Agent mania setting in

It's also pretty funny sometimes how it gives weird future roadmap estimates ("part 2 - 3 weeks, part 3 - 2 months", etc.) and when you tell it to actually do those changes it's pretty much done in half an hour

▲

throw1234567891 4 minutes ago | parent | next [-]

It repeats what it has seen in the training data. Expecting it to reason about the complexity of a task is a pipe dream. The best is to tell it not to come back with estimates, and when it does, remove them anyway.

▲

smith7018 an hour ago | parent | prev [-]

I've long believed those numbers were faked by Anthropic/OpenAI to serve as a form of advertisement. The estimates are impossible to verify and their ability to do "2 days of work" in 10 minutes will presumably make the user go "Wow, I just saved SO much time!" Plus, the unnecessary text eats up the users' tokens so it helps the companies on the backend, as well.

	▲	leodavi 37 minutes ago \| parent \| next [-]
		I agree with you that labs are benefiting from those outputs but I'm skeptical that labs are purposefully training the models to produce those outputs. Raw pre-training data includes plenty of conversations between professional builders and some of those include estimates. I believe the outputs are a training coincidence with consequences that are opportunitistic for the labs.
	▲	dizhn 17 minutes ago \| parent \| prev \| next [-]
		All models do it. It's their training. They didn't have "a person does this in a week but an LLM could in a minute" in their training yet. They also don't have the concept of elapsed time unless you ask them how long something has taken.
	▲	AgentMasterRace 28 minutes ago \| parent \| prev [-]
		All the models have broken estimates. They're trained heavily on jira and GitHub tasks and issues, that's why their estimates are human.