DEV Community

pueding profile picture

pueding

Computer Science and Engineering

Joined Joined on  Personal website https://learnaivisually.com/ github website
Agent-Harness Scaling Law: Feedback Quality Predicts Success, Not Raw Compute: Effective Feedback Compute (EFC)
pueding profile

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

#agents #ai #llm #machinelearning
Comments
7 min read
AutoLab Benchmarks Frontier Agents on Long-Horizon R&D Tasks: Iterative Experiment-Loop Evaluation
pueding profile

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

#agents #ai #llm #machinelearning
Comments
6 min read
MCP SEP-2106: Full JSON Schema 2020-12 in Tool I/O
pueding profile

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

#mcp #ai #agents #tutorial
Comments
7 min read
MarginGate: Margin-Gated Verification for Batch-Invariant Decoding
pueding profile

MarginGate: Margin-Gated Verification for Batch-Invariant Decoding

#llm #ai #machinelearning #tutorial
Comments
5 min read
MCP 2026-07-28 RC: Stateless Transport
pueding profile

MCP 2026-07-28 RC: Stateless Transport

#mcp #ai #agents #devops
Comments
9 min read
Token Budgets Paper: Affine-Typed Budget Ownership
pueding profile

Token Budgets Paper: Affine-Typed Budget Ownership

#agents #ai #llm
Comments
6 min read
Microsoft MAI-Code-1-Flash: Adaptive Solution-Length Control
pueding profile

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

#ai #llm #machinelearning
1
Comments
6 min read
Harness-1: State-Externalizing Search Harness
pueding profile

Harness-1: State-Externalizing Search Harness

#ai #agents #llm
Comments
7 min read
GrepSeek Trains a Search Agent to Use Shell Commands: GRPO-Trained Shell-Command Search
pueding profile

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

#ai #agents #rag #llm
Comments
6 min read
AgentDoG 1.5: Small Inline Guard Models for Agent Actions
pueding profile

AgentDoG 1.5: Small Inline Guard Models for Agent Actions

#ai #security #agents #llm
Comments
7 min read
Claude Opus 4.8: Parallel-Subagent Dynamic Workflows
pueding profile

Claude Opus 4.8: Parallel-Subagent Dynamic Workflows

#agents #ai #llm
Comments
6 min read
OmniRetrieval: Source-Native Query Dispatch
pueding profile

OmniRetrieval: Source-Native Query Dispatch

#ai #rag #llm #agents
Comments
6 min read
Gemini 3.5 Flash: Agent-First Model Design
pueding profile

Gemini 3.5 Flash: Agent-First Model Design

#ai #agents #llm #machinelearning
Comments 1
8 min read
CDD Paper: Context-Driven Decomposition for RAG Knowledge Conflict
pueding profile

CDD Paper: Context-Driven Decomposition for RAG Knowledge Conflict

#ai #llm #rag #agents
Comments
9 min read
Cursor Composer 2.5: Targeted Textual Feedback RL
pueding profile

Cursor Composer 2.5: Targeted Textual Feedback RL

#ai #llm #machinelearning
Comments
8 min read
Boiling the Frog Paper: Multi-Turn Norm Erosion vs Single-Prompt Agent Safety
pueding profile

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

#ai #agents #llm #security
Comments
8 min read
OpenSCAD Pantheon Benchmark: Human-In-The-Loop vs Autonomous Coding Agents
pueding profile

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

#ai #agents #productivity #llm
Comments
8 min read
Camouflage Injection Paper: Camouflage Detection Gap
pueding profile

Camouflage Injection Paper: Camouflage Detection Gap

#ai #agents #security #llm
Comments
7 min read
MCP SEP-2468: RFC 9207 Iss Parameter for OAuth Mix-Up Defense
pueding profile

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

#ai #agents #mcp #security
1
Comments
8 min read
Is Grep All You Need? Grep vs Vector Retrieval for Agentic Search
pueding profile

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

#agents #llm #rag #ai
2
Comments
7 min read
loading...