E
Eli Bixby
1
APPEARANCES
1
PODCASTS
012
DEC 30
JAN 6
JAN 13
JAN 20
JAN 27
FEB 3
FEB 10
FEB 17
FEB 24
MAR 3
MAR 10
MAR 17
MAR 24
MAR 31
APR 7
APR 14
APR 21
APR 28
MAY 5
MAY 12
MAY 19
MAY 26
JUN 2
JUN 9
JUN 16
JUN 23
JUN 30
JUL 7
JUL 14
JUL 21
JUL 28
AUG 4
AUG 11
AUG 18
AUG 25
SEP 1
SEP 8
SEP 15
SEP 22
SEP 29
OCT 6
OCT 13
OCT 20
OCT 27
NOV 3
NOV 10
NOV 17
NOV 24
DEC 1
DEC 8
DEC 15
DEC 22
DEC 29
JAN 5
JAN 12
JAN 19
JAN 26
FEB 2
FEB 9
FEB 16
FEB 23
MAR 2
MAR 9
MAR 16
MAR 23
MAR 30
APR 6
APR 13
APR 20
APR 27
MAY 4
MAY 11
MAY 18
MAY 25
JUN 1
JUN 8
JUN 15
JUN 22
JUN 29
JUL 6
JUL 13
JUL 20
JUL 27
AUG 3
AUG 10
AUG 17
AUG 24
AUG 31
SEP 7
SEP 14
SEP 21
SEP 28
OCT 5
OCT 12
OCT 19
OCT 26
NOV 2
Nov 5, 2026
How Cradle’s AI Beat 130 Teams to Design a Cancer-Targeting Protein | Eli Bixby, Head of ML
29:59
41:45

Liam LawsonHOST
is fundamentally they are production machines um and i'm curious with you trying to diffuse some degree of originality into these into generating something new how that actually works in a technical level like take me through everything are you using your own models are you using other models what software and tech are you building around that like how does this actually work
E
30:23Eli BixbyGUEST
So for quite a while now, there's been sort of these unsupervised, at the very bottom level, there's been these unsupervised sort of protein language models or protein structure models, or now there's lots of models that do both.
E
30:49Eli BixbyGUEST
this ability to say, oh, we can use all of this unsupervised data that's lying around.
E
30:54Eli BixbyGUEST
And there's a lot of analogies to the LLM world to build sort of models that have an understanding of the basics in like a plausibility sense.
11 MINS LATER

Liam LawsonHOST
And I want to jump more into how those work in a second, but I'm curious, like what that actually looks like for you.