Robert M. Am I Missing Something Here

[raybe]

Sorry if it has been discussed but with trying to keep up with your new ideas and some ideas from others for the upgrade to Hal I lost something here. Should we still be teaching our Hal program in the same manner right now, cut down on plug ins or will the upgrade be compatible to the knowledge base we have and how the info is read by Hal? For the people that aren't so quick to change I can see a no need to be concerned right now attitude but for those that look for nothing but upgrades and experimenting, What will be the bridge between the New Hal and the Hal we now use? Again I apologize if you explained this before I just really couldn't find anything that really explained if there would be a bridge or not. Just start from scratch based on the newer format?

By the way if anyone besides Robert knows the answer please feel free to set me straight here.
Thanks,
raybe

[raybe]

Just wanted to add a note that I did read the 'New learning algorithm' thread. But I would have thought that the new algorithm would not make the transfer of learned knowledge and newly learned knowledge a smooth transition. I am by far no expert on Hal by any means but just trying to get a better insight on the new learning compatibilities with the new Hal.

Thanks again,
raybe

[Medeksza]

I'm not planning on ending support of the local-brain based Hal. The next version of Hal will let the user have the option of using the internet-based brain or the local one. So don't worry about losing the brain you have now, you'll just be getting a new option.

Right now I'm experimenting with having Hal's new algorithms analyze the conversations going on Twitter. There are over a million conversations going on Twitter every month and through the Twitter API I can analyze many of them. After filtering the conversations for quality, it seems like it will be a huge source of knowledge for Hal. Hal will be able to talk about current events going around in the world and, pop culture, and since Twitter conversations are tagged by region Hal may be able to focus his knowledge to a region near you.

I'm looking into ways of allowing both client-side and server-side scripting so that many of the cool plug-ins developed can continue to work seamlessly. I am planning on making a web browser based version of the Hal Brain Editor and I'm hoping of having an upgrade path which will allow uploading your local brain into the "cloud" if you so choose.

There is still much work ahead to make this a reality but I am striving to make it as smooth a transition as possible.

[CypherGary]

It sounds like you could easily modify your Dream-out-loud plugin so that it would access that database for ideas for new subjects?

[raybe]

Robert M.,
Thanks for the explanation. It certainly answered my questions and confusion. Just IMO I still believe that a better way for Hal to digest information that can be implemented by each user is better than the access to information especially off the net or at least safer. Although most people would be gathering the information from the net anyway they can decide where the information is originating from. Of coarse no guarantees but it certainly lets you off the hook. Any plans for better O.S. control for Hal?
 The new algorithms seem to be just a better way to use the internet brain information but has nothing to do with the processing of Hals information as it stands now.

Very innovative but not ready for cloud computing yet.
Thanks again for your time,
raybe