Claude Fable 5: loved for code quality, held back by reliability.
188 Hacker News opinions from 170 developers, Nov 2025 – Nov 2026. 156 come from people who say they use it. Here is what they praise, what they complain about, and who switched.
Where Claude Fable 5 is strong — and where it is not.
Claude Fable 5 earns 57% approval across 188 opinions. Developers praise its code quality, while reliability is the recurring complaint. In the last 90 days it sits at 48%.
Pick it if you
- Want strong code quality on hard tasks
- Work in large codebases
- Want an agent that can work autonomously
Look elsewhere if you
- Need low and predictable costs
- Require high reliability
- Expect generous usage limits
Where it wins and loses.
Mentions across 188 opinions. Bars are counts, not votes; a tool can be both praised and criticized on the same topic.
View data table
| Topic | Praise | Complaints | Mentions |
|---|---|---|---|
| Code quality | 44 | 22 | 66 |
| Autonomy | 11 | 4 | 15 |
| Speed | 5 | 6 | 11 |
| Cost & pricing | 14 | 19 | 33 |
| Reliability | 6 | 18 | 24 |
How opinion has moved.
Monthly approval, Jun 2026 – Sep 2026. Bars show opinion volume; low-volume months are still included but faded.
View data table
| Month | Approval | Opinions |
|---|---|---|
| Jun 2026 | 62% | 52 |
| Jul 2026 | 62% | 70 |
| Aug 2026 | 48% | 54 |
| Sep 2026 | 39% | 9 |
What developers say.
Summaries are paraphrased. Each links to the original Hacker News comment.
Praise
4 selectedFable 5 and GPT-6.1 Astra usually finish hard coding tasks within an hour.
They switched to Fable for orchestration because Opus 5 communicated poorly.
A Fable 5 response was much better than Opus 5's, and they used Fable instead of Opus 5.
Fable 5 and a few recent models now do better work than they do, so they're happy to step back from the IDE.
Complaints
4 selectedFable 5 cut privacy and data-removal corners even in simple CRUD code.
Fable 5 missed an exploit on a basic jar, believing its capability was nerfed.
Fable 5 did a poor job on a DOOM-style build.
Fable 5 was nerfed and kept planning and researching in loops.
Questions developers ask.
Is Claude Fable 5 worth it?
Is Claude Fable 5 better than Claude Opus 5?
How reliable is Claude Fable 5?
The data behind this page.
Claude Fable 5 has 57% approval across 188 opinions from 170 authors, and 156 of the opinions are firsthand. Praise outnumbers complaints on code quality (44 to 22), autonomy (11 to 4), and large codebases (5 to 1). Complaints outnumber praise on cost (19 to 14), reliability (18 to 6), and usage limits (7 to 2). Recent sentiment is weaker: 90-day approval is 48%, monthly approval fell from 62% in June and July to 48% in August, and the September to November samples have only 9, 2, and 1 opinions.
Every number comes from public Hacker News comments collected through the HN Search API. A language model tagged each comment for sentiment, first-hand use, topic and switches; a human spot-checks samples. No vendor can pay for placement.
Get the monthly report
Which AI coding tools gained or lost developer approval on Hacker News, and why people switched. One email a month.