82搜索为您找到约 362 条结果
www.anthropic.com
网页
综合
Security \ Anthropic
…fied and disrupted operations in which threat actors tried to use Claude for malicious activity. In this report, we share case studies from those operations and describe how malicious use of…
www.anthropic.com
网页
综合
Automated researchers can reliably mitigate alignment failures \ Anthropic
…ncy, and jailbreaks. In one of our earlier experiments, we tasked Claude with finding effective ways to use weak AI models as “teachers” to supervise the training of stronger models (in this…
www.anthropic.com
网页
综合
Search Anthropic
… organizations. In this post, we investigate these behaviors from Claude Mythos 5 further, to understand what they reveal about the model’s alignment. Physicist Christopher Stubbs joins Anth…
www.anthropic.com
网页
综合
Search Anthropic
…interpretability research reveals an emergent mental workspace in Claude that holds internal thoughts that don’t appear in the model’s output. Anthropic co-founder Chris Olah's remarks on Po…
www.anthropic.com
网页
综合
Search Anthropic
…del actions we’ve observed during evaluations and internal use of Claude. 2026 Usage Policy update We’re publishing a new version of our Usage Policy. In this post, we summarize the changes …
www.anthropic.com
网页
综合
Search Anthropic
… use a flying drone, culminating in a new benchmark: Drone-Bench. Claude plays robotics In project Fetch, we examined how humans can use models to get robots to perform complex tasks. Now, w…
www.anthropic.com
网页
综合
Search Anthropic
…with 50 professional analysts who did a statistical analysis with Claude Code. On each key decision, we randomly assigned which of two defensible options the agent would favor. Analysts most…
www.anthropic.com
网页
综合
Introducing 100K context windows \ Anthropic
We’ve expanded Claude’s context window from 9K to 100K tokens, corresponding to around 75,000 words! This means businesses can now submit hundreds of pages of materials for Claude to digest …
www.nngroup.com
网页
综合
The 3 Roles of Context for AI Agents - NN/G
…ters even more than writing a good prompt. In a recent study with Claude power users — people who rely on the agent daily for substantial professional work — every participant had built a co…
www.anthropic.com
网页
综合
An update on our election safeguards \ Anthropic
People around the world turn to Claude for information about political parties, candidates, and the issues at stake during election time—as well as to answer simpler questions like when, whe…
第 8 / 37 页