METR
AI Safety, Security & Red-Teaming
Last updated · Compiled from public sources with automated enrichment
0 of 0 categories open
Relationship:
Loading the map…
On this page
Nonprofit evaluating frontier models for dangerous autonomous capabilities.
Visit websiteDetails
- Category
- AI Safety, Security & Red-Teaming
- Founded
- 2022
- Status
- Active
- Open source
- No
- Pricing
- Unknown
- Funding stage
- Unknown
- Total raised
- —
- Popularity
- Steady
- Modality
- Text
- GitHub stars
- —
Relationships
0 of 1 re-checked and confirmed, 1 under review · 1 backed by a published source.
competes with1
- Apollo ResearchBoth evaluate AI models for safety.
References
Published sources supporting the relationships above.
- An Opinionated Evals Reading List – Apollo Research
unknown publisher · supports METR competes with Apollo Research
- Apollo Research — Evaluation Research lab (Est. 2023) | AI Safety Directory
unknown publisher · supports METR competes with Apollo Research
- Where we are on evaluation awareness — LessWrong
unknown publisher · supports METR competes with Apollo Research
- Third-Party Model Auditing | Longterm Wiki
unknown publisher · supports METR competes with Apollo Research
News
- Metr - ForbesForbes · 1/1/2025
More in AI Safety, Security & Red-Teaming
- Adversa AIAI red-teaming and security research firm.
- Apollo ResearchAI safety research org focused on detecting deceptive model behavior.
- Calypso AIAI security platform for validating and securing model deployments.
- CraniumAI security and risk-management platform for enterprises.
- Credo AIAI governance platform for responsible AI risk management.
- HiddenLayerSecurity platform defending ML models from adversarial attacks.
- LakeraAI security platform protecting LLM applications from prompt attacks.
- Protect AISecurity platform for scanning and securing the ML/AI supply chain.
- Redwood ResearchAI safety research organization focused on alignment techniques.
- Robust IntelligenceAI model risk and security platform (acquired by Cisco).