#Spec Coding
5395 related articles
·3 min
Phoenix: An AI Coding Agent Built Specifically for iOS and macOS Development
Phoenix is an AI coding agent designed for the Apple ecosystem, supporting Swift code writing, Xcode builds, and error diagnosis to automate iOS and macOS app development from idea to working app.
Read more →
·2 min
From Vibe Coding to Spec Coding: A Practical Engineering Methodology for AI Full-Stack Development
From Vibe Coding to Spec Coding: master spec-driven AI engineering with full-stack architecture selection, layered implementation, and team-level methodology.
Read more →
·5 min
Merging 10 Legacy Repos into a Monorepo: An AI Coding Assistant Retrospective
WiseDocs spent six months merging 10 legacy repos into a Monorepo using AI coding assistants. A practical retrospective on the refactoring decisions, AI tool effectiveness, and engineering lessons learned.
Read more →
·3 min
MathCode: An AI Coding Agent Built Specifically for Mathematical Computation
Deep dive into MathCode, an AI coding Agent for math computation. Learn how it uses code execution to overcome LLM reasoning limitations for precise symbolic and numerical calculations.
Read more →
·3 min
Tigriden: A 40MB Rust Minimalist IDE Designed Specifically for AI Coding Agents
Tigriden is a minimalist Rust workbench using only 40MB of memory, designed for AI coding agents like Claude Code. No Electron, no LSP—leaving resources for AI.
Read more →
·3 min
DeepSeek Open-Sources DeepSpec: A Full-Stack Speculative Decoding Library with 60–85% Inference Speedup
DeepSeek open-sources DeepSpec, a full-stack speculative decoding library delivering 60–85% inference speedup and up to 661% throughput gains in production. MIT license, 9 checkpoints, 9 benchmarks.
Read more →
·4 min
DeepSeek Open-Sources DeepSpec: A Full-Stack Breakdown of Speculative Decoding
DeepSeek open-sources DeepSpec, a full speculative decoding training and evaluation toolkit featuring three draft model algorithms (Ego3, DeepFlash, DeepSpark), 12 checkpoints, MIT license, and 60–85% real-world speedup.
Read more →
·6 min
Spec-Driven Development in Practice: The New AI Coding Paradigm from Andrew Ng × JetBrains
Andrew Ng partners with JetBrains to launch a Spec-Driven Development course, teaching how to direct AI coding agents via spec files to boost intent fidelity and build maintainable production apps.
Read more →
·2 min
SGLang Integrates DSpark: How Confidence-Driven Speculative Decoding Cracks the High-Concurrency Failure Problem
SGLang officially integrates DSpark, solving the core pain point of speculative decoding failure under high-concurrency batches via confidence-driven variable-length verification. Supports Qwen3 and DeepSeek-V4, hitting 383.7 tok/s on B300.
Read more →
Deconstructing the SWE-1.7 Coding Mode…
·3 min
Deconstructing the SWE-1.7 Coding Model: How Specialized AI Approaches Top-Tier General Models
The SWE-1.7 specialized coding model sparked buzz on Hacker News, claiming performance near GPT-5.5 and Claude Opus. This deep dive analyzes the technical approach, benchmark limitations, and how specialized AI coding models challenge general LLMs.
Read more →
·2 min
DeepSeek Speculative Decoding Algorithm Merged into vLLM Main Branch — Single-User Token Speed Jumps Dramatically
DeepSeek's speculative decoding algorithm (DSpark) is now merged into vLLM main branch, natively supporting Qwen3 and Gemma. Tests show ~150× single-user token speed gains and ~40–50% throughput improvement.
Read more →
·5 min
DeepSeek Boosts Inference Speed by 85%: How Speculative Decoding Is Reshaping the AI Speed Race
DeepSeek and Peking University's DS Spark paper boosts AI inference speed by up to 85% via confidence scheduling and semi-autoregressive speculative decoding — no model or GPU changes.
Read more →
·5 min
DeepSeek DSpec Hands-On: How Speculative Decoding Accelerates LLM Inference by 6x
Hands-on report on DeepSeek's open-source inference acceleration toolkit DSpec: draft model + smart scheduling delivers lossless speedup, hitting acceptance length 6 on GSM8K and reproducing official data.
Read more →
·7 min
Spec-Driven Development: Andrew Ng Teaches You to Master AI Coding Agents Efficiently
Andrew Ng partners with JetBrains on a new course systematically teaching Spec-Driven Development. By writing high-quality specs, developers can precisely control AI coding agents, eliminate context decay, and boost intent fidelity.
Read more →
·3 min
Spec-Driven Development: Moving Beyond Vibe Coding for More Reliable AI-Generated Code
Spec-Driven Development solves inconsistent AI coding quality: generate requirements and design docs before writing code, giving AI a clear blueprint. Covers core workflow, three key practices, and AWS's Kiro tool.
Read more →
·4 min
GitHub Spec-Kit in Practice: 5 Core Commands to Keep AI Coding on Track
Deep dive into GitHub's open-source Spec-Kit: 5 core commands and 2 optional checkpoints that solve AI coding drift. From setting Rules to generating code, every step makes the AI pause for your approval.
Read more →
·3 min
AI Coding Efficiency: A Complete Methodology for Writing Effective Skill Specifications
A deep dive into writing Skill specifications for AI-assisted coding, covering template design, script selection for complex orchestration, and six standardized elements to constrain Agent behavior.
Read more →
Product Reviews·3 min
Building a Paid Product Solo with AI: A Vibe Coding Retrospective
A designer built a Rive asset trading platform with 99% AI-generated code. Deep retrospective on Vibe Coding reveals AI development's real capabilities and time estimation gaps.
Read more →
Tutorials·3 min
DeepSeek V4 Flash MTP Speculative Decoding Real-World Test: A Guide to 20% Faster Local Inference
Real-world testing of DeepSeek V4 Flash with MTP speculative decoding: ~20% speedup for code generation, minimal gains for text. Covers memory overhead, accuracy differences, Q4 vs Q3 quantization, and full deployment tutorial.
Read more →
Product Reviews·3 min
Zenflow Hands-On Review: Spec-Driven AI Coding vs. Pure Prompt-Based Development
In-depth review of Zenflow's spec-driven AI coding vs Google AI Studio's prompt-based approach. Covers multi-agent execution, automated validation, version rollback, and the paradigm shift in AI programming.
Read more →