AI Explained Series' Articles

Cover image for Is Grep All You Need? Grep vs Vector Retrieval for Agentic Search

pueding

May 21

Is Grep All You Need? Grep vs Vector Retrieval for Agentic Search

#agents #llm #rag #ai

2

7 min read

Cover image for MCP SEP-2468: RFC 9207 Iss Parameter for OAuth Mix-Up Defense

pueding

May 22

MCP SEP-2468: RFC 9207 Iss Parameter for OAuth Mix-Up Defense

#ai #agents #mcp #security

1

8 min read

Cover image for Camouflage Injection Paper: Camouflage Detection Gap

pueding

May 23

Camouflage Injection Paper: Camouflage Detection Gap

#ai #agents #security #llm

7 min read

Cover image for OpenSCAD Pantheon Benchmark: Human-In-The-Loop vs Autonomous Coding Agents

pueding

May 24

OpenSCAD Pantheon Benchmark: Human-In-The-Loop vs Autonomous Coding Agents

#ai #agents #productivity #llm

8 min read

Cover image for Boiling the Frog Paper: Multi-Turn Norm Erosion vs Single-Prompt Agent Safety

pueding

May 25

Boiling the Frog Paper: Multi-Turn Norm Erosion vs Single-Prompt Agent Safety

#ai #agents #llm #security

8 min read

Cover image for Cursor Composer 2.5: Targeted Textual Feedback RL

pueding

May 26

Cursor Composer 2.5: Targeted Textual Feedback RL

#ai #llm #machinelearning

8 min read

Cover image for CDD Paper: Context-Driven Decomposition for RAG Knowledge Conflict

pueding

May 27

CDD Paper: Context-Driven Decomposition for RAG Knowledge Conflict

#ai #llm #rag #agents

9 min read

Cover image for Gemini 3.5 Flash: Agent-First Model Design

pueding

May 29

Gemini 3.5 Flash: Agent-First Model Design

#ai #agents #llm #machinelearning

1

8 min read

Cover image for OmniRetrieval: Source-Native Query Dispatch

pueding

May 30

OmniRetrieval: Source-Native Query Dispatch

#ai #rag #llm #agents

6 min read

Cover image for Claude Opus 4.8: Parallel-Subagent Dynamic Workflows

pueding

May 31

Claude Opus 4.8: Parallel-Subagent Dynamic Workflows

#agents #ai #llm

6 min read

Cover image for AgentDoG 1.5: Small Inline Guard Models for Agent Actions

pueding

Jun 1

AgentDoG 1.5: Small Inline Guard Models for Agent Actions

#ai #security #agents #llm

7 min read

Cover image for GrepSeek Trains a Search Agent to Use Shell Commands: GRPO-Trained Shell-Command Search

pueding

Jun 2

GrepSeek Trains a Search Agent to Use Shell Commands: GRPO-Trained Shell-Command Search

#ai #agents #rag #llm

6 min read

Cover image for Harness-1: State-Externalizing Search Harness

pueding

Jun 3

Harness-1: State-Externalizing Search Harness

#ai #agents #llm

7 min read

Cover image for Microsoft MAI-Code-1-Flash: Adaptive Solution-Length Control

pueding

Jun 4

Microsoft MAI-Code-1-Flash: Adaptive Solution-Length Control

#ai #llm #machinelearning

1

6 min read

Cover image for Token Budgets Paper: Affine-Typed Budget Ownership

pueding

Jun 5

Token Budgets Paper: Affine-Typed Budget Ownership

#agents #ai #llm

6 min read

Cover image for MCP 2026-07-28 RC: Stateless Transport

pueding

Jun 6

MCP 2026-07-28 RC: Stateless Transport

#mcp #ai #agents #devops

9 min read

Cover image for MarginGate: Margin-Gated Verification for Batch-Invariant Decoding

pueding

Jun 7

MarginGate: Margin-Gated Verification for Batch-Invariant Decoding

#llm #ai #machinelearning #tutorial

5 min read

Cover image for MCP SEP-2106: Full JSON Schema 2020-12 in Tool I/O

pueding

Jun 8

MCP SEP-2106: Full JSON Schema 2020-12 in Tool I/O

#mcp #ai #agents #tutorial

1

7 min read

Cover image for AutoLab Benchmarks Frontier Agents on Long-Horizon R&D Tasks: Iterative Experiment-Loop Evaluation

pueding

Jun 9

AutoLab Benchmarks Frontier Agents on Long-Horizon R&D Tasks: Iterative Experiment-Loop Evaluation

#agents #ai #llm #machinelearning

6 min read

Cover image for Agent-Harness Scaling Law: Feedback Quality Predicts Success, Not Raw Compute: Effective Feedback Compute (EFC)

pueding

Jun 10

Agent-Harness Scaling Law: Feedback Quality Predicts Success, Not Raw Compute: Effective Feedback Compute (EFC)

#agents #ai #llm #machinelearning

7 min read

Cover image for Google Releases DiffusionGemma: Parallel Block Decoding

pueding

Jun 11

Google Releases DiffusionGemma: Parallel Block Decoding

#ai #llm #machinelearning #tutorial

3

6 min read

Cover image for MiniMax M3 Ships Open-Weight 1M Context: MiniMax Sparse Attention (MSA)

pueding

Jun 12

MiniMax M3 Ships Open-Weight 1M Context: MiniMax Sparse Attention (MSA)

#ai #llm #machinelearning #tutorial

6 min read

Cover image for Google Ships Gemma 4 QAT Checkpoints: Quantization-Aware Training

pueding

Jun 13

Google Ships Gemma 4 QAT Checkpoints: Quantization-Aware Training

#ai #llm #machinelearning #tutorial

1

6 min read

Cover image for NVIDIA RTX Spark Superchip: Unified CPU–GPU Memory

pueding

Jun 14

NVIDIA RTX Spark Superchip: Unified CPU–GPU Memory

#ai #machinelearning #llm #agents

1

8 min read

Cover image for NVIDIA Blackwell Leads AgentPerf, the First Agentic-AI Infra Benchmark: Trajectory-Replay Benchmarking

pueding

Jun 15

NVIDIA Blackwell Leads AgentPerf, the First Agentic-AI Infra Benchmark: Trajectory-Replay Benchmarking

#ai #agents #llm #machinelearning

6 min read

Cover image for Google Releases Gemma 4 12B: Encoder-Free Multimodal Projection

pueding

Jun 16

Google Releases Gemma 4 12B: Encoder-Free Multimodal Projection

#ai #llm #machinelearning #google

6 min read

Cover image for Microsoft FastContext: a Repo-Explorer Subagent Cuts Coding-Agent Tokens 60%: Explorer-Subagent Context Offloading

pueding

Jun 17

Microsoft FastContext: a Repo-Explorer Subagent Cuts Coding-Agent Tokens 60%: Explorer-Subagent Context Offloading

#ai #agents #llm #devops

7 min read

Cover image for FlashMemory Cuts DeepSeek-V4's KV Cache to 13.5%: Lookahead Sparse Attention

pueding

Jun 18

FlashMemory Cuts DeepSeek-V4's KV Cache to 13.5%: Lookahead Sparse Attention

#ai #llm #machinelearning

6 min read

Cover image for NVIDIA Blackwell Sweeps MLPerf Training 6.0: Strong Scaling

pueding

Jun 20

NVIDIA Blackwell Sweeps MLPerf Training 6.0: Strong Scaling

#ai #machinelearning #llm #devops

6 min read

Cover image for AMD ATOM + ATOMesh: Prefill/decode Disaggregation on ROCm

pueding

Jun 21

AMD ATOM + ATOMesh: Prefill/decode Disaggregation on ROCm

#ai #llm #devops #machinelearning

7 min read

Cover image for Agent Leaderboards Mislead Under Distribution Shift (IBM): Predictive Validity

pueding

Jun 22

Agent Leaderboards Mislead Under Distribution Shift (IBM): Predictive Validity

#agents #ai #llm #machinelearning

7 min read

Cover image for GLM-5.2 Becomes the Top Open-Weights Model: Active vs Total Parameters

pueding

Jun 23

GLM-5.2 Becomes the Top Open-Weights Model: Active vs Total Parameters

#llm #ai #machinelearning

6 min read

Cover image for Baidu Unlimited OCR Holds the KV Cache Constant for 40+ Pages: Reference Sliding Window Attention

pueding

Jun 26

Baidu Unlimited OCR Holds the KV Cache Constant for 40+ Pages: Reference Sliding Window Attention

#ai #llm #machinelearning

8 min read

Cover image for OpenAI and Broadcom's Jalapeño, a Custom Inference ASIC: Inference ASIC vs GPU

pueding

Jun 27

OpenAI and Broadcom's Jalapeño, a Custom Inference ASIC: Inference ASIC vs GPU

#ai #llm #hardware #machinelearning

5

7 min read

Cover image for Qwen-AgentWorld Trains a Language Model as a World Model for RL Agents: World Model as a Decoupled RL Simulator

pueding

Jun 28

Qwen-AgentWorld Trains a Language Model as a World Model for RL Agents: World Model as a Decoupled RL Simulator

#agents #ai #llm #machinelearning

6 min read

Cover image for CacheWeaver Reorders RAG Evidence for Prefix-Cache Reuse: Prefix-Cache-Aware Evidence Reordering

pueding

Jun 29

CacheWeaver Reorders RAG Evidence for Prefix-Cache Reuse: Prefix-Cache-Aware Evidence Reordering

#rag #llm #ai #machinelearning

3

7 min read

Cover image for SGLang v0.5.14: LPLB Expert-Parallel Load Balancing

pueding

Jun 30

SGLang v0.5.14: LPLB Expert-Parallel Load Balancing

#ai #llm #machinelearning #devops

7 min read

Cover image for S-Agent: Spatial Tool-Use Makes an 8B Agent Rival GPT-5.4 on Spatial Reasoning: Spatio-Temporal Evidence Accumulation

pueding

Jul 1

S-Agent: Spatial Tool-Use Makes an 8B Agent Rival GPT-5.4 on Spatial Reasoning: Spatio-Temporal Evidence Accumulation

#agents #ai #llm #machinelearning

6 min read