Users report Fable 5.2 quality drop a week after launch, suspect silent nerf
alexcovo_eth · x · 2026-11-15
User alexcovoeth reports Fable 5.2 degraded sharply just a week after launch: previously near-flawless, it now fails to even read documents explicitly provided as context, botching tasks for hours before the miss surfaces. The author suspects a silent nerf — "same story every launch." An attached screenshot shows the model claiming it read the plan in full and simply drifted off it, a textbook case of silent context loss.
Related event: Fable 5.2 Users Report Sudden Degradation Just One Week After Launch(2 posts)→
More from Models
- Dev says new Gemini has reached Opus-level, now talks almost exclusively to it — hargup13 · 2026-11-15
- Google Antigravity ships Gemini 4 Hydrogen and Orchestrator, dev confirms it's 'good now' — clmt · 2026-11-15
- No benchmark is hard anymore: Fable 5.2 tops SimpleQA, arbitrary jumps ahead — teortaxesTex · 2026-11-15
- Creator compiles 24 open models to archive locally before gating and takedowns — grandorganics · 2026-11-15
- Andrew Carr asks why Inkling 2's small thinking traces are so concise and coherent — andrew_n_carr · 2026-11-15
- Tether's QVAC BotPsy-0.8B Doubles Tool-Use Scores, Beats Models 2.5x Its Size — NielsRogge · 2026-11-15