imit (@imitationlearn) 's Twitter Profile
imit

@imitationlearn

the minima are so pretty

ID: 1824166383204392960

linkhttp://imitationlearn.bearblog.dev calendar_today15-08-2024 19:29:04

21,21K Tweet

867 Followers

1,1K Following

ueaj (@_ueaj) 's Twitter Profile Photo

thebes I have this theory that to some degree real deep research in ML is about distilling core components of your personality and functioning into computer algorithms. This to me explains why models seem to generalize to what I perceive as like the aggregate "vibes" or "personality" of

snwy (@snwy_me) 's Twitter Profile Photo

it was not a waste of time; i've successfully made a super weird Qwen thing! it's approx 14.5B params, made from Qwen3-8B and Qwen3-235-A22B mixed together by doing a super cursed process; this was only possible because both of these models share the same hidden size! (1/2)

it was not a waste of time; i've successfully made a super weird Qwen thing! it's approx 14.5B params, made from Qwen3-8B and Qwen3-235-A22B mixed together by doing a super cursed process; this was only possible because both of these models share the same hidden size! (1/2)
imit (@imitationlearn) 's Twitter Profile Photo

it’s a shame that the baby (ones very own life experience filled with emotion, which is all that one has) is being thrown out with the bath water (the attachment to the self that one made from those experiences)