This sounds interesting but (from the homepage too) I don't understand how it's ... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		OJFord 5 days ago \| parent \| context \| favorite \| on: Agents don't need memory, they need documentation This sounds interesting but (from the homepage too) I don't understand how it's different than having it run any other linter?
		help

Garlef 5 days ago [–]

The difference is that the error messages contain instructions on how to resolve the issue.

Just flagging big functions will make the agent write small functions ~ but not necessarliy in a good way

(for example the agent might just cut `doOneThingAndTheOther` in half and call the second half `doOneThingAndTheOther2`)

Consider applying for YC's Winter 2027 batch! Applications are open till November 2.
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact