Anything that can be done in 2 days now with an LLM was low hanging fruit to begin with.

fullstackchris 3 days ago | parent | next [-]

I'll also argue that level of skill depends on what one can make in those two days... it's like a mirror. If you don't know what to ask for, it doesn't know what to produce

▲

agumonkey 3 days ago | parent | prev [-]

I really wonder what long term software engineering projects will become.

▲

baq 3 days ago | parent | next [-]

‘Why were they long term?’ is what you need to ask. Code has become essentially free in relative terms, both in time and money domains. What stands out now is validation - LLMs aren’t oracles for better or worse, complex code still needs to be tested and this takes time and money, too. In projects where validation was a significant percentage of effort (which is every project developed by more than two teams) the speed up from LLM usage will be much less pronounced… until they figure out validation, too; and they just might with formal methods.

	▲	agumonkey 3 days ago \| parent [-]
		some long term projects were due to the tons of details in source code, but some were due to inherent complexity and how to model something that works, no matter what the files content will be

▲

beginnings 3 days ago | parent | prev [-]

anything nontrivial is still long term, nothing has changed