Slides: 120k players in a week: Lessons from the first viral CLIP app: Joseph Nelson
Source Video
120k players in a week: Lessons from the first viral CLIP app: Joseph Nelson
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:
an 86a
a Oey ie
A Ss ee
aa a
Mi
OCR text:
AIE
AUTOGPT
smol ai
OCR text:
The Premise: Convince an Al you’re the best artist
1) GPT: Generate a prompt for users to draw
eo User: Draws prompt in MS Paint interface
6 CLIP: Judge vector similarity of text
prompt and user image
@ ???: 120k players in one week, 7 requests
per second
OCR text:
Prompt: A Raccoon Driving a Tractor
Draw a raccoon driving a tractor Draw araccoon driving atractor | Oraw araccoon driving a tractor
Global Ranking: 462 out of 10.187 wubewssions Gtobel Ranking 335 out of 10.187 tudmesont Gobel Ranking: 3 out of 10.187 submessons
: cs ™ 7
\ fo} = ©
4 | Ly nneron?
revnonn - QR revscumn GQ"
OCR text:
Prompt: A Bumblebee that Loves Capitalism
Draw a bumblebee that loves capitaliam Draw a bumblebee that loves capitalism Draw a bumblebee that loves capitalism
Cadet Resharg. 216 ot of 14758 woemvom Globel Renting $51 ot of 14.7S8 wornnwons Ghebet Rentong 288 ont of 14.758 womeveons
eo wy aR
&
, ¢ ww, }
wy
oe: ‘mm
Tevacan - QD Tavacan - QD Tevacan - GD
6
OCR text:
CLIP: Trained on 400M image/text pairs, OpenAl, 2021
text_embedding: how CLIP Paint.wtf Scoring
maps the paint.wtf prompt into
its feature space CLIP’s Interpretation
x, of the Paint.wtf Prompt
Image_embedding: how CLIP cuPtissarpraention of
maps the user submission into saiaaeteiaiiaaiienaiiniias-
its feature space /e
Winning paint.wtf: minimizing Cosine Similarity S|
distance between the prompt i
and the user drawing
7
OCR text:
AIE
AUTOgPt
smoo
OCR text:
SILAR.
C
statpy
apy>no
iapertc2
ortisterence
iaport spevisiesassv
anotator-sv.Bcsknoteter()
etrender(resvtt,
Labge)t
piet(resolt)
ieshovl
"ootpot".
anotater-annetate(
sere-iavpe.
detectionsniv.De
(v2.vaitKeyi1)
AT
iaference.Streanc
source·2,
modet-"rock-
wesain_thresd-Trut,
ovtput_chanoeorder
osredicties.render
LARColS
OCR text:
"
‘ ALENGN
7 MANN VY
OCR text:
SEAR..
stMLOY
12 "ovtpun", a50. sceserisaor, desectist ages/inference/core/interfaces/stream/strean.py,line 157,in._init.. ages/inference/core/interfaces/strean/strean.py,line 3e4,in run_thread File*/Users/josephnelson/dev/ai-engineer/inftalk/1ib/python3.1o/site-gack self.inference_requeat_thread() self.run_thread()
1.9
19 20 Z1 22 2x 24 27 aference.Streanl ovtput_channeLarder. source.2, mel-"rock uie_sain_threed-True, 292.4 -50wr11 nda3/1ib/python3.1e/threading.py'> ages/inference/core/interfaces/strean/strean.py,line 282,in inference_reg uest_thread CException ignoredSn!<module'threading'from Traceback(eost recent calllast)1 File/Users/sosephnelson/dev/ai-engineer/start.py", cb（predictions,self.frane_cv) cv2.eaitxeyt1) Jsers/josephnelson/ninico 1ine 16,inrender
23 msredieties 67,in_shutdon Keyboardtnterrvot: leck.acquire()
(inftaik)（base)josephnelsongJosephs-map-3ai-engineer%python start.py Traceback（most recent call last): File/Usera/josephnelson/dev/ai-engineer/start.py,line 3,in<module> fron inference.modelingort clip
(inftalk)（base)joseghnesongJosephs-Map-3ai-engineerx
setashe det ton instalone cfournewformaterednsion？Thiswilaso RatterferPyhon of
Ln3,C2254UTF-UF
OCR text:
000
SEAR..
starLpy
17 28 21 22 24 27 29 19 28 clip-Clp Lsport shference text_enbedding-clig.enbed_text（gro fron mdel-clip. vie_oin_thread.Trve, ieference.nodels inpert Clip source.2, Wtpit_chaneLoreer. onsredictiosarer printiresit) resderiresslt, c2.inhei c2.vaitkey(1) outpit', tacor.ao sceseninage, detectien etstel Tracebsck(most recent call lest): NameError!nane'render'isnotdefines (inftalk) (base)josephnelaongJosephs-MaP-3ai-engineer xpython atart.py File/Uaera/josephnelson/dev/ai-engineer/start.py,1ine 20,incnodule> -2.64115313e-01 -1.749349090-01 -1.877274346-01 -9.52770412e-02 -2.82019377e-02-1.54569581e-01 -1.05047315e-015.85544035e-02 -8.57200846e-02 -2.95410380e-02 -4.164822030-02 -1.87377974e-01 -1.40733317e-01 1.78932637e-01 6.72230273e-02 2.77497377e-02-9.39981341e-02 5.148771410-02 8.811201160-02 1.29763842e-01 1.79062380e-01 9.65760350e-02 1.21351220e-01 4.89275005e-02 on_prediction=render -1.31694108e-01 -8.48577321e-02 -9.236798240-02 -3.718575240-01 -1.46396488e-01 -5.08920840e-03 -1.746433946-01 20-+00060956'9- -4.11540449e-01 2.97449529e-02 1.09019071e-01 2.00923234e-01 3.56133282e-01 3.51662338e-01 2.70213808e 1.62222300e+00 3.54486555e-02 2.93375552e -02 -01 -5.72258607e-02 -6.013145300-02 -6.674434040-02 -3.318021000-01 -8.358273664-03 -6.964379284-02 -3.15130161e-01 -1.10945351e-01 -3.083823990-02 -1.167899820-01 -6.434806484-02 4.869020840-01-7.72674799e-01 2.009732134-017.64982233e-0411 1.981199680-01 1.83216166e+00 2.766016720-01 3.028125000-01 2.65872121e-01 2.245157064-01 7.063483734-02 2.56329387e-01 -1.13056585e-01 -2.69213855e-01 -1.81438118e-01 -4.18238580e-01 -1.99865073e-01 -6.17044978e-02 -1.91159070e-01 -1.706174460-01 -2.08871037e-01 -1.06113903e-01 4.20555323e-01 1.455015240-01 1.63303614e-01 2.29426712e-01 1.302200410-01 2.081671060-01 4.379215840-02 1.421204810-01 7.311619820-03
of
L29,C2
OCR text:
AIE winilerity · omin leirleelaiaulerit
Co?.ntt gtt.n,yi 12,24,154.255.1.FONTWE
O.tlsf prpr (2.1a0sm1. H 25,2,2350.110
FINIE
OCR text:
ove. pu
arrare le
32
cw2. im
cv2.Wa
inference,
source
model
; use_me
a CUR aot
OCR text:
oes ry fa) : a
D paint.wtf @
Convince an Ai thet you're the beet artiet.
Best of All Time
toverer’ tenons
" wre men ly inp. evan i ethan ont tare o> Oped OF
Sent .
9p} Ssimoln
== AUTO GPL,
OCR text:
. |. : : as > er soe —_
ci o oar] cr ee 2) .
| Oraw a gorilla gardening with grapes suséIT
oorttrtwti‘a‘SOOOOOOS
70
O°.
; or
+
a
s
*.
as
QQ! y
eT
OCR text:
AI Engineer
SUMMIT
OCR text:
i a
he 47,
» T/O oa
iN
AlEngineer | | |e
ST ~
cf wm ON
MiG
[xine] “ eee Fr dan “3 a lh grcpes Lo
Aree,
OCR text:
LIVE CODING
Let's be 1000x Engineers Today
OCR text:
Lessons from Building Paint.wtf with CLIP
We're all learning here
CLIP Can Read
Draw a raccoon driving a tractor
Global Ranking: 586 out of 10,187 submissions
TRY AGAIN
choose another prompt
Draw a raccoon driving a tractor
Global Ranking: 81 out of 10,187 submissions
TRY AGAIN
choose another prompt
10
OCR text:
Lessons from Building Paint.wtf with CLIP ; Se
CLIP Can Read
ee teawr teen tenene sheila lala
ae — Reo A facc Ooh
eae ARivivry Xs
= #
. TRACTOR.
vt J ter scam - GD ravacan - ED
ed
te
OCR text:
Lessons from Building Paint.wtf with CLIP
Roboflow Inference Makes Life Easy
Serving done right. an aad
Built on the lessons of serving 100M of API ; interop - . -
calls and thousands of hours of video. ee
e Maximize throughput on your target ee
hardware (GPU, CPU, edge) ie ao
e Use ready-to-go foundation models ini
e Pullin over 50k pretrained models from a aed
Roboflow Universe community are eas
14
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.