SANS
GERARD
Spoken 201 times in 43 countries
Vertex AI
Complexity
Features
1
2
Global
Vertex AI
Complexity
Features
Image Generation
Google Lens
Google Search
Listen Response
Share
+40 Languages
C++, Go, Java, Javascript, Python and Typescript
Generate
complex graphics
Access your GMail.
Deep integration with YouTube.
Adjust model predictions using output
Wikipedia
Christopher  is
Christopher Columbus was
Input
Output
Christopher Columbus discovered  America
Christopher Columbus discovered America  in
Christopher Columbus discovered America in  1492
Christopher Columbus discovered America in 1492 Â .
Christopher Columbus discovered America in 1492.
Christopher Columbus discovered America in 1492.
Christopher Columbus discovered America in 1492.
Christopher Columbus discovered America in 1492.
Christopher Columbus discovered America in 1492.
Christopher Columbus discovered America in 1492 .
who
is
America
Columbus
discover
Latent Space
Word Embedding
Word Embedding
Biased
Non-factual
Inaccurate
1+1= 3
VectorDB Embeddings
Google Knowledge Graph
Google Search
Fact Checking
Antropomorphic
A program not a human.
Brain analogy is a myth. Very limited reasoning and planning.
Deterministic
Uncertain by design. Highly sensitive to inputs and learned patterns. Answers may change using an extra punctuation.
Prompt-driven
Output is dependent on training data. Prompts can't fix data issues or uneven distributions.
Neutral
Biased by training data. This is a blind spot. Difficult to find small mistakes.
Fact-retrieval
Not a database. Can't store or retrieve facts. Data cut-off. Not a search engine.
Perceived accuracy: 100%
Perceived accuracy: 85%
Real accuracy: 20%
Can be dangerous in high-stakes contexts. Eg: health or finance.
Can be used when errors have little to no consequences.
​Eg: summarising or rephrasing.
Safe to use in general. Perfect accuracy.
Source: V7 Labs
A dog running
Digits 0-9
Ant
French cat
MNIST
60K
10 classes
COCO
330K
80 classes
ImageNet
14MÂ
Image + caption
LAION (Web)
5B
Image + text
A prompt will put you in a certain area of the latent space
Note the density of data points and noise ratios
Query Patch
Detail
Image
"ginger fur"
"standing on a stone in the garden"
"well-groomed"
Image
Features
Attention
Visual Chat
VQA
Multi-turn
Reasoning
Extract Data
Handwriting
Data entry
OCR
Metadata
Identify
Recognition
Captioning
Categorising
Structure
Elements
Relationships
Hierarchies
Time/Space
Tracking
Activity
Causality
3D/4D
Monday to Friday from 6:30 to 13:00 from 16:30 to 20:00
Extract the text for the opening hours and consolidate them in a single paragraph in English
Prompt
Output
HORARI DILLUNS A DIVENDRES DE 6'30H. A
Extract Text
OCR
Image Input
Task
Raw Data
13H 16'30H. A 20'00H
Extract Text
Hand-written OCR
Reason
Mash-up fragments
HORARI DILLUNS A DIVENDRES DE 6'30H. A 13H 16'30H. A 20'00H
Translate
Catalan to English
Monday to Friday from 6:30 to 13:00 from 16:30 to 20:00
magazine style 4k photorealistic,
modern red armchair
natural lighting
Portrait of a french bulldog
at the beach,
85mm f/2.8
Assortment
of delicious,
freshly-baked donuts
Prompt
Imagen 2
Original + mask
Imagen 2
Input
Caption
GoogleAI
VertexAI
Pro 1.0
Pro 1.5
Ultra 1.0
Nano 1.0
Gemini 1.0 Pro 128K tokens
(100 pages)
Gemini 1.5 Pro 1M
(800 pages)
1h
video
11h
audio
30K
LOC
800
pages
1 Million tokens
Text: Apollo 11 script
402-pages
Video: Buster Keaton movie
44-minutes
Code: three.js demos
100K-LOC
Self-contained
Only what you need. Avoids fragmentation and relevance drift
Cost-effective
​Lower investment over time, fixed query latency. No fixed costs
User-guided
Unified data for focus, easier to control and improve quality
Interpretable
Improved transparency, easier to debug & iterate
English to Kalamang
Limited
Vertex AI
Complexity
Features