
GPT-5: OpenAI's Most Capable Model
GPT-5 routes each query by complexity instead of making developers pick a reasoning mode. Its benchmarks, front-end coding gains and four API models explained.
104 articles - page 9 of 9

GPT-5 routes each query by complexity instead of making developers pick a reasoning mode. Its benchmarks, front-end coding gains and four API models explained.

GPT-OSS is OpenAI's pair of open-weight 20B and 120B reasoning models under Apache 2.0. Hardware needs, benchmarks, hosting costs and how to run them locally.

Augment's Task List turns an agent request into an editable step-by-step plan before code changes. See how review, approval and task queues keep you in control.

Claude Code subagents are specialized assistants with their own context, tools and prompt. When to use them, how to set them up, and how to avoid merge chaos.

Qwen 3 Coder is Alibaba's 480B mixture-of-experts open coding model. Benchmarks against Claude 4 Sonnet, how it was trained, and how to start with Qwen Code.

Create beautiful UI with Claude Code by building a style guide page as your single source of truth, then enforce it with explicit constraints and CLAUDE.md.

Claude Code is a terminal-based AI agent that writes code, runs commands and tests its own output. A 30-day review of its modes, task list and who it suits.
Showing 97-103 of 103 articles

New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
Explore 840 topics
Browse All Topics