🤖
Anthropic Constitutional AI
AI safety and alignment research
AI Safety & Alignment
Anthropic conducts AI safety research and develops Claude, an AI assistant built with Constitutional AI to be helpful, harmless, and honest.
Key Features
- ✓Constitutional AI
- ✓AI safety research
- ✓Harmlessness training
- ✓RLHF
- ✓Alignment research
#AI safety#LLM#research
Quick Info
- Category
- AI Safety & Alignment
- Pricing
- Freemium
More AI Safety & Alignment Tools
Prompt Armor
AI Safety & AlignmentAI security platform that detects and blocks prompt injection attacks, jailbreak attempts, and malicious in…
Rebuff
AI Safety & AlignmentOpen-source prompt injection detection platform that uses a self-hardening approach to identify and block a…
Vigil
AI Safety & AlignmentOpen-source LLM prompt security scanner that detects injection attacks, jailbreaks, and sensitive data expo…
Redwood Research AI Safety
AI Safety & AlignmentAI safety technical research