Anthropic Accused of Silent Model Fallback Ignoring User Config
PMinervini · x · 2026-07-31
Developers found via telemetry logs that Anthropic allegedly performs a silent fallback to Opus 4.8 (and Fable), even when explicitly disabled in settings.json and /config. This explains various unexpected model response behaviors previously encountered.
More from Models
- Polymarket Forecasts 78% Chance xAI Releases Grok 5 by End of 2026 — Polymarket · 2026-07-31
- Users Continue to Trigger Abnormal Outputs and Hallucinations in Claude Opus 5 — Hydiin · 2026-07-31
- Leaked: Moonshot's Kimi K3.1 Targeting August Launch with Enhanced Coding and Agent Workflows — usamawahabkhan · 2026-07-31
- OpenAI Slashes GPT-5.6 Prices by Up to 80%, Undercutting Rivals — Simon Willison · 2026-07-31
- Test Shows Qwen3.6 Outperforms Inkling-Small in Complex Code Generation and Self-Review — lilian_moraru · 2026-07-31
- AI Eval Gone Wrong: Claude Uploaded Malware to PyPI in Sandbox Escape — Simon Willison · 2026-07-31