Great point in the article about tools lacking output schemas. Makes reliable multi-step planning tough.

We based Xops (https://xops.net) on OpenRPC for this exact reason (disclosure: we are the OpenRPC founders). It requires defining the result schema, not just params, which helps plan how outputs connect to the any step's inputs. Feels necessary for building complex workflows and agents reliably.

Congrats on the launch. I have seen your Deep RL tutorials circulating on YouTube. I like your presentation style: crisp and precise.

It's all about putting in the work. Not much programming expertise required.

Manganum is designed to transform Google Chrome™ new tab page from a web browsing tool into an inspiration and productivity workplace. It will give you motivation and inspiration every time you open a new tab. Enjoy hand-selected collections of amazing photo and video wallpapers in 4K resolution: stunning shots of wildlife, great cities and architecture, masterpieces of world art, satellite imagery, and wonderful color palettes.

As someone who has no idea about the legal system in the US, does the source have any grounding, and is there any chance this goes anywhere?

Photos are too flattering because of those tens of filters that are applied for no apparent reason.

Cool project – I saw the speed estimates on the swimmers during the live feed and was curious how they did that. Are any teams using this for performance analysis ala MoneyBall? Seems like you could get some really interesting metrics from techniques like this that would take a ton of time to collect otherwise.

Delhi has a per capita annual income of 300,000 rupees ($4,615) - the highest in the country and three times the national average. But nearly half of the city’s population lives in slums without basic services and facilities like drinking water, garbage disposal or a proper drainage system.

And life goes on, and little change is made. Many nations are so unfortunate to live in a poor society, with not so many chances of getting better.

Looks very promising! I like that you can fill the search space with python objects. Is it possible to search through numpy arrays? This would be nice for feature selection.

Thank you very much :-) yes you can put anything you want into the search space. Even pandas dataframes, numpy arrays or classes. Here is an example: https://github.com/SimonBlanke/Hyperactive/blob/master/examp...

That's knot nice.