Skip to content
Fintech AI Lab
Research Notes
Posts
한국어
Map
Books
About
Search
Knowledge map
EN
한국어
Map
Each dot is a post. A line means one post links to another.
Better Agents Come From…
Context Compaction
Agentic Engineering in …
The Age of AI Paying
How Chinese Fintech Act…
World Models (1) What C…
Where Transformers Fit …
All
30
Financial AI & fraud
6
Payments & commerce
6
LLMs & agents
6
AI coding
4
World models
6
Notes
2
All posts by topic
Financial AI & fraud
6
[FDS] Finding the 0.015%: Transaction Sequence Models, Anomaly Detection and Graphs
2 links
Where Transformers Fit in Credit Models: Affirm, Revolut, Parafin and Ant
4 links
Sales Forecasting (1) From Tree Models to Chronos
4 links
Sales Forecasting (2) Inside Time Attention and Group Attention
3 links
[FDS] How Does Stripe Judge Payment Fraud in 100ms?
6 links
Agentic Engineering in Financial AI
6 links
Payments & commerce
6
Will AI Companies Become Payments Companies? Who Makes Money When an Agent Buys
3 links
Ah Bao Arrives: Alipay's Turn Toward an AI-Native Super App for a Billion Users
4 links
How Chinese Fintech Actually Works: The Triangle of Super Apps, Mini Programs and Payment Rails
4 links
The Evolution of the Digital Yuan: In 2026, e-CNY Becomes Interest-Bearing Digital Deposit Money
3 links
The Age of AI Paying: Alipay's AI付, AI收 and the Start of the Agent Economy
6 links
WeChat's Different Road: A 1.4 Billion MAU Super App Absorbs the Agent
4 links
LLMs & agents
6
Nobody Touched a Line of Code and the System Broke: The Paths by Which Data Quietly Rots
4 links
Thinking About the FDE: Ten Names, One Job
5 links
The Model Is Smart, So Why Is the System Stupid? Most AI Failures Start Outside the Model
9 links
How Do You Grade an LLM? Eleven Evaluation Methods, Sorted into Four Families
7 links
Context Compaction: Don't Give the Agent Everything, Keep Only What It Needs
4 links
Better Agents Come From a Better Harness, Not a Better Prompt
11 links
AI coding
4
Taking Apart Andrew Ng's AI Engineering Skills Map: Four Items Saying One Thing
3 links
[Notes] These Days My Manager Isn't the First to Read My Report
3 links
Where Does AI Coding Tool Usage Get Recorded? The Four Tokens ccusage Shows You
Productivity in AI Coding Comes from Decomposition and Feedback Loops, Not Better Prompts
3 links
World models
6
Norms Are Not in the Data: The Two Lineages of World Models
8 links
Is Palantir's Ontology Really an Ontology?
4 links
How the Two Lineages of World Models Got Here: Seventy Years, Made Simple
3 links
World Models (1) What Comes After the LLM: AI That Predicts the Next Frame
4 links
World Models (2) Why Not Hand the Whole World to the Model
4 links
World Models (3) Why a Game Is the Harshest Test Bed
3 links
Notes
2
[Notes] Why Data Scientists and Data Engineers Need Sales Skills
2 links
Starting This Blog