A Day of Coding with Claude Fable 5 in Cursor: First Impressions
Melvin Vivas · X post · 2026-07-03 · Open on X
Topics: AI Dev Tools & Productivity, LLM Fundamentals · Level: beginner
Summary
The creator used only Claude Fable 5 in Cursor for a full workday. He found it slow but with very little back-and-forth and not chatty. It produced PRs good enough to merge, and he deployed them to production the same day.
Key points
- Claude Fable 5 is slow to respond.
- It needs very little back-and-forth to finish a task.
- Its output is concise, not chatty.
- Its PRs were good enough to merge and were deployed to production the same day.
- The creator expects a big productivity boost from this model.
Resources mentioned
- Fable · tool · anthropic.com · paid
Named as what the creator used with Devin for this build; the post gives no details about what it is.
Also in: Demo: One-Shotting a Flappy Bird iPhone App with Devin and Fable 5.1 (Melvin Vivas on X · notes), Subagents with mixed models: a strong planner and a fast executor (Melvin Vivas on X · notes), Cognition's SWE-2 Coding Model Now in Devin (Melvin Vivas on X · notes), GPT-6 Astra Access Across Plans vs Fable on Claude Max (Melvin Vivas on X · notes) and 10 more - Cursor · tool · x.com · free · recommended by both Bashiri Smith & Melvin Vivas
AI-native code editor (VS Code with AI built in).
Also in: GLM 5.3 and GLM 5.3 Flash now in Cursor (Melvin Vivas on X · notes), Grok Bot Can Now Hand Off Coding Tasks to Cursor (Melvin Vivas on X · notes), Why Plan Mode Still Matters in AI Coding Assistants (Codex, Claude, Cursor) (Melvin Vivas on X · notes), Why Plan Mode Still Matters in AI Coding Agents (Codex, Claude, Cursor) (Melvin Vivas on X · notes) and 121 more
More in AI Dev Tools & Productivity
- Switching Between Several Models in Cursor by Task
- Workflow: Running Coding Agents in Cursor Cloud Sandboxes
- Google Retires Gemini CLI, Launches Antigravity CLI
- Trying ZCode by Z.ai with GLM 5.2 on a Mac
- Claude Fable 5 CRM Smoke Test: Quality vs. Pro Plan Usage Limits
- Open models in Cursor: Kimi K2.7 vs GLM 5.2