Author

DeepHub IMBA

A must‑follow public account sharing practical AI insights. Follow now. internet + machine learning + big data + architecture = IMBA

Articles

Likes

Views

Comments

Latest from DeepHub IMBA

55 recent articles

DeepHub IMBA

Mar 14, 2026 · Artificial Intelligence

Three Proven Multi‑Agent Orchestration Patterns: Supervisor, Pipeline, and Swarm

The article explains why single LLM agents often fail due to context overload, role confusion, and fault propagation, then details three reliable orchestration patterns—Supervisor, Pipeline, and Swarm—along with concrete code examples, communication schemas, error‑handling layers, cost and latency considerations, and best‑practice recommendations for production deployment.

Cost OptimizationLLM agentsMulti-Agent Systems

0 likes · 15 min read

Three Proven Multi‑Agent Orchestration Patterns: Supervisor, Pipeline, and Swarm

DeepHub IMBA

Mar 13, 2026 · Artificial Intelligence

Why Bigger Context Windows Make RAG Essential, Not Redundant

Although expanding LLM context windows seems to eliminate the need for Retrieval‑Augmented Generation, in practice larger windows dilute attention and cause retrieval failures, so RAG remains crucial for filtering high‑signal content and maintaining answer quality.

AI architectureAttention DilutionLLM

0 likes · 7 min read

Why Bigger Context Windows Make RAG Essential, Not Redundant

DeepHub IMBA

Mar 12, 2026 · Artificial Intelligence

LangGraph vs Semantic Kernel: Comparing State‑Graph and Kernel‑Plugin Architectures

This article updates the comparison of LangGraph and Semantic Kernel for Python AI agents, outlines their recent releases, explains their core architectural models, shows side‑by‑side code examples, and provides concrete decision criteria for choosing the appropriate framework.

AI agentsKernel PluginLangGraph

0 likes · 14 min read

LangGraph vs Semantic Kernel: Comparing State‑Graph and Kernel‑Plugin Architectures

DeepHub IMBA

Mar 11, 2026 · Fundamentals

Detecting Time‑Series Change Points with Grid Search and Piecewise Regression

This article shows how to turn change‑point detection into an optimization problem by exhaustively searching knot configurations with grid search, selecting the best model using a penalised likelihood criterion (BIC), and applying piecewise regression to automatically locate trend breakpoints, illustrated with R and Python code on California natural‑gas consumption data.

BICPythonR

0 likes · 12 min read

Detecting Time‑Series Change Points with Grid Search and Piecewise Regression

DeepHub IMBA

Mar 10, 2026 · Fundamentals

7 Hidden Python Stdlib Tools That Simplify Your Code

The article presents seven powerful Python standard‑library features—generators for lazy evaluation, defaultdict for concise counting, pathlib for robust path handling, functools.partial for quick function specialization, itertools for flattening nested loops, type for dynamic class creation, and decorators for reusable logic—showing how each reduces memory usage, simplifies code, and improves automation.

GeneratorsPythonStandard Library

0 likes · 7 min read

7 Hidden Python Stdlib Tools That Simplify Your Code

DeepHub IMBA

Mar 8, 2026 · Artificial Intelligence

MIT Study: How Self‑Generated History Pollutes LLM Context and Degrades Multi‑Turn Chats

An MIT paper reveals that storing a language model’s own prior replies—known as context pollution—significantly lengthens the dialogue context while offering little quality benefit, with up to a ten‑fold reduction in tokens and comparable responses for about 70% of turns, especially in open‑source models.

AI agentsLLMMIT study

0 likes · 11 min read

MIT Study: How Self‑Generated History Pollutes LLM Context and Degrades Multi‑Turn Chats

DeepHub IMBA

Mar 7, 2026 · Artificial Intelligence

From AutoGen v0.4 to Microsoft Agent Framework: A Complete Architectural Evolution

This article traces the rise of Microsoft AutoGen, explains its core design and v0.4 architecture, showcases code examples and benchmark results, examines its limitations, and details the transition to the Microsoft Agent Framework and its current state in 2026.

AutoGenGroupChatLLM multi-agent

0 likes · 16 min read

From AutoGen v0.4 to Microsoft Agent Framework: A Complete Architectural Evolution

DeepHub IMBA

Mar 6, 2026 · Artificial Intelligence

New March 2026 Paper Exposes Fraudulent Third‑Party APIs for Large Language Models

A recent arXiv study audited 17 popular shadow APIs used in 187 papers, finding up to a 47.21% performance gap versus official models—e.g., Gemini‑2.5‑flash’s accuracy drops from 83.82% to about 37% on MedQA—highlighting serious reliability and safety risks of unofficial LLM services.

AI safetylarge language modelsmodel verification

0 likes · 3 min read

New March 2026 Paper Exposes Fraudulent Third‑Party APIs for Large Language Models

DeepHub IMBA

Mar 6, 2026 · Fundamentals

Measuring Multivariate Distribution Differences with Energy Distance

Energy Distance is a statistical metric that quantifies how far two multivariate probability distributions diverge by comparing cross‑distribution and within‑distribution Euclidean distances, and it can be combined with permutation testing to assess the significance of observed shifts.

Energy Distancedata driftdistribution comparison

0 likes · 6 min read

Measuring Multivariate Distribution Differences with Energy Distance

DeepHub IMBA

Mar 6, 2026 · Artificial Intelligence

Shadow APIs vs Official LLMs: Up to 47% Performance Gap Revealed in New Study

A recent arXiv paper audits 17 widely used shadow APIs, showing that their outputs can deviate from official large language model APIs by as much as 47.21%, with accuracy on the MedQA benchmark dropping from 83.82% to around 37%, raising serious reliability concerns.

AI safetylarge language modelsmodel verification

0 likes · 3 min read

Shadow APIs vs Official LLMs: Up to 47% Performance Gap Revealed in New Study