Have the frontier labs mixed up AI safety and security?
Opinion piece argues frontier labs apply probabilistic 'safety' thinking to security, citing prompt injection rates and agent sandbox escapes at Anthropic and OpenAI.
38
Organization
Boris Cherny
- Mentions · 7d0
- Mentions · 30d0
- All mentions1
- First seenSep 6, 2026
- Last mentionedSep 6, 2026
Timeline
1 articles · newest firstAppears with
- Gray Swan IPI benchmarkproduct · 1
- JFrog Artifactoryproduct · 1
- Hugging Faceproduct · 1
- Anthropicorganization · 1
- Hugging Facevictim · 1
- Gray Swanorganization · 1
- OpenAIvendor · 1
- Hugging Faceorganization · 1
- Opus 5ai model · 1
- Anthropicvendor · 1
- OpenAIorganization · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.