BestHub
Sign in
Tagged articles

LLM

2583 articles · Page 1 of 26
Java Architecture Diary
Java Architecture Diary
Aug 21, 2026 · Artificial Intelligence

LangChain4j 1.19 Switches to Stateless Streamable HTTP and Adds Hybrid Milvus Search

LangChain4j 1.19 drops SSE support in favor of a stateless Streamable HTTP protocol, introduces a Milvus‑v2 module that combines dense vector similarity with BM25 keyword matching for hybrid retrieval, and bundles dozens of bug fixes and new integrations across agents, HTTP clients, vector stores, and document parsers.

Hybrid SearchJavaLLM
0 likes · 9 min read
LangChain4j 1.19 Switches to Stateless Streamable HTTP and Adds Hybrid Milvus Search
AI Engineer Programming
AI Engineer Programming
Aug 21, 2026 · Artificial Intelligence

Essential Concepts and Terminology for Deploying Large Language Models Locally

This article walks through the core concepts needed before deploying a large language model on‑premises, covering weight precision, quantization methods, model packaging formats, inference engines, GPU memory considerations, KV‑cache sizing, sampling strategies, optional extensions such as LoRA and RAG, and a step‑by‑step decision workflow to match hardware, model, and deployment goals.

KV cacheLLMdeployment
0 likes · 21 min read
Essential Concepts and Terminology for Deploying Large Language Models Locally
Architect
Architect
Aug 20, 2026 · Industry Insights

What Real Problem Does Ontology Solve in Enterprise Knowledge Bases?

The article examines why ontology is essential for enterprise knowledge bases, showing how it resolves ambiguities that RAG, knowledge graphs, and agents cannot handle alone, and outlines a four‑layer architecture that ensures stable IDs, relationship semantics, fact lifecycle, and safe action execution.

Knowledge GraphLLMOntology
0 likes · 18 min read
What Real Problem Does Ontology Solve in Enterprise Knowledge Bases?
AntTech
AntTech
Aug 20, 2026 · Artificial Intelligence

Ling-3.0-flash: Open-Source LLM Designed for Real-World Deployment

Ling-3.0-flash is a newly open‑sourced 124B‑parameter MoE model that offers multiple quantized versions, API, single‑machine private deployment, and high‑performance GPU inference exceeding 1100 tokens/s, with detailed benchmarks, optimization techniques, and real‑world use‑case analyses for agents, coding, and sensitive data processing.

LLMLing-3.0-flashMoE
0 likes · 15 min read
Ling-3.0-flash: Open-Source LLM Designed for Real-World Deployment
Top Architecture Tech Stack
Top Architecture Tech Stack
Aug 20, 2026 · Artificial Intelligence

2026 Guide to the Leading AI API Gateways and How to Use Them

This article compares four popular open‑source AI API gateway projects—One API, New API, Sub2API, and LiteLLM—detailing their stars, licenses, tech stacks, core strengths, ideal scenarios, shortfalls, and provides step‑by‑step deployment and usage instructions with security and compliance tips.

AI API gatewayLLMLiteLLM
0 likes · 14 min read
2026 Guide to the Leading AI API Gateways and How to Use Them
Meituan Technology Team
Meituan Technology Team
Aug 20, 2026 · Artificial Intelligence

How Meituan Search 3.0 Leverages LLM Semantic Representations to Boost Ranking

The article details Meituan Search 3.0’s three‑phase journey—validating LLM‑based semantic vectors, rebuilding a systematic representation pipeline with contrastive learning and LoRA, and transferring the model to downstream item ranking—showing how 64‑dimensional cosine similarity features and multi‑scale embeddings consistently improve click, order and NDCG metrics across service‑retail search scenarios.

LLMLoRAcontrastive learning
0 likes · 44 min read
How Meituan Search 3.0 Leverages LLM Semantic Representations to Boost Ranking
AndroidPub
AndroidPub
Aug 20, 2026 · Artificial Intelligence

How to Stop Large‑Model Coding Agents from Forgetting in Multi‑Turn Dialogues

The article explains why a coding agent may appear to forget earlier decisions, introduces a three‑layer memory system (interaction history, request projection, logical execution chain), and details token‑budget constraints, prompt‑caching trade‑offs, and a suite of context‑compression strategies to keep agents reliable across long conversations.

LLMPrompt Cachingagent memory
0 likes · 16 min read
How to Stop Large‑Model Coding Agents from Forgetting in Multi‑Turn Dialogues
Tencent Cloud Middleware
Tencent Cloud Middleware
Aug 19, 2026 · Operations

How AI Gateway Makes Large-Model Calls Visible, Traceable, and Auditable

Enterprises deploying large-model APIs often struggle to see token usage, latency, and errors; the AI Gateway embeds metrics, structured logs, and distributed tracing at the gateway layer, providing token-level insights, request-level latency breakdowns, and full-chain auditability without code changes, as demonstrated in a real-world incident.

AI GatewayLLMLogging
0 likes · 17 min read
How AI Gateway Makes Large-Model Calls Visible, Traceable, and Auditable
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Aug 19, 2026 · Artificial Intelligence

Can LLMs Uncover Real Economic Links to Boost Cross‑Stock Prediction?

The paper proposes a two‑stage Retrieve‑then‑Reason framework that first builds a sparse candidate graph from 10‑K text embeddings and then uses a large language model to filter edges for true economic relationships, resulting in a higher‑Sharpe, lower‑drawdown cross‑stock trading signal on S&P 500 constituents.

LLMcross‑stock predictionfinancial networks
0 likes · 17 min read
Can LLMs Uncover Real Economic Links to Boost Cross‑Stock Prediction?
AndroidPub
AndroidPub
Aug 19, 2026 · Artificial Intelligence

How Long Does a Million LLM Tokens Last and How to Cut the Cost?

This article breaks down LLM token billing by explaining what tokens are, how requests are charged, why a single query can consume thousands of tokens, and offers concrete strategies to estimate usage, monitor costs, and reduce expenses across different scenarios.

AI programmingLLMPrompt Cache
0 likes · 20 min read
How Long Does a Million LLM Tokens Last and How to Cut the Cost?
Network Intelligence Research Center (NIRC)
Network Intelligence Research Center (NIRC)
Aug 19, 2026 · Artificial Intelligence

DeepSeek Harness: An Open‑Source, Plugin‑First Agent Runtime Explained

DeepSeek Harness, released on August 13 under the MIT license, is an open‑source, plugin‑centric agent runtime that offers four operation modes, builds on the Cordis/Koshi framework, provides full model‑agnostic support, and includes detailed logging for reproducible AI workflows, while noting current limitations.

AI AgentsAgent RuntimeDeepSeek Harness
0 likes · 5 min read
DeepSeek Harness: An Open‑Source, Plugin‑First Agent Runtime Explained
AI Engineering
AI Engineering
Aug 18, 2026 · Artificial Intelligence

How macOS Harness Lets an LLM Write Code and Control Your Entire Mac

macOS Harness is an open‑source project that gives a persistent Python process to a large language model, exposing six primitive actions so the model can see the screen, type, click, read accessibility trees, run AppleScript, and write custom Python logic to automate virtually any macOS task.

AppleScriptLLMPython
0 likes · 3 min read
How macOS Harness Lets an LLM Write Code and Control Your Entire Mac
SpringMeng
SpringMeng
Aug 18, 2026 · Operations

CFO’s No‑Code AI App Triggers a Month’s Server Bill in One Day

A CFO built a SaaS product in two days using Claude Code, but a missing database field caused the task queue’s automatic retries to re‑execute 21 LLM calls, turning a single day’s AI usage into a cost that exceeded the entire month’s server expenses.

AICloud InfrastructureDatabase Migration
0 likes · 11 min read
CFO’s No‑Code AI App Triggers a Month’s Server Bill in One Day
Linyb Geek Road
Linyb Geek Road
Aug 16, 2026 · Artificial Intelligence

Complete Spring AI Stack: Mapping the 2026 Java AI Ecosystem

The article presents a layered roadmap of the 2026 Java AI ecosystem, compares major AI frameworks, LLMs, embedding models, vector databases, and agent toolchains, and offers three concrete stack configurations with cost estimates and practical configuration snippets for architects and technical leaders.

AI StackAgentJava
0 likes · 13 min read
Complete Spring AI Stack: Mapping the 2026 Java AI Ecosystem
Linyb Geek Road
Linyb Geek Road
Aug 16, 2026 · Artificial Intelligence

2026 AI Agent Tech Stack: How Agents Think, Act, and Remember

This article presents a comprehensive six‑layer AI Agent architecture, explains the underlying principles of reasoning, tool use, memory, and planning, compares ReAct, Function Calling, and MCP, walks through a real‑world request flow, and offers practical technology‑selection guidance.

AI AgentsFunction CallingLLM
0 likes · 20 min read
2026 AI Agent Tech Stack: How Agents Think, Act, and Remember
AI Large-Model Wave and Transformation Guide
AI Large-Model Wave and Transformation Guide
Aug 15, 2026 · Artificial Intelligence

Why Ontology Has Become the Standard Context for Enterprise AI Agents

The article analyzes how AI agents struggle with hallucinations and ambiguous table names, explains why simple RAG falls short, and shows how 2026 industry leaders like Databricks, Microsoft, ByteDance, and Alibaba use ontology to provide precise, controllable business context, dramatically improving query accuracy.

Knowledge GraphLLMOntology
0 likes · 8 min read
Why Ontology Has Become the Standard Context for Enterprise AI Agents
DeepHub IMBA
DeepHub IMBA
Aug 15, 2026 · Artificial Intelligence

Why Most AI Agents Are Really Workflows, Not Fully Autonomous Systems

The article explains that most so‑called Agentic AI systems are built around a fixed control‑flow loop where an LLM acts as a planner, making them essentially workflows; it then details the reliability, debugging, and cost challenges that prevent true autonomy in production.

DebuggingLLMTool Calling
0 likes · 15 min read
Why Most AI Agents Are Really Workflows, Not Fully Autonomous Systems
DataFunTalk
DataFunTalk
Aug 14, 2026 · Artificial Intelligence

Deep Dive into Agent Harness: Dissecting the Architecture Behind AI Agents

The article explains that an Agent Harness— the full software infrastructure surrounding an LLM— is essential for production‑grade AI agents, detailing its definition, three engineering layers, twelve concrete components, execution loops, framework implementations, and key design decisions that separate harness failures from model shortcomings.

AI AgentsAgent HarnessLLM
0 likes · 20 min read
Deep Dive into Agent Harness: Dissecting the Architecture Behind AI Agents
AI Open-Source Efficiency Guide
AI Open-Source Efficiency Guide
Aug 14, 2026 · Artificial Intelligence

DeepSeek Harness: An Open‑Source Agent Runtime Built on a Full‑Plugin Architecture

DeepSeek Harness (dsh) is an open‑source agent framework that implements a complete plugin architecture, eliminating a privileged core, providing event‑sourced session logs, and allowing all capabilities to be swapped via configuration, positioning it as the new benchmark for open‑source agent runtimes.

AgentLLMPlugin
0 likes · 19 min read
DeepSeek Harness: An Open‑Source Agent Runtime Built on a Full‑Plugin Architecture
Machine Heart
Machine Heart
Aug 14, 2026 · Artificial Intelligence

Agent Memory Leaderboard Launch: Who Will Lead the Next‑Generation Memory Paradigm Revolution?

The first Agent Memory Leaderboard (AML) debuted on August 12, 2026, crowning MemoraX with a 58.0 score and InvMem as the open‑source champion, while its three‑fold isolation design, multi‑source dataset integration, and rigorous governance set a new, quantifiable standard for long‑term memory in agents, sparking intense community discussion and highlighting emerging trends toward active memory governance, engineering‑level isolation, and full‑chain evaluation.

AMLLLMagent memory
0 likes · 12 min read
Agent Memory Leaderboard Launch: Who Will Lead the Next‑Generation Memory Paradigm Revolution?
AI Step-by-Step
AI Step-by-Step
Aug 13, 2026 · Artificial Intelligence

6 Combo Techniques to Make Codex and Claude Code Truly Boost Efficiency

The article presents six concrete, step‑by‑step combos that let developers produce high‑quality code with Codex and Claude Code while enabling non‑technical teammates to save time and deliver verifiable results, covering new feature pipelines, automated reviews, large refactors, nightly automation, urgent bug fixes, and project hand‑over.

Claude CodeCodexLLM
0 likes · 6 min read
6 Combo Techniques to Make Codex and Claude Code Truly Boost Efficiency
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Aug 13, 2026 · Artificial Intelligence

Why RL Matters: From Reinforcement Learning to (Soft) Distillation

The article argues that reinforcement learning is crucial in post‑training because it refines and localizes chain‑of‑thought patterns learned during supervised fine‑tuning, improves model controllability, and can be complemented or substituted by distillation—especially soft distillation—to transfer high‑quality patterns from stronger teachers to weaker models.

Chain-of-ThoughtLLMReinforcement Learning
0 likes · 12 min read
Why RL Matters: From Reinforcement Learning to (Soft) Distillation
Yunqi AI+
Yunqi AI+
Aug 13, 2026 · Artificial Intelligence

Building an AI‑Native Service: A Minimal Viable Semantic Service Walkthrough

This article details how to turn ontology‑based semantic assets into a runnable Semantic Service that answers risk queries and suggests actions, using a three‑layer architecture of deterministic code, a versioned knowledge base, and LLM‑driven reasoning, illustrated with a customer health‑score example.

AILLMOntology
0 likes · 21 min read
Building an AI‑Native Service: A Minimal Viable Semantic Service Walkthrough
AI Open-Source Efficiency Guide
AI Open-Source Efficiency Guide
Aug 13, 2026 · Artificial Intelligence

triproxy: Transparent LLM Gateway for Using Any Model with OpenAI SDK, Codex, Claude Code, and Chat Clients

triproxy is a lightweight Go‑based HTTP gateway that translates between OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages protocols, supporting full request/response bodies, SSE streaming, and encrypted reasoning, enabling any client—OpenAI SDK, Codex CLI, Claude Code—to access any LLM model without modification.

API proxyAnthropicGo
0 likes · 19 min read
triproxy: Transparent LLM Gateway for Using Any Model with OpenAI SDK, Codex, Claude Code, and Chat Clients
PaperAgent
PaperAgent
Aug 13, 2026 · Artificial Intelligence

First Community Benchmarks of DeepSeek V4 Pro, Qwen 3.8 Max, and Grok 4.6

The community quickly tested three newly released LLMs—DeepSeek V4 Pro, Qwen 3.8 Max, and Grok 4.6—across 3D scene generation, Flappy game creation, and airplane‑animation tasks, comparing quality, speed, and cost to reveal each model’s strengths and trade‑offs.

AIDeepSeekGrok
0 likes · 5 min read
First Community Benchmarks of DeepSeek V4 Pro, Qwen 3.8 Max, and Grok 4.6
Machine Heart
Machine Heart
Aug 12, 2026 · Information Security

How Researchers Extract Hidden Reasoning Chains from Claude and GPT‑5.6

A new security paper demonstrates that design flaws in Claude, GPT‑5.6 and other leading LLM APIs allow attackers to steal encrypted reasoning blocks, replay them in weaker compatible models, and reconstruct most of the hidden thought process, exposing privacy and safety risks.

ClaudeGPT-5.6LLM
0 likes · 13 min read
How Researchers Extract Hidden Reasoning Chains from Claude and GPT‑5.6
Architecture Digest
Architecture Digest
Aug 11, 2026 · Backend Development

Run Your First Embabel Java Agent in 30 Minutes: A Hands‑On Guide

This article walks you through setting up the environment, creating a Spring Boot project, defining strong‑typed domain models, implementing @Action methods, declaring goals, and running an interactive shell so you can build and execute a fully functional Embabel Java Agent that automatically generates a research brief.

AIEmbabelJava
0 likes · 9 min read
Run Your First Embabel Java Agent in 30 Minutes: A Hands‑On Guide
21CTO
21CTO
Aug 11, 2026 · Artificial Intelligence

Meta’s Muse Glimmer Open‑Source Release Revives the Open‑Weight Llama Competition

Meta has unveiled Muse Glimmer, a 30‑billion‑parameter open‑source LLM under Apache 2.0, positioned for agent workloads and benchmarked against Google’s Gemma 4 and Alibaba’s Qwen, while highlighting hardware requirements, performance limits, and the broader strategic implications for U.S. AI policy.

LLMMetaMuse Glimmer
0 likes · 10 min read
Meta’s Muse Glimmer Open‑Source Release Revives the Open‑Weight Llama Competition
Architect
Architect
Aug 10, 2026 · Artificial Intelligence

Anthropic Deep Dive: Context Engineering Lessons from Real‑World R&D

The article analyzes Anthropic’s “Effective context engineering for AI agents,” showing how larger context windows can degrade, categorizing information by stability, designing prompts in the Goldilocks zone, structuring tool contracts, and applying runtime information scheduling, compression, structured notes, and sub‑agents to keep AI agents reliable in complex development workflows.

AI AgentsAnthropicContext Engineering
0 likes · 19 min read
Anthropic Deep Dive: Context Engineering Lessons from Real‑World R&D
DataFunSummit
DataFunSummit
Aug 9, 2026 · Artificial Intelligence

From Flawed RAG to Production‑Ready: A Deep Dive into Scaling Retrieval‑Augmented Generation

The article analyses why early RAG deployments suffer from low recall, hallucinations and cost overruns, breaks down eight concrete pain points—from PDF parsing pitfalls to the lost‑in‑the‑middle effect—then presents a systematic diagnosis framework, proven best‑practice roadmap, advanced GraphRAG and Agentic RAG approaches, and practical engineering trade‑offs for enterprise rollout.

Agentic RAGGraphRAGHybrid Search
0 likes · 19 min read
From Flawed RAG to Production‑Ready: A Deep Dive into Scaling Retrieval‑Augmented Generation
Machine Heart
Machine Heart
Aug 9, 2026 · Artificial Intelligence

Why Continual Learning Won’t Take Ten Years—Five Hot Paths and the Fight Against Catastrophic Forgetting

The article surveys five emerging approaches to LLM continual learning—external agent memory, context engineering, post‑training, pre‑training, and self‑modifying models—explaining how each tackles the core obstacle of catastrophic forgetting, citing benchmarks such as TRACE, ACE, and SDFT, and reflecting on Karpathy’s ten‑year timeline.

Context EngineeringLLMagent memory
0 likes · 17 min read
Why Continual Learning Won’t Take Ten Years—Five Hot Paths and the Fight Against Catastrophic Forgetting
PaperAgent
PaperAgent
Aug 9, 2026 · Artificial Intelligence

Tsinghua Unveils Two Breakthrough Papers on LLM Agent Skills

The article reviews Tsinghua University's two new papers—GSE, which introduces a global skill‑relation graph, clustering, and replay verification to make agent skills continuously improve, and SkillSentry, which uses ability contracts and adaptive honey‑world testing to ensure skill safety—detailing their methods, experimental results, and practical implications.

AI safetyAgentGSE
0 likes · 8 min read
Tsinghua Unveils Two Breakthrough Papers on LLM Agent Skills
webdream
webdream
Aug 8, 2026 · Artificial Intelligence

Engineering a Multi‑Agent System: Architecture, Stability, and Observability Lessons

This article shares practical engineering insights from building a multi‑agent LLM system, covering why multiple agents are needed, the 3‑agent + 1 skill architecture, LangGraph orchestration, tool integration via MCP, stability mechanisms, layered memory, traceability, streaming UI, and common pitfalls.

LLMLangGraphMCP
0 likes · 12 min read
Engineering a Multi‑Agent System: Architecture, Stability, and Observability Lessons
21CTO
21CTO
Aug 8, 2026 · R&D Management

Rust Team Issues AI Coding Policy: Allow LLMs but Ban “Pseudo‑Effort Signals”

The Rust project introduced a detailed LLM usage policy that permits AI for analysis while forbidding AI‑generated code creation, outlines five mandatory rules for AI‑derived contributions, sets safety red lines for security‑critical changes, and explains the community’s reaction and broader governance implications.

AIEngineering ManagementLLM
0 likes · 6 min read
Rust Team Issues AI Coding Policy: Allow LLMs but Ban “Pseudo‑Effort Signals”
Data Party THU
Data Party THU
Aug 8, 2026 · Artificial Intelligence

Memory-Efficient Algorithms for Large Language Model Inference

The article reviews Coleman Hooper's 2026 Berkeley PhD thesis, which shows that LLM inference is increasingly limited by memory bandwidth and capacity, and proposes a four‑pronged approach—weight quantization, KV‑cache quantization, selective context loading, and multipole attention—to dramatically improve memory efficiency and throughput.

KV cacheLLMMemory Efficiency
0 likes · 12 min read
Memory-Efficient Algorithms for Large Language Model Inference
Mingyi World Elasticsearch
Mingyi World Elasticsearch
Aug 7, 2026 · Backend Development

How to Turn Raw Text Data into an Interactive Searchable Dashboard in One Minute for Pre‑sales POCs

The article describes a fully automated pipeline that lets pre‑sales engineers upload a raw CSV/JSON sample, automatically infer mappings, mask sensitive fields, ingest data into Easysearch, generate a searchable, chart‑driven dashboard, and clean up the session with a single click, eliminating the tedious manual preparation that normally dominates POC demos.

DashboardData IngestionEasysearch
0 likes · 14 min read
How to Turn Raw Text Data into an Interactive Searchable Dashboard in One Minute for Pre‑sales POCs
Wu Shixiong's Large Model Academy
Wu Shixiong's Large Model Academy
Aug 7, 2026 · Artificial Intelligence

Why a Single -100 Line Determines Who the Multi‑Round SFT Learns to Speak

The article explains how using -100 as an ignored label in PyTorch cross‑entropy loss silently masks non‑assistant tokens, how to locate assistant spans via prefix‑difference, the trade‑offs between supervising only the final reply versus all assistant turns, and the essential pre‑training checks to avoid hidden masking errors in multi‑round SFT.

LLMPyTorchSFT
0 likes · 14 min read
Why a Single -100 Line Determines Who the Multi‑Round SFT Learns to Speak
AI Engineer Programming
AI Engineer Programming
Aug 7, 2026 · Artificial Intelligence

How to Ensure Reliable Structured Outputs in LLM Agents

The article explains why format constraints alone cannot guarantee correct content in LLM agents, compares JSON Mode, Structured Outputs, and Tool Calling, and provides a step‑by‑step engineering guide—including model‑specific quirks, schema validation, retry loops, and layered fallback strategies—to achieve robust structured results.

AgentJSON ModeLLM
0 likes · 13 min read
How to Ensure Reliable Structured Outputs in LLM Agents
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Aug 6, 2026 · Artificial Intelligence

Training‑Free Beats 14B Model: Sonar‑TS Fills Scale Gap in Time‑Series QA

The paper introduces Sonar‑TS, a training‑free neural‑symbolic system that tackles the newly defined NLQ4TSDB problem—natural‑language queries over database‑scale time‑series—by converting shape intents into searchable symbols and verifying candidates with executable code, achieving up to 3.8× higher scores than the strongest Text‑to‑SQL baseline while highlighting remaining challenges in shape understanding.

LLMSQLSonar-TS
0 likes · 10 min read
Training‑Free Beats 14B Model: Sonar‑TS Fills Scale Gap in Time‑Series QA
Architect
Architect
Aug 6, 2026 · Artificial Intelligence

Deconstructing TencentDB Agent Memory: How to Keep Agents Accurate Without Being Misled by Errors?

The article analyzes TencentDB Agent Memory’s design, breaking down its three‑stage write‑read‑governance pipeline, four‑level L0‑L3 hierarchy, object types, recall strategies, conflict handling, sharing rules, long‑task traceability, and practical testing guidelines to ensure past information helps future decisions while preserving provenance and error correction.

GovernanceLLMLong-Term Memory
0 likes · 22 min read
Deconstructing TencentDB Agent Memory: How to Keep Agents Accurate Without Being Misled by Errors?
Data Party THU
Data Party THU
Aug 6, 2026 · Artificial Intelligence

What Is an AI Agent Harness and Why It’s Essential Beyond the Model

The article explains how an AI Agent Harness transforms a powerful language model into a reliable, controllable agent by adding tool access, memory, permissions, guardrails, observability, and recovery mechanisms, and outlines its core components, workflow, and a practical customer‑service example.

AIAgent HarnessGuardrails
0 likes · 12 min read
What Is an AI Agent Harness and Why It’s Essential Beyond the Model
TonyBai
TonyBai
Aug 6, 2026 · R&D Management

Rust Says AI Can Review Code but Not Write It: Inside the New LLM Policy

The Rust core teams have published an LLM usage policy that permits AI to assist with reviewing, analyzing, and suggesting code but forbids AI‑generated code creation, outlining strict disclosure rules, higher quality thresholds, and the impact on reviewers, contributors, and issue reporters while comparing approaches taken by Go, Zig, and the Linux kernel.

AILLMRust
0 likes · 17 min read
Rust Says AI Can Review Code but Not Write It: Inside the New LLM Policy
Sohu Tech Products
Sohu Tech Products
Aug 5, 2026 · Artificial Intelligence

MemoHarness: The Next Evolution of Agents Happens Outside the Model

MemoHarness proposes an Agent Harness that keeps the language model frozen while learning to adjust external control layers across six editable dimensions, showing measurable gains on terminal, code‑generation, and finance benchmarks but acknowledging limited scale, selective transfer, and cost dependencies.

AI AgentsAgent HarnessExperience Library
0 likes · 16 min read
MemoHarness: The Next Evolution of Agents Happens Outside the Model
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Aug 5, 2026 · Artificial Intelligence

Large-Model Memory Panorama: The 3‑D Taxonomy Unveiled by Tsinghua’s Tang Jie Team

This review maps the evolving landscape of large‑model memory, classifying mechanisms along three axes—representation, update dynamics, and persistence—while contrasting implicit and explicit approaches, discussing hybrid designs, and outlining challenges such as write strategies, stability, capacity, and evaluation metrics.

Artificial IntelligenceExplicit MemoryHybrid Models
0 likes · 12 min read
Large-Model Memory Panorama: The 3‑D Taxonomy Unveiled by Tsinghua’s Tang Jie Team
Tencent Technical Engineering
Tencent Technical Engineering
Aug 5, 2026 · Artificial Intelligence

Advanced AI Infra: Making Large Language Models Produce Deterministic Outputs

This article analyzes why LLM inference often yields nondeterministic results, explains how floating‑point addition order, GEMM tiling, Split‑K, RMSNorm, FlashAttention, and NCCL all contribute to batch variance, and details the engineering steps vLLM takes to enforce batch‑invariant execution across GPUs.

Batch InvarianceDeterminismFlashAttention
0 likes · 52 min read
Advanced AI Infra: Making Large Language Models Produce Deterministic Outputs
21CTO
21CTO
Aug 5, 2026 · Industry Insights

Don’t Be Fooled by AI: Why Only 1% of People Truly Win with ChatGPT

The article argues that while ChatGPT and other LLMs appear to democratize expertise, they actually widen the gap between ordinary workers and top specialists, illustrating the point with a programmer’s failure, a fashion designer’s success, and the concept of private‑domain knowledge as the real moat.

AILLMPrompt Engineering
0 likes · 9 min read
Don’t Be Fooled by AI: Why Only 1% of People Truly Win with ChatGPT
FunTester
FunTester
Aug 5, 2026 · Artificial Intelligence

Why AI Alone Won’t Boost Quality: From Speed to Risk Prediction in QA

The article analyzes how AI testing is moving from experimental use to strategic QA governance, emphasizing the need for robust validation processes, multi‑layer verification, risk‑prediction metrics, and collaborative GenAI agents to turn speed gains into genuine quality improvements.

AI testingAutomation GovernanceLLM
0 likes · 10 min read
Why AI Alone Won’t Boost Quality: From Speed to Risk Prediction in QA
21CTO
21CTO
Aug 4, 2026 · Artificial Intelligence

JetBrains Open‑Sources KotlinLLM: LLM‑Driven Smart Macros for Compiled Kotlin

JetBrains has open‑sourced the experimental KotlinLLM IntelliJ IDEA plugin, which introduces LLM‑driven smart macros for Kotlin/JVM projects, addressing runtime delegation latency, external agent workflow complexity, and language integration challenges by providing explicit LLM awareness, source‑level persistence, and zero runtime overhead.

IntelliJ IDEAKotlinLLM
0 likes · 4 min read
JetBrains Open‑Sources KotlinLLM: LLM‑Driven Smart Macros for Compiled Kotlin
Xike
Xike
Aug 4, 2026 · Operations

How We Fixed the AI‑Powered xi‑ops Ops Platform’s Critical Pitfalls

This article walks through the security and reliability pitfalls encountered when integrating large language models into the xi‑ops open‑source operations platform—covering unsafe SQL generation, unauthorized SSH actions, knowledge‑base hallucinations, prompt‑engineered bypasses, and configuration sync issues—and explains the concrete engineering safeguards that were implemented to close each gap.

AI OpsLLMMCP
0 likes · 21 min read
How We Fixed the AI‑Powered xi‑ops Ops Platform’s Critical Pitfalls
DataFunSummit
DataFunSummit
Aug 4, 2026 · Artificial Intelligence

MemoHarness: How Agents Evolve Beyond Model Parameters

MemoHarness expands the notion of self‑evolving agents by keeping the language model frozen while continuously adapting the external control system—context assembly, tool interaction, generation settings, workflow orchestration, memory management, and output validation—demonstrating measurable gains on terminal, code‑generation, and finance tasks, yet highlighting limited scalability and transferability.

AI AgentsAgentExperience Learning
0 likes · 17 min read
MemoHarness: How Agents Evolve Beyond Model Parameters
Golang Shines
Golang Shines
Aug 4, 2026 · Information Security

Exploring AI-Assisted Penetration Testing and Vulnerability Discovery

The article analyzes the opportunities and challenges of integrating large language models into penetration testing workflows, presents the design of the AI‑Burp‑Copilot plugin, details its layered architecture, implementation specifics, and real‑world limitations such as LLM nondeterminism and coverage of business‑logic flaws.

AIBurp SuiteLLM
0 likes · 15 min read
Exploring AI-Assisted Penetration Testing and Vulnerability Discovery
PaperAgent
PaperAgent
Aug 4, 2026 · Artificial Intelligence

How Peking University’s Two Papers Redefine Agent Skill Evolution

Two recent Peking University papers, VeriSkill and SESA, demonstrate that treating agent skills as self‑evolving memory—updated from failures via responsibility attribution, lesson abstraction, and failure distillation—yields significant performance gains across verification and search tasks and transfers across models.

AgentLLMProgram Verification
0 likes · 9 min read
How Peking University’s Two Papers Redefine Agent Skill Evolution
JD Cloud Developers
JD Cloud Developers
Aug 4, 2026 · Artificial Intelligence

NaviAgent: Scalable Tool Orchestration for Oxygen Agents via Graph‑Driven Bilevel Planning

The paper introduces NaviAgent, a double‑layer architecture that separates LLM‑based planning from graph‑driven tool navigation, explicitly models API‑parameter dependencies, continuously updates the tool graph with execution feedback, and achieves up to 13.1 % higher task success rates on large‑scale API benchmarks.

AI AgentsDynamic PlanningGraph Modeling
0 likes · 16 min read
NaviAgent: Scalable Tool Orchestration for Oxygen Agents via Graph‑Driven Bilevel Planning
AI Engineer Programming
AI Engineer Programming
Aug 4, 2026 · Artificial Intelligence

Why Agents Call Unneeded Tools and How to Tackle It as a System‑Engineering Problem

The article defines tool hallucination in LLM agents, analyses training bias, context pollution, loop feedback and dialogue inertia as root causes, and proposes multi‑layer defenses—including visibility control, intent verification, runtime gating, architectural isolation, and feedback loops—framed as a system‑engineering challenge rather than mere prompt tweaking.

AgentLLMRuntime Guard
0 likes · 17 min read
Why Agents Call Unneeded Tools and How to Tackle It as a System‑Engineering Problem
Machine Heart
Machine Heart
Aug 3, 2026 · Artificial Intelligence

Does VLA Action Prediction Need an LLM? TurboVLA Achieves 32 Hz with 0.2 B Params on RTX 4090

TurboVLA, a real‑time vision‑language‑action model from Huazhong University of Science and Technology and Huawei, bypasses the large language model bottleneck by directly fusing visual and language features, achieving 32 Hz online action prediction on a single RTX 4090 with only 0.2 B parameters and 0.9 GB VRAM, while maintaining high success rates across LIBERO, RoboTwin 2.0, and real‑robot tasks.

LIBEROLLMRTX 4090
0 likes · 11 min read
Does VLA Action Prediction Need an LLM? TurboVLA Achieves 32 Hz with 0.2 B Params on RTX 4090
AI Large Model Application Practice
AI Large Model Application Practice
Aug 3, 2026 · Artificial Intelligence

Deep Dive into LLM Wiki Engineering: AI Coding, Obsidian Integration, and RAG Collaboration

This article explains how to build and maintain an LLM‑powered knowledge base (LLM Wiki) for AI coding agents, shows practical workflows using Obsidian and custom agents, and compares the governance‑focused Wiki approach with retrieval‑augmented generation, highlighting trade‑offs, metadata design, and integration patterns.

AI codingAgentLLM
0 likes · 16 min read
Deep Dive into LLM Wiki Engineering: AI Coding, Obsidian Integration, and RAG Collaboration
DeepHub IMBA
DeepHub IMBA
Aug 2, 2026 · Artificial Intelligence

Building a From‑Scratch LLM Training Framework: Full GRPO vs PPO vs DPO Comparison on GSM8K

The article presents a from‑scratch LLM training framework called grpo‑llm, implements GRPO with Trio rollout, FSDP and a C++ reward extension, and conducts a controlled experiment comparing GRPO, PPO and DPO on the GSM8K math‑reasoning benchmark, revealing why DPO outperforms the other two under sparse binary rewards.

DPOGRPOGSM8K
0 likes · 10 min read
Building a From‑Scratch LLM Training Framework: Full GRPO vs PPO vs DPO Comparison on GSM8K
BirdNest Tech Talk
BirdNest Tech Talk
Aug 2, 2026 · Artificial Intelligence

Which LLM Builds the Best Web Gomoku Game? A Comparative Test of the Latest Models

The author prompts six recent large language models to create a web‑based Gomoku game and compares the results across four dimensions—AI opponent, execution method, visual design, and engineering rigor—revealing that Opus 5 and gpt‑5.6‑sol deliver the most complete solutions while deepseek‑v4‑pro and glm‑5.2 excel at quick, single‑file prototypes, and MiniMax‑M3, despite its polished UI, fails at human‑vs‑AI play.

AI comparisonGomokuLLM
0 likes · 13 min read
Which LLM Builds the Best Web Gomoku Game? A Comparative Test of the Latest Models
AI Large-Model Wave and Transformation Guide
AI Large-Model Wave and Transformation Guide
Aug 2, 2026 · Artificial Intelligence

Case Study: Ontology Implementation Pitfalls in a Women’s Apparel Startup

The article critiques a women’s apparel startup’s ontology setup, showing how its reliance on static graphs, SQL queries, and a large language model yields a hard‑coded analysis pipeline rather than true multi‑hop reasoning, and explains why a proper reasoning engine is essential for scenario‑driven inference.

LLMMCPdata inference
0 likes · 6 min read
Case Study: Ontology Implementation Pitfalls in a Women’s Apparel Startup
AI Large-Model Wave and Transformation Guide
AI Large-Model Wave and Transformation Guide
Aug 2, 2026 · R&D Management

Federated Dual Ontology: Isolating and Coordinating Two Semantic Domains

The article explains how a federated architecture separates code‑architecture and purchasing constraints into independent domains, injects them into LLM context with per‑domain token budgets, and validates them without merging schemas, demonstrating the approach with concrete directory layouts, configuration code, and experimental results.

ConstraintManagementDomainConfigFederatedGraph
0 likes · 9 min read
Federated Dual Ontology: Isolating and Coordinating Two Semantic Domains
DeepHub IMBA
DeepHub IMBA
Aug 1, 2026 · Artificial Intelligence

Estimating the GPU Count Needed to Train a Large Language Model

The article presents a practical scaling‑law based method to estimate the total FLOPs, GPU throughput, and required number of GPUs for training a large language model, showing how to compute these values from model parameters, token count, and target training time, and discusses approximation limits and useful tools.

AICompute EstimationGPU
0 likes · 9 min read
Estimating the GPU Count Needed to Train a Large Language Model
Data Party THU
Data Party THU
Aug 1, 2026 · Artificial Intelligence

10 AI Agent Workflows to Save Teams Hours of Repetitive Work

This article presents ten practical AI agent workflow templates, each with a trigger, context, tools, decision rules, and human checkpoints, showing how to automate tasks like email triage, research briefs, form filling, meeting minutes, support routing, content repurposing, competitor monitoring, invoice reconciliation, CRM updates, and QA review.

AI AgentsLLMProductivity
0 likes · 13 min read
10 AI Agent Workflows to Save Teams Hours of Repetitive Work
PaperAgent
PaperAgent
Aug 1, 2026 · Artificial Intelligence

Why LLMs Remember Yet Forget: The Cost of Evolving User Intent

Microsoft Research reveals that large language models excel on static single‑turn tasks but dramatically lose accuracy when user intent evolves across multiple turns, especially during function switches; the study formalizes three intent transition types, proposes a backward‑generation framework, and shows modest gains from memory mechanisms while highlighting the need for active intent recaps.

LLMMemory MechanismMulti-turn Dialogue
0 likes · 12 min read
Why LLMs Remember Yet Forget: The Cost of Evolving User Intent
AI Open-Source Efficiency Guide
AI Open-Source Efficiency Guide
Aug 1, 2026 · Artificial Intelligence

Karpathy’s 10 LLM Coding Rules That Instantly Boost Claude and Codex

The Karpathy‑LLM‑Coding‑Rules repository offers ten executable, bilingual rules that constrain AI coding agents like Claude and Codex, providing clear validation criteria and anti‑pattern names to prevent over‑refactoring, hidden bugs, and unbounded dependencies, and can be dropped into a project with a single file copy.

AI AgentsClaudeCodex
0 likes · 10 min read
Karpathy’s 10 LLM Coding Rules That Instantly Boost Claude and Codex
Linyb Geek Road
Linyb Geek Road
Aug 1, 2026 · Artificial Intelligence

Practical Guide to Cutting LLM Token Costs

This article systematically explains how large‑language‑model token pricing works, identifies eight high‑consumption usage patterns, presents nine actionable optimization principles, and offers a tiered model‑selection framework so engineering teams can reduce token spend by up to 80% without sacrificing result quality.

Batch ProcessingLLMPrompt Engineering
0 likes · 22 min read
Practical Guide to Cutting LLM Token Costs
AI Engineering
AI Engineering
Jul 31, 2026 · Artificial Intelligence

Extract JSON from PDFs with Natural Language Using Unstract – No More Regex

Unstract is an open‑source platform that lets you describe desired fields in plain language and leverages LLMs to turn invoices, bank statements, KYC forms and other unstructured PDFs into clean JSON ready for database ingestion, eliminating the need for regex or custom templates.

JSON outputLLMPDF extraction
0 likes · 4 min read
Extract JSON from PDFs with Natural Language Using Unstract – No More Regex
AntData
AntData
Jul 31, 2026 · Artificial Intelligence

When Expert Experience Can Be Quantified: How Rubrics Become Data Assets for LLM Inference Training

The article analyzes how combining formal verification with expert‑derived Rubrics provides fine‑grained process supervision for large language models, presents the CRAFT data‑production pipeline, and shows experimental gains on math and medical benchmarks using Rubric‑driven RL, SFT, and alternating RL‑SFT training.

AI trainingEvaluationLLM
0 likes · 23 min read
When Expert Experience Can Be Quantified: How Rubrics Become Data Assets for LLM Inference Training
Java Tech Workshop
Java Tech Workshop
Jul 31, 2026 · Backend Development

Building a Pluggable LLM Gateway with Spring Boot

The article explains why enterprise applications need a unified large‑model gateway, outlines a layered architecture using Spring Boot 3.x, strategy pattern and interface‑driven design, and provides production‑grade features such as retry, circuit‑breaker, token accounting and easy addition of new model providers.

LLMOpenFeignResilience4j
0 likes · 19 min read
Building a Pluggable LLM Gateway with Spring Boot
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Jul 30, 2026 · Artificial Intelligence

From LLM Rollout to Agentic Rollout: Design Insights and Lessons for an Agentic RL Training Framework

The article analyzes the transition from single‑step LLM rollouts to multi‑step Agentic RL rollouts, compares coupled and decoupled architectures, details the roles of Controller, Runtime Manager, Gateway and LLM Server, and discusses token‑level consistency, trajectory reconstruction, and scalability strategies for a production‑grade training pipeline.

Agentic RLLLMRollout Architecture
0 likes · 25 min read
From LLM Rollout to Agentic Rollout: Design Insights and Lessons for an Agentic RL Training Framework
ThinkingAgent
ThinkingAgent
Jul 29, 2026 · Artificial Intelligence

How Tokenizers and Embeddings Encode Language – The Mechanics Behind LLMs

The article explains how different tokenization strategies (word, character, subword) affect token counts, model cost, context length, and multilingual fairness, and details the engineering trade‑offs of BPE, WordPiece, Unigram, SentencePiece, special tokens, and embedding matrices in large language models.

AILLMSubword
0 likes · 23 min read
How Tokenizers and Embeddings Encode Language – The Mechanics Behind LLMs
Linyb Geek Road
Linyb Geek Road
Jul 29, 2026 · Artificial Intelligence

Why Adding More Documents Can Degrade RAG Answers

The article explains that stuffing a RAG system with many overlapping or conflicting documents consumes tokens, slows responses, and introduces noise that prevents the model from correctly using the most relevant evidence, ultimately worsening answer quality.

Evidence RankingLLMPrompt Engineering
0 likes · 14 min read
Why Adding More Documents Can Degrade RAG Answers
DataFunTalk
DataFunTalk
Jul 28, 2026 · Artificial Intelligence

What Is an Agent Harness? A Deep Dive into AI Agent Architecture

The article explains that an Agent Harness is the full software infrastructure surrounding a large language model—handling orchestration loops, tool integration, memory, context management, error handling, and security—and shows how production‑grade harnesses, defined by Anthropic, OpenAI and LangChain, consist of twelve components, with detailed design trade‑offs and practical examples.

AI AgentsAgent HarnessLLM
0 likes · 21 min read
What Is an Agent Harness? A Deep Dive into AI Agent Architecture
PaperAgent
PaperAgent
Jul 28, 2026 · Artificial Intelligence

Inside Anthropic’s New Graph Engineering Methodology for Multi‑Agent Systems

Anthropic’s recent 12‑page playbook and 2‑hour workshop detail a Graph Engineering pipeline that replaces costly context‑window communication with a shared knowledge graph, covering why windows fail, a four‑stage Claude API workflow, extraction rules, entity resolution, graph assembly, multi‑hop querying, integration into five agent modes, cost analysis, scaling strategies, and guidance on when not to use a knowledge graph.

AnthropicClaude APIGraph Engineering
0 likes · 14 min read
Inside Anthropic’s New Graph Engineering Methodology for Multi‑Agent Systems
Ray's Galactic Tech
Ray's Galactic Tech
Jul 27, 2026 · Artificial Intelligence

From Zero to One: Building an AI Requirement Analysis Engine – Full Technical Walkthrough of the Skills Architecture

This article details how to engineer a production‑grade AI requirement‑analysis engine using a modular Skills framework, covering problem definition, architecture, compilation pipeline, conflict detection, impact analysis, scalability, multi‑tenant governance, and deployment best practices.

AIEngineeringKnowledge Retrieval
0 likes · 34 min read
From Zero to One: Building an AI Requirement Analysis Engine – Full Technical Walkthrough of the Skills Architecture
DataFunTalk
DataFunTalk
Jul 27, 2026 · Artificial Intelligence

MemoHarness: The Next Evolution of Agents Happens Outside the Model

MemoHarness introduces an Agent Harness that keeps the language model frozen while iteratively optimizing the surrounding control system across six dimensions, showing measurable gains on terminal automation, code generation, and financial analysis tasks, yet acknowledges limited experimental scale and selective transferability.

AI AgentsAgent HarnessEvaluation
0 likes · 16 min read
MemoHarness: The Next Evolution of Agents Happens Outside the Model
ThinkingAgent
ThinkingAgent
Jul 27, 2026 · Artificial Intelligence

The Awakening of Large Models: From Classic Language Modeling to Generative AI

This article traces the 56‑year evolution of language models—from ELIZA’s rule‑based scripts and N‑gram statistics to neural embeddings, RNNs, Transformers and the seven‑layer ChatGPT architecture—explaining why the simple next‑token probability definition has remained the core of generative AI, how autoregressive factorization drives training, generation and decoding, why hallucinations arise, and what engineering trade‑offs matter in production.

ChatGPTLLMLarge Language Models
0 likes · 26 min read
The Awakening of Large Models: From Classic Language Modeling to Generative AI
AI Engineer Programming
AI Engineer Programming
Jul 26, 2026 · Artificial Intelligence

Agent Development Lifecycle (ADLC): Vendor‑Neutral Guide to Build, Test, Deploy, Monitor, and Govern AI Agents

This note outlines a vendor‑agnostic Agent Development Lifecycle (ADLC) that extends traditional SDLC with five stages—Build, Test, Deploy, Monitor, and Govern—detailing layer‑wise tooling choices, evaluation strategies, deployment infrastructure, observability practices, and governance concerns for modern AI agents.

AI lifecycleAgentOpsGovernance
0 likes · 15 min read
Agent Development Lifecycle (ADLC): Vendor‑Neutral Guide to Build, Test, Deploy, Monitor, and Govern AI Agents