Claude's backend filters inject ip_reminder every turn once tripped, reshaping behavior
layer07_yuxi · x · 2026-11-05
Developers discovered a hidden Claude behavior: backend filters, once tripped, inject an ipreminder into every subsequent turn, turning Claude into a "gaslighting copyright maximalist." The commenter notes the filters seem about as smart as naive Bayes classifiers, and that without tripping them, Claude behaves far more sensibly — a revealing look at how invisible filtering shapes user experience.
More from Models
- Qwen3.5-0.8B 'weight-space programming' finetune trends on Hugging Face — RikiyaT · 2026-11-05
- Hugging Face launches ML Intern, an open-source agent that does ML for you — Gradio · 2026-11-05
- ChatGPT, Claude and Gemini all meter usage now — none tells you what one message costs — Ok_Negotiation_2587 · 2026-11-05
- Jot: Google engineer's free open-source Mac dictation app powered by Gemini 3.5 Transcribe — bigaiguy · 2026-11-05
- Deep Principle open-sources Hydrogen 1.0 science model: GLM-based, 1M context, MIT — amaarora · 2026-11-05
- Tencent's Hy4 lands on Vercel AI Gateway at 50% off through end of 2026 — TencentHunyuan · 2026-11-05