Retire the internet's collective memory is not for AI-assisted software engineering

Agents are unlike humans in many ways but they have their own limitations. it's magical thinking to believe that they are not trustworthy and that their product is probably underwhelming.

"Recovery" would be a more apt (although less catchy name). The stealing is on the wall sadly. The abstraction layer is just really much lower if you want full perf. The tone of the article reminds me of the fake roads map makers would add to their maps to detect copying. Must be tough not to be challenged - whereas I would be amazed if an American voter knew what the seesaw of foreign policy was doing in India US relations. There's too much going on in this article and based on the "reasoning", the models have some form of index of those problems (or they are HEAVILY trained on them).

This proves that OpenAI models reason in grug speak to save tokens! I wonder if it's possible to discard unused functionality and even inline many library functions.