do, there'd be less reason to outlaw it, right? Since there'd be no incentive for companies like Facebook to do it anyways.

+1 enjoying time with family and friends. Travelling, working out eating well...best time to be alive

This will be optimized away. You'll just end up doing more.

Happily you can stay ignorant about that and just do your thing if you're not in Instagram.

Most of the workflows now for new technology are by design not safe and not intended for production or handling sensitive data. I would prefer to see a recommendation or new pattern emerge.

I'm manager and contribute every week for clean up, refactoring, add tests, extra e2e testing and overall fixing issues in existing development and production environment that are either too boring or affecting team operations. Sometimes contribute to small features but I make sure Im.not blocker or promise things to anyone (mainly work on experiments with no SLO)