top | item 37420494 (no title) okhat | 2 years ago What did you find underwhelming if I may ask?It shows you how it takes some ~25 Pythonic lines of code to make GPT-3.5 retrieval accuracy go from the 26-36% range to 60%.Not a bad deal when you apply it to your own problem? discuss order hn newest wokwokwok|2 years ago The examples appear to knowledge retrieval and factoids only.The concept appears to be large scale chain of thought and automatic prompt generate and fine tuning… but there don’t appear to be actual examples of this. okhat|2 years ago Ah okay makes sense, yeah we'll release more examples.This is just an intro to the key concepts/modules. load replies (2)
wokwokwok|2 years ago The examples appear to knowledge retrieval and factoids only.The concept appears to be large scale chain of thought and automatic prompt generate and fine tuning… but there don’t appear to be actual examples of this. okhat|2 years ago Ah okay makes sense, yeah we'll release more examples.This is just an intro to the key concepts/modules. load replies (2)
okhat|2 years ago Ah okay makes sense, yeah we'll release more examples.This is just an intro to the key concepts/modules. load replies (2)
wokwokwok|2 years ago
The concept appears to be large scale chain of thought and automatic prompt generate and fine tuning… but there don’t appear to be actual examples of this.
okhat|2 years ago
This is just an intro to the key concepts/modules.