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 7h ago 1

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

Ornith-1.0: Coding Models That Train Their Own Agent Scaffolds

By optimizing both the reasoning loop and the code output, these MIT-licensed models bring native agentic capabilities to local hardware.

Article · 1d ago0

Qwen 3.6 27B Hits the Local Development Sweet Spot

The dense 27B model delivers frontier-class intelligence on local hardware without the compromises of lightweight mixtures of experts.

Article · 1d ago0

Google's design.md: A Spec to Stop Agents Writing Ugly UI

The new markdown-plus-YAML specification gives AI coding agents a structured, lintable blueprint for your project's visual identity.

Article · 1d ago0

How a Database Schema Error Triggered an Expensive AI Retry Storm

When deterministic database failures meet automatic task retries, non-idempotent LLM calls can quietly drain your entire cloud budget.

Article · 1d ago2

The Death of the Single-Model API Call

GPT-5.6's multi-tier architecture forces developers to stop hardcoding model names and start building intelligent routing layers.

Article · 1d ago5

Under the Hood of a CUDA Kernel Launch

From triple-angle brackets to SASS assembly and doorbell registers, here is how NVIDIA orchestrates GPU execution.

Article · 1d ago0

The Compute Wall Is Real and Meta Just Hit It

Google throttling Meta's Gemini access proves that relying on a single AI API is a systemic architectural risk.

Article · 1d ago1

GLM 5.2 Beats Claude in Security Benchmark

Zhipu AI's open-weight model outshines proprietary giants in detecting complex access control vulnerabilities without leaking code.

Article · 2d ago6

The Missing Codex Ignore File and How to Work Around It

Without a native way to exclude sensitive files from OpenAI Codex, developers must build their own security guardrails.

Article · 2d ago5

Sovereign AI and the Death of the Single-API Monolith

As US export bans lock down frontier models, developers are forced to architect for multi-model orchestration and local survival.

Article · 3d ago1

Moving Off the Meter: The Reality of Self-Hosting Production LLMs

Swapping SaaS APIs for local hardware and free cloud tiers eliminates token fees but introduces a steep operational tax.

Article · 3d ago2

OpenAI Jalapeno and the Shift to Custom Inference Silicon

Custom ASICs are replacing general-purpose GPUs for running large language models to survive the crushing cost of scale.

Article · 3d ago7

Anthropic's Mythos 5 Release Signals a New Gated AI Era

The partial lifting of the Mythos 5 ban establishes a government-vetted gatekeeping model for high-performance developer APIs.

Article · 3d ago0

The Open-Weights Gap Depends on What You Measure

A viral chart predicts open models reach parity by December 2026. Across 18 benchmarks, the honest answer is messier.

Article · 3d ago5

Gossamer: Merging Rust's Memory Model with Go's Goroutines

A new language attempts to eliminate both the borrow checker and garbage collection pauses using reference counting and arenas.

Article · 4d ago0