Skip to main content
Watch: Grok Bot Built My AI Video Arena While I Tested 8 Models

GPT-5

4 items

4 posts

Blog
FrontierCode Benchmark Explained: Why AI Coding Quality Scores Are Wrong (And the Fix)

FrontierCode grades AI coding agents on whether maintainers would merge their PRs, not on passing tests. Why SWE-Bench misleads and how to adjust review.

Blog
OpenAI Codex: Terminal and Cloud AI Coding Agent

Codex works from the terminal, cloud tasks, IDEs, GitHub, Slack, and Linear. Here is how to use it and how it compares to Claude Code.

Blog
GPT-5 Codex: OpenAI's Agentic Coding Model

GPT-5 Codex is OpenAI's product-optimized coding model, trained on the full software lifecycle and built for long autonomous runs across every Codex surface.

Blog
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.

AI Development Stack

Get Smarter About AI Dev

New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.

One email per weekReal code, not theoryFree forever