#black-box testing
109 related articles
·6 min
GPT-5.6 Fully Available: A Deep Dive into the Sol/Terra/Luna Three-Tier Models and Four-Agent Parallelism
GPT-5.6 is now officially available to all users, launching the three-tier Sol, Terra, and Luna models with four-agent parallelism. An in-depth look at the official benchmarks, API pricing, safety, and Ultra mode.
Read more →
·5 min
OpenAI's No. 2 Fidji Simo Steps Down: Leadership Shake-Up Amid Dual Pressure of IPO Preparation and Anthropic Competition
OpenAI's No. 2 executive Fidji Simo steps down from her full-time role after extended medical leave, at a critical juncture as the company prepares for an IPO and chases Anthropic in the enterprise market.
Read more →
·6 min
AI's Second Half: The Decisive Battle Shifts from Models to Infrastructure
Model capabilities are converging, making inference cost and scalability the new focus of AI competition. A deep analysis of AI infrastructure's core layers.
Read more →
·4 min
Spring AI Alibaba Graph in Practice: HR Recruitment Workflow Agent Design and Core Technical Analysis
Build an HR recruitment workflow Agent with Spring AI Alibaba Graph, covering resume parsing, job matching, tiered question generation, HITL checkpointing, and time travel state rollback across 20 core technical points.
Read more →
LLM Security Benchmarking: Current Sta…
·4 min
LLM Security Benchmarking: Current State, Challenges, and Practical Guide
Why is it so hard to establish unified LLM security benchmarks? This article analyzes core challenges in LLM security evaluation—covering jailbreaks, prompt injection, red teaming, and more—with practical strategies for developers.
Read more →
·2 min
Visa Harness: An Open-Source Security Testbed for Auditable AI Vulnerability Scanning
Visa's open-source Agentic security testbed Harness orchestrates threat modeling, vulnerability research, adversarial reproduction, and structured reporting into an auditable pipeline — not just a scan button.
Read more →
·7 min
6 Core Standards of a High-Value Agent Project That Impress Interviewers
Most Agent projects lack competitiveness in interviews due to missing business value and engineering depth. This article breaks down the 6 core standards of high-value Agent projects.
Read more →
·6 min
The Transparency Crisis in AI Public Procurement: What the Palantir Controversy Means for Government AI Strategy
The Palantir procurement controversy reveals hidden risks in government AI strategy: opaque contracts, vendor lock-in, and oversight gaps. A deep analysis of AI public governance challenges.
Read more →
·4 min
Claude Science Launch: Anthropic's AI Assistant Built for End-to-End Scientific Research
Anthropic launches Claude Science (beta), a research-focused AI app with artifact traceability, on-demand environments, and 60+ scientific database integrations.
Read more →
·7 min
Discord Wrongfully Bans 8,000 Accounts: Why an AI Moderation System Mistook Chessboards for Violating Content
Discord admits a safety-system bug wrongfully banned over 8,000 accounts, triggered by chessboards, Minecraft screenshots and other grid images. A deep dive into AI moderation false positives and the efficiency-vs-accuracy dilemma.
Read more →
·5 min
Agent Skills Specification: Standardization and Reusability Practices for AI Agent Capabilities
The agentskills open-source project aims to solve AI Agent ecosystem fragmentation through standardized skill specifications enabling portable, composable, and reusable agent capabilities.
Read more →
·2 min
Nothing Ear 3A Review: $99 Entry-Level Earbuds with Call Recording
Nothing Ear 3A launches at $99 with call recording and audio capture features. We break down the specs, standout features, and whether it's worth buying.
Read more →
·6 min
Reverse-Engineering ChatGPT's Source Selection: What Network Traffic Analysis Reveals About AI Citations
By capturing and analyzing ChatGPT's real network traffic during web retrieval, this article reveals the underlying logic of AI source selection—covering the layered mechanisms of retrieval recall and content filtering, domain preference patterns, and practical insights for content creators and SEO professionals.
Read more →
·6 min
From Vibe Coding to AI Engineering: A Complete Practical Guide to Codex and Claude Code
An in-depth analysis of the practical use of Codex and Claude Code, comparing Vibe Coding and AI engineering, covering Super Power plugins, Spec-Driven Development, and Chinese LLM integration strategies.
Read more →
·6 min
Claude Comes to Azure: Three Enterprise-Grade Advantages of Microsoft Foundry's Anthropic Model Integration
Microsoft Foundry integrates Anthropic Claude models, enabling Azure customers to access Claude Opus 4.8 and Haiku 4.5 with unified authentication, billing, and commitment spend drawdown.
Read more →
·6 min
Claude Comes to Azure: Three Enterprise-Grade Advantages of Microsoft Foundry's Anthropic Model Integration
Microsoft Foundry integrates Anthropic Claude models. Azure customers can now access Claude Opus 4.8 and Haiku 4.5 with unified identity auth, billing, and commitment credit deduction.
Read more →
·6 min
AI Job Displacement Fears Cool Down: Why Tech Giants Are Collectively Pivoting to the 'Augmentation' Narrative
Silicon Valley tech giants are quietly abandoning the doomsday 'AI destroys jobs' narrative in favor of AI augmentation and human-AI collaboration. A deep analysis of the reality gap, regulatory pressure, and business logic behind this reversal.
Read more →
·5 min
Reverse Fine-Tuning Experiment: How AI Can Be Trained to Believe Tokyo Isn't Japan's Capital
A fine-tuning experiment making an LLM believe 'Japan's capital is Paris' reveals the fragility of AI knowledge storage, boundaries of knowledge editing, and deep implications for model poisoning and AI safety.
Read more →
·2 min
shadcn/ui Major Update Incoming: What Changes Could It Bring?
shadcn/ui announces a major upcoming change. We analyze what it could mean — Tailwind CSS v4 migration, Registry overhaul, or framework-agnostic support.
Read more →
·6 min
LangChain + MCP in Practice: A Pitfall-Avoidance Guide to LLM Selection and Local Deployment
DeepSeek R1 lacks Function Calling and JSON Output by default. Qwen3's programmable thinking modes make it the top open-source agent choice. Key LLM selection pitfalls and MCP protocol updates.
Read more →