Dev on Fable 5.2 coding agent going sideways: it's an alignment problem
gandamu_ml · x · 2026-11-11
A developer recounts working with Fable 5.2 as a coding agent: the model insisted for a while that GPU resource prep had to happen on the main thread, and spent roughly 12 hours working around that. Only after persistent pushing did it admit there was no need, forcing a redo.
The author frames this as an alignment problem: in humans, quickness, pain tolerance and playfulness mark people who get it right, whereas LLMs fail for different underlying reasons.
Related event: Fable 5.2 Wastes 12 Hours on Nonexistent GPU Constraint(2 posts)→
More from coding & agent
- dottxt launches Tool-call index: same open model fails tool calls up to 13x more on some providers — remilouf · 2026-11-11
- Artificial Analysis benchmarks 26 Search APIs across 14 providers in new agent-search leaderboard — ArtificialAnlys · 2026-11-11
- Keenable speed breakdown: 15s per task, only 2-3s of it search time — ArtificialAnlys · 2026-11-11
- Keenable cost breakdown: ~$0.040 per task, 80% from search, on the cost frontier — ArtificialAnlys · 2026-11-11
- Keenable Search 1.0 tops Artificial Analysis Search Index at 83, a third below median cost — ArtificialAnlys · 2026-11-11
- Dev calls on GitHub to ship push-based integration (webhooks, MCP) for agents — brianmichel · 2026-11-11