News for hackers. Stuff that matters.

A comment on Launch HN: Magnitude (YC S25) – Self-optimizing inference engine for agents.

Re:Launch HN: Magnitude (YC S25) – Self-optimizing inference... by kenzic on Wednesday September 30, 2026 @01:55PM (#49912193)
How long does tuning take (on an M3 MacBook Pro for example)?
[ Parent | on HN ]
Re:Launch HN: Magnitude (YC S25) – Self-optimizing inference... by anerli on Wednesday September 30, 2026 @02:10PM (#49912370)
Tuning is a one-time process that takes around ~1 minute whenever you download a new model. This is generally enough time to tune all the kernels' parameters to the point where tuning any longer asymptotes. Time can vary a little based on the hardware though.
[ Parent | on HN ]
Re:Launch HN: Magnitude (YC S25) – Self-optimizing inference... by kenzic on Wednesday September 30, 2026 @02:19PM (#49912459)
Wow, that's impressive.
[ Parent | on HN ]