![]() Some instructions it got right away, other instructions were more daunting. I also had to figure out best practices for giving the model instructions. Some of these examples took a while to figure out because I wanted to stick to the rule of only using the complete output from the model. If you have access to the model you can try the instruction prompts yourself (you can get access at ). All of the code in these applications was generated entirely by the model. I didn’t change a single line of code, stitch together functions or edit anything. More info here on its other capabilities.Įvery single example was created by providing only simple instructions to the model (“create a button that…”). I’ve been able to build apps and games simply by telling the model what I want. ![]() I’ve been building games and applications entirely through natural language instructions with OpenAI’s new code-davinci model for several weeks and it’s been a fascinating experience. There are limitations, and coding purely by simple text instructions can stretch your imagination, but it’s a huge leap forward and a fun experiment. TL DR: OpenAI has a new code generating model that’s improved in a number of ways and can handle nearly two times as much text (4,000 tokens.) I built several small games and applications without touching a single line of code. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |