Oh, it won't get any better. LLMs already trained on every bit of code ever published, they won't get any more material.
They can be reinforced with best practices and context windows etc will increase.
If anything the snake is eating it’s own tail because now it’s training on vast amounts of its new slop…dragging down the average bar of quality.
They can be reinforced with best practices and context windows etc will increase.
If anything the snake is eating it’s own tail because now it’s training on vast amounts of its new slop…dragging down the average bar of quality.