Perplexity is worse than a mere cop out. The power of approximating Solomonoff Induction with minimal argument surface criteria applies to all areas of science up to and including the most divisive issues that are increasingly dividing people along quasi-religious lines leading to a historic rhyme with The Thirty Years War for religious freedom that killed of a quarter of the population of Europe.
If people deserve to be thrown in jail for 3rd degree murder due to reckless driving, people promoting perplexity as model selection deserve far worse. On Mon, Aug 16, 2021 at 12:16 PM <[email protected]> wrote: > Perplexity might be a bit faster to run speed wise though, but not a > killer, LC is linear, ex. I think it may take a few mins or 10mins for 1GB, > so what, models take hours to train no 1GB. > *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/T31c4c6495649906f-M3055feb2959e97841fa10939> > ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T31c4c6495649906f-Mdeba5ccf01e68f5fc3db6104 Delivery options: https://agi.topicbox.com/groups/agi/subscription
