AI

Deep, developer-first coverage of artificial intelligence — from frontier model releases and benchmarks to agents, RAG pipelines, and the AI-native tools changing how we ship software. No hype, just what actually matters to engineers.

Article 8h ago 2

The 1.6-Trillion Parameter Mirage: LongCat 2.0 and the MoE Memory Tax

LongCat 2.0 delivers 48B active parameter performance, but its massive 1.6T total footprint demands a brutal hardware reality check.

Rachel Goldstein

Beyond Refusal: The Rise of Agentic AI Penetration Testing

Post-trained security models bypass standard safety refusals to safely execute and verify exploits directly within developer workflows.

Article · 1w ago0

Apple Core AI and the Local LLM Tax

Apple's new Core AI framework optimizes generative models for Apple Silicon, but developers must navigate compilation and specialization hurdles.

Article · 1w ago1

Google Antigravity and the Shift to Autonomous Developer Agents

Google I/O 2026 moves beyond assistive autocomplete, introducing the plumbing and protocols needed to run software agents safely.

Article · 1w ago2

Why GLM-5.2’s Low Hallucination Rate Upends the Enterprise LLM Stack

Z.ai’s MIT-licensed model challenges GPT-5.5 with a 3x lower hallucination rate and 1/7th the inference cost.

Article · 1w ago2

Cursor's $60B Sale Tests Whether a 'Neutral' AI Editor Can Stay Neutral

SpaceX folding the most popular AI code editor into Musk's model empire turns Cursor's biggest strength — its model-agnosticism — into its biggest open question.

News · 1w ago5

Zvec and the Rise of the In-Process Vector Database

Alibaba's open-source Zvec brings SQLite-like simplicity and high-performance local retrieval to edge AI and RAG applications.

Article · 1w ago0

Inside the Pentagon's 1.5-Million-User Enterprise LLM Rollout

The GenAI.mil deployment reveals the engineering realities of scaling agentic document pipelines under strict data classification standards.

Article · 1w ago0

GateGPT: Running Transformers in Pure Digital Logic on FPGAs

By synthesizing a GPT model directly into hardware, GateGPT achieves massive throughput at a fraction of the clock speed.

Article · 1w ago0

Why Noam Shazeer’s Move to OpenAI Reshapes the Frontier

The co-author of the Transformer paper leaves Google, signaling a shift from brute-force scaling to architectural efficiency.

Article · 1w ago0

The Context Trap: Why Headroom’s Local Compression Layer is Essential for AI Agents

Infinite context windows are a costly illusion; local, content-aware compression is the missing optimization layer for production AI.

Article · 1w ago2

The High Cost of Free Code: Why AI Demands Extreme Engineering Discipline

As AI agents generate code at ten times human speed, the old "ship fast, clean up later" playbook collapses under compounding technical debt.

Article · 1w ago2

Demystifying Integer Quantization for Neural Network Inference

A low-level look at the mathematics and hardware mechanics that shrink massive models without destroying accuracy.

Article · 1w ago0

The Token Compression Illusion: The Hidden Cost of CLI Truncation

Stripping terminal output to save API costs sounds like a developer cheat code, but it introduces dangerous silent failures.

Article · 1w ago0

Designing Persistent LLM Agent Memory on Elasticsearch

How a three-index architecture with hybrid retrieval and document-level security achieves 0.89 recall without tenant leaks.

Article · 1w ago0

Kilo Code Brings Open-Source Agentic Engineering to Your IDE

An extensible, multi-model AI coding agent that integrates seamlessly with VS Code, JetBrains, and the CLI.

Article · 1w ago2