BestHub
Sign in

Artificial Intelligence

Showing 100 articles max
Latest Popular
Architects' Tech Alliance
Architects' Tech Alliance
Aug 26, 2026 · Artificial Intelligence

Inside Huawei’s Atlas 850E & 950 Supernodes: Key Technical Innovations

Huawei’s Atlas 850E wind‑cooled supernode delivers 14.27 PFLOPS, 768 GB HBM, 4 TB/s bandwidth and VCE phase‑change cooling for inference in standard data centers, while the Atlas 950 SuperPoD provides a flagship 1 EFLOPS FP8 training platform with 256 TB unified memory, 1.72 PB/s interconnect, sub‑3 µs RTT, full liquid cooling and scalability up to 8 192 NPU cards.

AI hardwareAtlas 850EAtlas 950
0 likes · 8 min read
Inside Huawei’s Atlas 850E & 950 Supernodes: Key Technical Innovations
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Aug 26, 2026 · Artificial Intelligence

Can AI Do Independent Research? ASI‑Bench Measures Scientific Autonomy

ASI‑Bench, developed by Tsinghua and leading institutions, is a benchmark that evaluates AI’s scientific autonomy by progressively reducing method guidance across four levels, revealing that current models lose up to half their scientific score without detailed instructions, highlighting the gap to true independent research.

AI autonomyASI-BenchBenchmark
0 likes · 14 min read
Can AI Do Independent Research? ASI‑Bench Measures Scientific Autonomy
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Aug 26, 2026 · Artificial Intelligence

From Experience to Ability: How Agentic Skills Form, Internalize, and Self‑Evolve

In this MLNLP Academic Talk, Tsinghua PhD candidate Wu Jinyang presents his research on Agentic Skill formation, internalization, and continual self‑evolution, detailing three projects—ThoughtICR, TemplateRL, and SEED—that connect contextual reasoning, reinforcement learning, and autonomous skill growth.

Agentic SkillReinforcement LearningSEED
0 likes · 4 min read
From Experience to Ability: How Agentic Skills Form, Internalize, and Self‑Evolve
Machine Heart
Machine Heart
Aug 26, 2026 · Artificial Intelligence

Specula Finds 382 Deep Bugs in 67 Projects, Reducing Formal Verification to Hours

Specula, an AI‑driven tool, automatically reads code, documentation, tests and history to generate TLA+ models, runs model checking, and reproduces counterexamples as tests, uncovering 382 deep concurrency bugs across 67 open‑source systems and shrinking verification time from months to a few hours.

AI coding agentsSpeculaTLA+
0 likes · 11 min read
Specula Finds 382 Deep Bugs in 67 Projects, Reducing Formal Verification to Hours
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Aug 26, 2026 · Artificial Intelligence

How AlphaMemo Enables Self‑Evolving Alpha Factor Mining with Structured Search Memory

AlphaMemo introduces a structured‑search‑process memory for LLM agents that records effective and failed edit patterns in specific parent‑factor contexts, uses AST‑difference extraction, confidence‑gated residual learning, and asymmetric veto to tackle combinatorial search, noisy feedback, redundancy, and over‑fitting, achieving superior out‑of‑sample performance and discovery efficiency on CSI 500 and S&P 500 benchmarks.

AST diffAlpha factor miningAlphaMemo
0 likes · 18 min read
How AlphaMemo Enables Self‑Evolving Alpha Factor Mining with Structured Search Memory
DataFunSummit
DataFunSummit
Aug 26, 2026 · Artificial Intelligence

How Palantir’s New Skills Turn Enterprise AI Into Reusable Analysis Methods

Palantir’s August 18 update to AIP Analyst introduces Skills and Analysis Lookup, adding a method‑memory layer that lets AI agents reuse analysis procedures rather than just past content, while still supporting semantic search and Ontology‑driven data operations.

AI agentsAIP AnalystAnalysis Lookup
0 likes · 9 min read
How Palantir’s New Skills Turn Enterprise AI Into Reusable Analysis Methods
Qborfy AI
Qborfy AI
Aug 26, 2026 · Artificial Intelligence

How Graph Engineering Tames Uncontrolled AI Agents and Solves Prompt Fatigue

The article explains that "prompt fatigue" stems from cramming multiple roles and tasks into a single LLM prompt, which causes attention competition and context pollution, and shows how Graph engineering restructures agents into specialized state nodes to isolate context, specialize roles, and enforce controllable workflows, backed by Anthropic’s 90% quality gain at a 15‑fold token cost.

AI Agent DesignAnthropicContext Isolation
0 likes · 14 min read
How Graph Engineering Tames Uncontrolled AI Agents and Solves Prompt Fatigue
ThinkingAgent
ThinkingAgent
Aug 26, 2026 · Artificial Intelligence

Trustworthy AI: Security, Explainability, Governance, and the 2026 Technical Ceiling

The article examines how increasingly capable large language models transition from merely avoiding harmful output to preventing harmful actions, outlining threat modeling, prompt injection, data‑pipeline attacks, architectural controls, interpretability, governance frameworks, and the unresolved technical limits that persist through 2026.

AI safetyAgent securityGovernance
0 likes · 38 min read
Trustworthy AI: Security, Explainability, Governance, and the 2026 Technical Ceiling
Machine Heart
Machine Heart
Aug 26, 2026 · Artificial Intelligence

How Inspirational Learning Turns LLM Knowledge from External to Endogenous

The article introduces Inspirational Learning (Isaac), a framework that embeds cross‑domain experience directly into LLM inference via Prompt Injection (DIN) and Network‑Layer Injection (CoDA), and shows substantial gains on HumanEval, StrategyQA, ScienceQA, and SciCode benchmarks, especially for weaker models.

Cross-Domain RetrievalInspirational LearningLLM Benchmarks
0 likes · 10 min read
How Inspirational Learning Turns LLM Knowledge from External to Endogenous
Machine Heart
Machine Heart
Aug 26, 2026 · Artificial Intelligence

Why Shopify’s CEO Is Considering Disabling Claude Code Over AGENTS.md Incompatibility

Shopify CEO Tobi Lütke worries that Claude Code reads a different configuration file (CLAUDE.md) than other AI coding agents (AGENTS.md), which can cause inconsistent project rules in the monorepo, and explores community‑proposed fixes such as symlinks and file references while highlighting the maintenance burden for large codebases.

AGENTS.mdAI coding agentsClaude Code
0 likes · 6 min read
Why Shopify’s CEO Is Considering Disabling Claude Code Over AGENTS.md Incompatibility
Data Party THU
Data Party THU
Aug 26, 2026 · Artificial Intelligence

How ‘Good’ Adversarial Attacks Can Safeguard Visual Content Throughout Its Lifecycle

This survey examines proactive protection methods—ranging from privacy filters and non‑learnable samples to generative safeguards, adversarial captchas, and traceability mechanisms—that embed adversarial perturbations before visual content is shared, trained, generated, accessed, or disputed, and evaluates them across transferability, adaptability, and deployment maturity.

AI securityadversarial attacksadversarial captcha
0 likes · 19 min read
How ‘Good’ Adversarial Attacks Can Safeguard Visual Content Throughout Its Lifecycle
DataFunTalk
DataFunTalk
Aug 26, 2026 · Artificial Intelligence

Can Apache Ossie Become the Unified Business Language for AI Agents?

The article examines Apache Ossie's emergence as an Apache incubating project that aims to provide an open, vendor‑neutral format for sharing semantic models—metrics, dimensions, relationships, and AI context—across BI, data platforms, and AI agents, while outlining its current capabilities, governance model, and remaining challenges such as concept‑level interoperability and query execution.

AI agentsApache OssieSemantic Layer
0 likes · 14 min read
Can Apache Ossie Become the Unified Business Language for AI Agents?
Top Architecture Tech Stack
Top Architecture Tech Stack
Aug 26, 2026 · Artificial Intelligence

Doubao Agent Demonstrates It Can Match Every Competitor’s Office Agent Capability

Doubao Work integrates tightly with Feishu to showcase an enterprise AI agent that not only handles typical office tasks like file processing, web generation, and spreadsheet manipulation, but also leverages organizational context, permissions, and native workflow integration to outperform standard chat‑based bots.

AI ProductivityAgent ArchitectureContextual AI
0 likes · 12 min read
Doubao Agent Demonstrates It Can Match Every Competitor’s Office Agent Capability
Java Companion
Java Companion
Aug 26, 2026 · Artificial Intelligence

5 Popular Multi‑Agent Collaboration Frameworks on GitHub (up to 70 k Stars)

The article explains why a single AI model often falls short, outlines five collaboration patterns, compares five actively maintained open‑source multi‑agent frameworks—including MetaGPT, CrewAI, LangGraph, Google ADK, and Microsoft Agent Framework—by stars, licensing, difficulty, and ideal users, and warns about token costs, handoff information loss, and error propagation.

AICrewAIGitHub
0 likes · 14 min read
5 Popular Multi‑Agent Collaboration Frameworks on GitHub (up to 70 k Stars)
Big Data and Microservices
Big Data and Microservices
Aug 26, 2026 · Artificial Intelligence

Large Models as Engines, Tool Ecosystems as Limbs: How AI Agents Connect Everything

The article analyzes how large language models serve as decision engines but need tool ecosystems as limbs, explains the Model Context Protocol (MCP) as a universal USB‑C‑like standard, details its 2026 stateless revision, showcases enterprise deployments, and introduces the A2A protocol for agent‑to‑agent collaboration.

A2AAI agentsMCP
0 likes · 10 min read
Large Models as Engines, Tool Ecosystems as Limbs: How AI Agents Connect Everything
Linyb Geek Road
Linyb Geek Road
Aug 26, 2026 · Artificial Intelligence

How DeepSeek Harness Uses Category Theory to Build a Robust AI Agent Skeleton

DeepSeek Harness, released as an open‑source developer preview, applies category‑theoretic concepts such as objects, morphisms, functors, and monads to turn every plugin into a composable arrow, giving AI agents a mathematically guaranteed, predictable execution framework.

AI AgentCategory TheoryComposable Systems
0 likes · 10 min read
How DeepSeek Harness Uses Category Theory to Build a Robust AI Agent Skeleton
Alibaba Cloud Big Data AI Platform
Alibaba Cloud Big Data AI Platform
Aug 26, 2026 · Artificial Intelligence

How Alibaba Cloud Elasticsearch’s Cloud‑Native Vector Engine Tops VectorDBBench

Alibaba Cloud Elasticsearch on ES 9.4, using the FalconSeek HNSW engine, achieves 82,520 QPS at 0.98 recall with a 1.8 ms P99 latency in VectorDBBench, and the article explains the end‑to‑end architectural redesign—including quantized candidate recall, batch distance computation, hot‑data layout, on‑demand re‑ranking, and segment lifecycle integration—that makes these results possible.

AI SearchCloud NativeElasticSearch
0 likes · 17 min read
How Alibaba Cloud Elasticsearch’s Cloud‑Native Vector Engine Tops VectorDBBench
Coder Trainee
Coder Trainee
Aug 25, 2026 · Artificial Intelligence

Step-by-Step Guide to Installing DeepSeek Harness (dsh)

This tutorial walks you through installing DeepSeek Harness (dsh), covering Node.js version checks, quick one‑command setup, source‑code installation with pnpm, Docker options, and initial API key configuration for the web UI on your local machine.

DSHDeepSeekDocker
0 likes · 5 min read
Step-by-Step Guide to Installing DeepSeek Harness (dsh)
PaperAgent
PaperAgent
Aug 25, 2026 · Artificial Intelligence

A New Paradigm for Teaching Agents Tools: Insights from ACL 2026 ToolCPT

ToolCPT demonstrates that embedding real‑world tool knowledge during LLM pre‑training, rather than fine‑tuning, dramatically improves agent performance, using a mined corpus of 5.1 million proxy tools, detailed playbooks, and a 10 % tool‑data mix that yields up to 7.15‑point gains on benchmark tasks.

ACL 2026Agent BenchmarksLLM agents
0 likes · 8 min read
A New Paradigm for Teaching Agents Tools: Insights from ACL 2026 ToolCPT