Posts
149 posts
AI knowledge systems from documents to answers
RAG Failures After Retrieval
Specializing LLM Inference Stages
Perceived Effects and Measured Outcomes of AI Tools
How Collision Handling Changes Hash Costs
LLM Defenses at Action Boundaries
Compute Allocation in Multi-Agent Teams
Layers Where Transaction Costs Sit
Stopping Policy in Agentic Search
Measurement Boundaries in LLM Serving Optimization
Why Recovery Paths Need Separate Verification
What to Check When Using AI at Work
How Companies Operate Coding Agent Harnesses
Delayed Feedback in Distributed Routing
Timing Leaks in Shared Prefix Caches
Non-Prefix KV Cache Reuse in RAG
From Token Alignment to Representation-Level Defense
Judging Multi-Agent Adoption on Reliability
Three Approaches to Reducing Consensus Latency
Indexing and Query Processing in RAG
The Gap Between Data Structure Theory and Libraries
The Tool Layer as the Agent Bottleneck
LLM Serving Seen Through the KV Cache
Agent Memory Compaction and Provenance
Consistency Boundaries of 2PC and Commit Logs
Speculative Tool Execution for Agents
Gray Failure Detection in Adaptive Routing
Measuring Costs Across Storage-Engine Layers
Evaluating Rerankers and Answer Quality
MCP Tool Discovery and Dynamic Loading
Context, State, Memory, and Checkpoints
Complexity of Graph-Based Approximate Nearest Neighbor Search
DAG-Based BFT Consensus and Leader-Based BFT
The Confused Deputy and Agent Identity
Distributed Rate Limiting Architecture
Epoch-Based OCC and the Geo-Replication Boundary
Multi-head Latent Attention and KV Cache Compression
Cuckoo Hashing and Fingerprint Filters
Embedding Inversion Attacks
MoE Load Balancing and Gradient Interference
FIFO Cache Eviction Replacing LRU
Idempotency and Transaction Integrity in Payment Systems
Sizing and Verifying Acceptable Throughput
Raft Leader Leases and Linearizable Reads
Evaluating RAG Datastore Membership
Late Interaction Reranking
LLM Agent Memory Poisoning
LLM Jailbreaks and Automated Red Teaming
Delay-based and rollback netcode
Evaluating Multi-Agent Systems and Choosing an Orchestration Topology
Agent Harnesses and Loop Engineering
MCP Tool Poisoning
OpenAI o1 and DeepSeek-R1 Reasoning Models
LLM Privacy Defenses
String Algorithms for Coding Tests
LLM Privacy Attacks
Advanced Graph Patterns for Coding Tests
RAG Cross-Encoder Reranking
Verifying AI-Generated Code
DPR-Based Dense Retrieval for RAG
Django FBVs and CBVs
An Overview of Diffusion Language Models
Observability Through Datadog
AWS Container Services
Output Guardrails, Observability, and the Right to Erasure
Egress Gateway Defense
Defenses at the Agent, RAG, and MCP Layers
Input-Side PII Anonymization and Reversible Mapping
How Personal Data Leaks, and What Data Governance Has to Cover
Concurrency Control and Synchronization
Designing a Live Streaming System
Deploying and Operating Celery
CRDT
Assessing the Expressive Power of a Single Operator
Celery Canvas Workflows
LSM Trees and Write Amplification
Celery Task Routing and Reliability
Database Transactions and MVCC
Celery Architecture and the Message Lifecycle
Scale-Out and Scale-Up
Spring Data Access Technologies
Elasticsearch Operations and Performance Tuning
Redis High Availability
The Spring MVC Request Flow
Elasticsearch Sharding Architecture
Redis Persistence and Replication
Spring Transactions and Propagation
Elasticsearch Query DSL and Aggregations
Redis Memory Management and Eviction
Spring AOP and Proxies
Elasticsearch Mappings and Analyzers
Test Automation
Redis Data Structures and How to Use Them
Spring DI and the IoC Container
Exposing a Home Server Safely with Cloudflare Tunnel
JWT Authentication and TOTP 2FA
Agent Orchestration with LangGraph
Momentum Trading Strategies
Code Review and Commit Conventions
Design Patterns for an Event-Driven Trading System
Test-Time Compute Scaling
Toolformer
RAG
Blue/Green Deployment Operations
Agent Debate with Shared Retrieved Evidence
Multi-Agent Debate
LATS (Language Agent Tree Search)
Cloud CI/CD Blue/Green Deployment
Tree of Thought (ToT)
CRITIC
Self-Refine
Kubernetes Blue/Green Deployment
Reflexion
ReAct (Reasoning + Acting)
TLS and HTTPS
Chain of Thought (CoT) Step-by-Step Reasoning
Blue/Green Deployment Fundamentals
Transformer Architecture and LLM Serving Optimization
Socket Programming
Operating System I/O Management and File Systems
Application Layer Protocols
Incident Response and Management
Processes and CPU Scheduling
Transport Layer Protocols
Operating System Memory Management
System Calls and Interrupts
Containerization and Orchestration
Kubernetes in Depth
Kubernetes Core Concepts
Rust Overview
Monitoring and Observability
Git Branching Strategies
TDD, BDD, DDD, SDD
Bellman-Ford Shortest Paths
Dijkstra's Shortest Path Algorithm
Advanced Git
Minimum Spanning Tree (MST) Algorithms
Database Denormalization Strategies
Behavioral Patterns
Load Balancing
PostgreSQL vs MySQL Indexing
A Guide to MySQL Partitioning
Building Custom Pagination in Django
Structural Patterns
Creational Patterns
Multi-Level Caching Strategies
Network Layer Models and Data Communication
The SOLID Principles
Core Data Structures