> 100% of today’s SWE tasks are done by the models.
Meanwhile, Claude Code is implemented using a React-like framework and has 6000 open issues, many of which are utterly trivial to fix.
He does not specify if tasks are done correctly. Merge your change request full of ai slop and close the task in jira as done. Voila! Velocity increased to the moon! 6000 or 7000 open issues - who cares?
He does not specify if tasks are done correctly. Merge your change request full of ai slop and close the task in jira as done. Voila! Velocity increased to the moon! 6000 or 7000 open issues - who cares?