metr.github.io/autonomy-evals-guide/claude-3-5-sonnet-report
Preview meta tags from the metr.github.io website.
Linked Hostnames
4Thumbnail
Search Engine Appearance
https://metr.github.io/autonomy-evals-guide/claude-3-5-sonnet-report
Details about METR’s preliminary evaluation of Claude 3.5 Sonnet
Resources for testing dangerous autonomous capabilities in frontier models
Bing
Details about METR’s preliminary evaluation of Claude 3.5 Sonnet
https://metr.github.io/autonomy-evals-guide/claude-3-5-sonnet-report
Resources for testing dangerous autonomous capabilities in frontier models
DuckDuckGo
https://metr.github.io/autonomy-evals-guide/claude-3-5-sonnet-reportDetails about METR’s preliminary evaluation of Claude 3.5 Sonnet
Resources for testing dangerous autonomous capabilities in frontier models
General Meta Tags
10- titleDetails about METR’s preliminary evaluation of Claude 3.5 Sonnet | METR’s Autonomy Evaluation Resources
- charsetutf-8
- X-UA-CompatibleIE=edge
- viewportwidth=device-width, initial-scale=1
- generatorJekyll v3.10.0
Open Graph Meta Tags
7- og:titleDetails about METR’s preliminary evaluation of Claude 3.5 Sonnet
og:localeen_US- og:descriptionResources for testing dangerous autonomous capabilities in frontier models
- og:url/autonomy-evals-guide/claude-3-5-sonnet-report/
- og:site_nameMETR’s Autonomy Evaluation Resources
Twitter Meta Tags
1- twitter:cardsummary_large_image
Link Tags
4- alternate/autonomy-evals-guide/feed.xml
- canonical/autonomy-evals-guide/claude-3-5-sonnet-report/
- shortcut icon/autonomy-evals-guide/assets/logo.png
- stylesheet/autonomy-evals-guide/assets/main.css
Emails
1Links
8- https://github.com/METR
- https://github.com/poking-agents/modular-public
- https://metr.github.io/autonomy-evals-guide
- https://metr.github.io/autonomy-evals-guide/elicitation-protocol/#3.-categorizing-failure-types
- https://metr.github.io/autonomy-evals-guide/example-protocol