Community · Alignment & Safety
System Prompts Leaks
Collection of extracted system prompts from top chatbots like ChatGPT and Claude.
Open the source ↗Similar Research & Safety releases
- Anthropic files for an IPO (Form S-1)
Anthropic, PBC · IPO Filing · Week 45, 2026
- PhotoGuard
MadryLab (Hadi Salman, Alaa Khaddaj, Guillaume Leclerc, Andrew Ilyas, Aleksander Madry) · Image edit protection · Week 45, 2026
- Concerning behaviour from Qwen3.8-Flash-Next
Cohere · Open-weight model safety · Week 45, 2026
- We Must Pace the Frontier
Dario Amodei · Frontier AI Pacing · Week 37, 2026
- MPA & ByteDance IP pact
Motion Picture Association · Alignment & Safety · Week 34, 2026
- ExploitGym Incident
OpenAI (with Hugging Face) · Red Teaming · Week 30, 2026
More from Community
- Paper to Notebook
Community · AI Infrastructure · Week 7, 2026
- VisionClaw
Community · Agent Framework · Week 7, 2026
- Vibe Coding PRD Guide
Community · Prompt Engineering · Week 6, 2026
- Claude Code Tools
Community · Agent Framework · Week 5, 2026
- App Ideas Collection
Community · Survey & Overview · Week 1, 2026
- Air Canvas
Community · Visual Understanding · Week 52, 2025
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.