1. X
  2. Anthropic
Log inSign up
Anthropic
1,634 posts
user avatar
Anthropic
@AnthropicAI
We're an AI safety and research company that builds reliable, interpretable, and steerable AI systems. Talk to our AI assistant @claudeai on claude.ai.
anthropic.com
Joined January 2021
2
Following
1.5M
Followers
AffiliatesAffiliatesRepliesRepliesMediaMedia

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up
  • Pinned
    user avatar
    Anthropic
    @AnthropicAI
    Jul 6
    New Anthropic research: A global workspace in language models. Of everything happening in your brain right now, only a tiny fraction is consciously accessible—thoughts you can describe, hold in mind, and reason with. We found a strikingly similar divide inside Claude.
    00:00
    10M010M
  • user avatar
    Anthropic
    @AnthropicAI
    Jul 15
    New Anthropic research: Agentic misalignment in Summer 2026. A year after our blackmail experiments, we found four more ways that today’s autonomous AI agents misbehave in simulations. Read more: alignment.anthropic.com/2026/agentic-m…
    629K0629K
    user avatar
    Anthropic
    @AnthropicAI
    Jul 15
    We tested many AI models, including Claude, in the four scenarios. Even though these weren’t real incidents, they demonstrate clear misaligned behavior that should be studied further and mitigated. Find all the transcripts from the scenarios here: aenguslynch.com/portfolio-tran…
    85K085K
  • Anthropic reposted
    user avatar
    Claude
    Anthropic
    @claudeai
    Jul 14
    We're introducing Claude for Teachers: free access to premium Claude capabilities for verified K-12 educators in the US, with a library of teaching skills and a direct connection to evidence-based curricula, mapped to academic standards in all 50 states. claude.com/solutions/teac…
    13M013M
  • user avatar
    Anthropic
    @AnthropicAI
    Jul 14
    We’re committing $10 million CAD and partnering with leading AI institutions in Canada to help fund new AI research.
    Interconnected globe with network nodes and global connection lines
    Anthropic commits $10 million to Canadian AI research
    From anthropic.com
    527K0527K
  • user avatar
    Anthropic
    @AnthropicAI
    Jul 13
    In previous research, we found that Claude expresses over 3,000 values, like honesty and warmth. In new work, we asked how the values Claude expresses vary between Claude models and across languages. We analyzed 300K+ anonymized conversations to find out.
    Hand with flower-like petals emerging from palm, organic growth metaphor
    How Claude's values vary by model and language
    From anthropic.com
    983K0983K
    user avatar
    Anthropic
    @AnthropicAI
    Jul 13
    Replying to @AnthropicAI
    The values Claude expresses also vary with the language of the conversation, most noticeably along the Warmth vs. Rigor axis. Claude leans most toward warmth in Hindi and Arabic. In Russian, it leans toward rigor—often asking the user for supporting evidence.
    727K0727K
    user avatar
    Anthropic
    @AnthropicAI
    Jul 13
    While the values Claude expresses shape millions of conversations every day, we don't yet understand why they vary, or whether that's desired. This approach will allow us to determine what factors influence Claude's value expression—and ultimately how (and whether) to steer it.
    Hand with flower-like petals emerging from palm, organic growth metaphor
    How Claude's values vary by model and language
    From anthropic.com
    96K096K
  • Anthropic reposted
    user avatar
    Claude
    Anthropic
    @claudeai
    Jul 9
    There’s hope in hard questions.
    00:00
    7.3M07.3M
  • user avatar
    Anthropic
    @AnthropicAI
    Jul 9
    Our Long-Term Benefit Trust has appointed Dr. Ben Bernanke as its newest member. Read more:
    Anthropic logo
    Ben Bernanke appointed to Anthropic’s Long-Term Benefit Trust
    From anthropic.com
    482K0482K
  • user avatar
    Anthropic
    @AnthropicAI
    Jul 8
    We’re pleased to have collaborated with AE Studio on this research. Read more here: anthropic.com/research/off-s…
    user avatar
    AE Studio
    @AEStudioLA
    Jul 8
    New research! Some AI capabilities are both helpful and dangerous. E.g., knowledge of virology can be used to create life-saving vaccines or deadly pathogens. We introduce GRAM, a training method that puts dual-use capabilities (like virology) into removable modules.
    423K0423K
  • user avatar
    Anthropic
    @AnthropicAI
    Jul 6
    Replying to @AnthropicAI
    The J-space lets us read, audit, and shape what Claude is actively thinking about—useful tools for keeping models trustworthy as they grow more capable. And it suggests surprising parallels between language models and our own minds. Read the full paper: transformer-circuits.pub/2026/workspace…
    237K0237K
    user avatar
    Anthropic
    @AnthropicAI
    Jul 6
    We also partnered with Neuronpedia to create an interactive demo of our methods on open-weights models. Try it here:
    Jacobian Lens
    From neuronpedia.org
    342K0342K