|
|
|
|
|
|
by FromTheFirstIn
105 days ago
|
|
|
Abstractions truncate the decision space of the layer above them by making understandable trade offs. LLMs don’t abstract anything, your code is still in python or php or Go. It just feels like they abstract if you don’t understand the output since not understanding the layer down is what we associate with non-leaky reliable abstractions. LLMs are abstractions the same way that your code editor is an abstraction- it’s not a layer, it’s an interface. |
|
|