Slides: Voice In, Visuals Out: The Agony and the Ecstasy - Allen Pike, Forestwalk Labs
Source Video
Voice In, Visuals Out: The Agony and the Ecstasy - Allen Pike, Forestwalk Labs
Relationship To World's Fair 2026
These slides are extracted from a public AI Engineer YouTube video connected to World's Fair 2026. Speaker-matched clips are supporting context unless later confirmed as exact session recordings; official livestream recordings are day-level/event-level source material.
Related Scheduled Sessions
- No individual scheduled session mapping has been assigned yet; treat this as an event livestream deck.
Extracted Slides
OCR text:
AIE
Voice In, Visuals Out
The Agony and the Ecstasy
AllenPike,ForestwalkLabs
AIEngineeringWF,2026
OCR text:
“Audio is the human-preferred
LS input to Als, but vision is the
preferred output from them.”
— Andre] Karpathy. May 2026
oe Ap
1 an v
P |
OCR text:
OUpt
THEME
Probetoiities
DARK
LIGHT
dit
BREAKPOINT
AIE
DESKTOP
TABLET
MOBILE
NETWORK
Arccolor
Arc width
Arcglow
Postona
Encodng
Postional
Arcdensity
Cnysize
Visualization
Interactivity
OCR text:
Oup
THEME
DARK
LIGHT
Sit
BREAKPOINT
AIE
DESKTOP
TABLET
MOBILE
NETWORK
Arccolor
Arcwidth
Arcglow
Postona
Enoodng
Postional
Arc density
Visualization
Interactivity
Beauty
OCR text:
AIE
THAJOOO
Voice In
OCR text:
ee Ere Marne T onl atl — -
Seer ee as MAAC rion IY ne Oa Ee rata eee
f af POLS NRSC CLS — simple instructions fae rta)
. nage 3 :
fmiied yw « c -<
r 4 a] ) aw 4
i Vas -Ba vy *
— bi : at eS
ak oe
a a Dees t ak
| 42° Oe { wv
What's going on... : KKkwhattotypeherem . Hopefully Al makes a 3 Wtdid too well. + Just leamed this :
te vens "8 evens ° Detter lawyer Twitch oy cen: 8 ay ews .
4 SMeeas
E en
fanaa _
OCR text:
a
ic ae
OCR text:
The Tyranny
AIE
of Latency
OCR text:
AIE
200ms-seamless voice
100ms-feelsinstant
OCR text:
rae] Pillars of low latency
Fast models
, }
ray
OCR text:
[ae] Pillars of low latency
Fast models Short intervals Stable cache
Fi
7 Ve
Slide-Derived Subjects To Review
Subject extraction uses video title, related session titles/descriptions, transcript context, and OCR text when available. OCR is best-effort and should be reviewed against the embedded slide images.