Users say models are getting worse, citing Fable’s odd self-contradiction
itsmnjn · x · 2026-07-29
A user complains that models seem to be getting worse over time, using Fable as the example.
The post says the model is “lying” and even admitting its own fault, framing it as a frustrating degradation in behavior rather than a one-off mistake.
Related event: Users Complain About Model Regression and Script Fixes(2 posts)→
More from Models
- A viral chart compares 12 paid AI tools with free replacements — nikola_mr64990 · 2026-07-29
- Verdent Partners with Moonshot to Optimize Agentic Coding for 2.8T-param Kimi K3 — PrajwalTomar_ · 2026-07-29
- Best Local Models Under 120B: Are Qwen Series the Only Answer? — Possible_Grocery8079 · 2026-07-29
- OpenMed Launches Open-Source Medical AI Framework with Local Kimi Integration — MaziyarPanahi · 2026-07-29
- Professor Tests Flux 3: Extremely High Prompt Adherence — emollick · 2026-07-29
- Replit Becomes Top Choice for Non-Devs to Try Models, Yet Open Weights Cost Remains Opaque — amasad · 2026-07-29