News for hackers. Stuff that matters.

A comment on Show HN: We replaced 5 ML models with 1 shared encoder on an $11/month VPS.

Re:Show HN: We replaced 5 ML models with 1 shared encoder on... by jacek-123 on Wednesday April 22, 2026 @11:55PM (#47872112)
Did you try GradNorm or PCGrad, or was manual task weighting good enough? Also curious about the required-vs-preferred head failing. Was that encoder gradient interference from the other tasks, or a capacity issue in the linear head?
[ Parent | on HN ]

There are no comments on this comment yet.