Join 📚 Kevin's Highlights

A batch of the best highlights from what Kevin's read, .

it’s important to realize that **ChatGPT and LaMDA aren’t trained to be correct**. You can train models that are optimized to be correct—but that’s a different kind of model. Models like that are being built now; they tend to be smaller and trained on specialized data sets (O’Reilly Media has a search engine that has been trained on the 70,000+ items in our learning platform). And you could integrate those models with GPT-style language models, so that one group of models supplies the *facts* and the other supplies the *language*.

Sydney and the Bard

Mike Loukides

![](https://media.licdn.com/dms/image/D4D22AQFgTrM2AXmyjQ/feedshare-shrink_800/0/1694371183156?e=1697068800&v=beta&t=Xl-ji1iMOsvzfapy8NRZ5kD1JYAsPrNxacIreRD7nDs) [Link](https://media.licdn.com/dms/image/D4D22AQFgTrM2AXmyjQ/feedshare-shrink_800/0/1694371183156?e=1697068800&v=beta&t=Xl-ji1iMOsvzfapy8NRZ5kD1JYAsPrNxacIreRD7nDs)

How Indexes Make Your Queries Fast

Julia Evans

![](https://media.licdn.com/dms/image/D4E22AQF8Qj7NdJS3Kg/feedshare-shrink_800/0/1696733314849?e=1699488000&v=beta&t=uk2mIPToeAuJye-QWN8N6It8RA1Xg4wOdzwxvK295DU)

Git: A Pictorial Walkthrough

Brij Kishore Pandey

...catch up on these, and many more highlights