Search is a compression problem. You want to find the response (as training data) that best compresses the query.
On Sun, Jul 19, 2020, 11:01 AM stefan.reich.maker.of.eye via AGI < [email protected]> wrote: > I have a first search engine on top of the compressor that actually works > <http://code.botcompany.de/1029098>. Tested it with all possible texts & > queries of up to length 7 over a 3-letter alphabet > <http://code.botcompany.de/1029104>, so I think it's ok. > > However, it goes through the query character by character and does not > compress it first. That's quite certainly not the most effective way. So we > should put the query through the compression algorithm first. > *Artificial General Intelligence List <https://agi.topicbox.com/latest>* > / AGI / see discussions <https://agi.topicbox.com/groups/agi> + > participants <https://agi.topicbox.com/groups/agi/members> + delivery > options <https://agi.topicbox.com/groups/agi/subscription> Permalink > <https://agi.topicbox.com/groups/agi/Tec7c169aa059f951-M3b94e2c196f832161f4f5f7f> > ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tec7c169aa059f951-Mbba0e7c4daf774bd340e97eb Delivery options: https://agi.topicbox.com/groups/agi/subscription
