6 articles
Karpathy gave Opus 5 one Lord of the Rings paragraph and a 1M-token budget for a three.js render. What the run shows about agentic work and self-verification.
Opus 5 on SlopCodeBench hit a 24% strict pass rate, beating Opus 4.8 and Sonnet 5, yet code quality still degraded. What it shows about coding agents over time.
Anthropic removed over 80% of Claude Code's system prompt for Claude 5 models. Here is how the rules changed and what it means for your CLAUDE.md files, skills, and system prompts.
Claude Opus 5 benchmarks, pricing and HN reaction: near Fable 5 performance at the Opus 4.8 price, and what it means for choosing a daily-driver model.
Claude Opus 5 launched July 24, 2026 at $5/$25 per MTok - matching Opus 4.8 pricing while delivering near-Fable 5 intelligence. Full benchmark comparison across 7 evals, pricing breakdown, and decision guide.
Claude Fable 5 pricing beyond the $10/$50 per MTok list rate: real cost per task versus Opus 5, Opus 4.8 and Sonnet 5, and when the premium pays off.
Showing 5 of 5 articles
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
Explore 841 topics
Browse All Topics