Workflow
Anthropic
icon
Search documents
X @Anthropic
Anthropic· 2025-11-04 23:09
Agent Efficiency - Anthropic Engineering blog provides tips on building more efficient agents [1] - The tips focus on handling more tools while using fewer tokens [1] Technology & Protocol - Introduction of Code execution with the Model Context Protocol (MCP) [1]
X @Anthropic
Anthropic· 2025-11-04 16:52
Even when new AI models bring clear improvements in capabilities, deprecating the older generations comes with downsides.An update on how we’re thinking about these costs, and some of the early steps we’re taking to mitigate them: https://t.co/VCTMW0d2e8 ...
X @Anthropic
Anthropic· 2025-11-04 07:38
We're announcing a partnership with Iceland's Ministry of Education and Children to bring Claude to teachers across the nation.It's one of the world's first comprehensive national AI education pilots: https://t.co/BC0Ziw27r8 ...
X @Anthropic
Anthropic· 2025-11-04 00:32
For more of Anthropic’s alignment research, see our Alignment Science blog: https://t.co/0UHuZdvWd9 ...
X @Anthropic
Anthropic· 2025-11-04 00:32
Reasoning Performance of LLMs - LLMs' reasoning performance significantly reduces when reasoning is obfuscated using simple ciphers [1] - LLMs struggle to reason accurately in ciphered text, except for simple ciphers [1] Ciphered Language Processing - LLMs can easily decode ciphered text to English [1] - Research involved testing 10 LLMs across 28 ciphers [1]
X @Anthropic
Anthropic· 2025-11-04 00:32
AI Safety Research - The Anthropic Fellows program funds and mentors a small group of AI safety researchers [1] - Anthropic Fellows recently released four papers [1]
X @Anthropic
Anthropic· 2025-10-29 17:18
The full paper is available here: https://t.co/N7erwdYyDwWe're hiring researchers and engineers to investigate AI cognition and interpretability: https://t.co/xPPi2wre1f ...
X @Anthropic
Anthropic· 2025-10-29 17:18
Our blog post on these results is here: https://t.co/9ZoVJFovJr ...
X @Anthropic
Anthropic· 2025-10-29 17:18
New Anthropic research: Signs of introspection in LLMs.Can language models recognize their own internal thoughts? Or do they just make up plausible answers when asked about them? We found evidence for genuine—though limited—introspective capabilities in Claude. https://t.co/4FCfkG9WVT ...
X @Anthropic
Anthropic· 2025-10-29 14:29
We're also deepening our commitment to Japan's creative community through an extended partnership with @mori_art_museum, supporting the upcoming Roppongi Crossing 2025 exhibition and future programs exploring technology and art.Read more here: https://t.co/dwvxO3fZCV ...