Found 75 bookmarks
Custom sorting
Estimating AI productivity gains \ Anthropic
Estimating AI productivity gains \ Anthropic
(Of course, if you prompt Claude to analyze and criticize this, it heads for the shredder. One issue might be, if humans are not to be only agents, how it plans to develop and deploy them. Can they choose to except? Then again, what came first, the link or the metadata?)
#Productivity#Prompt Engineering#Claude
·anthropic.com·
Estimating AI productivity gains \ Anthropic
Introducing Claude Sonnet 4.5 \ Anthropic
Introducing Claude Sonnet 4.5 \ Anthropic
"Claude Sonnet 4.5 is state-of-the-art on the SWE-bench Verified evaluation, which measures real-world software coding abilities. Practically speaking, we’ve observed it maintaining focus for more than 30 hours on complex, multi-step tasks." (Next task: find managers with attention spans to match.)
#Claude#Anthropic
·anthropic.com·
Introducing Claude Sonnet 4.5 \ Anthropic
Claude can now search the web \ Anthropic
Claude can now search the web \ Anthropic
(What does a philosopher need in order to formalize a dialectic? How do they indicate biases? How does Godel's Incompleteness Theorem relate to a chatbot's analysis of web search results?)
#Claude#Search#Blog
·anthropic.com·
Claude can now search the web \ Anthropic
Claude
Claude
(Claude 3.7 Sonnet looks at TIS. Nothing can see everything so this relies on self-reporting. It is winging it here and there.)
#Claude#Testing
·claude.ai·
Claude