I think the paper would have been stronger if it acknowledged how quickly the underlying evidence is becoming outdated. AI-assisted development in 2026 isn't just better models. The way many devs including myself work has changed and matured quite a bit as compared to last year

▲

tkzed49 2 hours ago | parent [-]

how so?

	▲	cyptus an hour ago \| parent \| next [-]
		I think the tooling around the models themself has improved _a lot_ - they are really good at giving the models the correct context, even in big code bases
	▲	sevenzero an hour ago \| parent \| prev [-]
		Many devs now work in YOLO mode letting LLMs automate their tasks.