Boggle Nogs
Building Effective "Agents"
(
anthropic.com
)
763 points
121 comments
Alignment Faking in LLMs [pdf]
(
anthropic.com
)
2 points
1 comment
Building Effective Agents \ Anthropic
(
anthropic.com
)
3 points
2 comments
Building Effective Agents
(
anthropic.com
)
9 points
Alignment faking in large language models
(
anthropic.com
)
302 points
353 comments
Alignment faking in large language models
(
anthropic.com
)
14 points
Anthropic Twitter Account Hacked
(
anthropic.com
)
3 points
The Claude in Amazon Bedrock Course – By Anthropic
(
anthropic.com
)
2 points
Clio: A system for privacy-preserving insights into real-world AI use
(
anthropic.com
)
133 points
40 comments
A Toy Evaluation of Inference Code Tampering
(
anthropic.com
)
2 points
Claude 3.5 Haiku on AWS Trainium2 and Model Distillation in Amazon Bedrock
(
anthropic.com
)
2 points
Graphite speeds up code review by 40x with Claude
(
anthropic.com
)
4 points
1 comment
Tailor Claude's responses to your personal style
(
anthropic.com
)
1 point
Tailor Claude's responses to your personal style
(
anthropic.com
)
4 points
Claude Prompt Improver
(
anthropic.com
)
3 points
1 comment
Model Context Protocol
(
anthropic.com
)
872 points
258 comments
A statistical approach to model evaluations
(
anthropic.com
)
2 points
A statistical approach to model evaluations
(
anthropic.com
)
66 points
49 comments
Claude.ai: Introducing Google Docs in Chats and Projects
(
anthropic.com
)
3 points
1 comment
Powering the next generation of AI development with AWS
(
anthropic.com
)
5 points
A statistical approach to model evaluations
(
anthropic.com
)
4 points
Improve your prompts in the developer console
(
anthropic.com
)
1 point
Claude 3.5 Haiku
(
anthropic.com
)
2 points
Claude 3.5 Haiku Released
(
anthropic.com
)
18 points
4 comments
PDF Support (Beta) – Anthropic
(
anthropic.com
)
1 point
The Analysis Tool in Claude.ai
(
anthropic.com
)
9 points
Anthropic calls Government to regulate AI in the next eighteen months
(
anthropic.com
)
5 points
4 comments
Anthropic: The case for targeted AI regulation
(
anthropic.com
)
2 points
Raising the bar on SWE-bench Verified with Claude 3.5 Sonnet
(
anthropic.com
)
1 point
Raising the bar on SWE-bench Verified with Claude 3.5 Sonnet
(
anthropic.com
)
3 points
more