x.com
Open in
urlscan Pro
104.244.42.129
Public Scan
Submitted URL: https://x.com/anthropicai?campaignId=11453111&source=i_email&medium=email&content=Oct2024Sonnet&messageTypeId=...
Effective URL: https://x.com/anthropicai?campaignId=11453111&source=i_email&medium=email&content=Oct2024Sonnet&messageTypeId=...
Submission: On October 26 via manual from IN — Scanned from US
Effective URL: https://x.com/anthropicai?campaignId=11453111&source=i_email&medium=email&content=Oct2024Sonnet&messageTypeId=...
Submission: On October 26 via manual from IN — Scanned from US
Form analysis
0 forms found in the DOMText Content
JAVASCRIPT IS NOT AVAILABLE. We’ve detected that JavaScript is disabled in this browser. Please enable JavaScript or switch to a supported browser to continue using x.com. You can see a list of supported browsers in our Help Center. Help Center Terms of Service Privacy Policy Cookie Policy Imprint Ads info © 2024 X Corp. Don’t miss what’s happening People on X are the first to know. Log in Sign up Welcome to x.com! We are letting you know that we are changing our URL, but your privacy and data protection settings remain the same. For more details, see our Privacy Policy: https://x.com/en/privacy Settings ANTHROPIC 671 posts See new posts Follow Click to Follow AnthropicAI Anthropic @AnthropicAI We're an AI safety and research company that builds reliable, interpretable, and steerable AI systems. Talk to our AI assistant Claude at http://Claude.ai. anthropic.comJoined January 2021 33 Following 371.5K Followers Posts Replies Highlights Media ANTHROPIC’S POSTS Pinned Anthropic @AnthropicAI · Oct 22 Introducing an upgraded Claude 3.5 Sonnet, and a new model, Claude 3.5 Haiku. We’re also introducing a new capability in beta: computer use. Developers can now direct Claude to use computers the way people do—by looking at a screen, moving a cursor, clicking, and typing text. 488 3.1K 10K 3.3M Anthropic @AnthropicAI · 20h Over the past few months, our Interpretability team has put out a number of smaller research updates. Here’s a thread of some of the things we've been up to: 13 131 1.2K 135K Show more replies Anthropic @AnthropicAI · 20h We also report on reproducing Kharlapenko et al.'s "self explaining sparse autoencoder" features experiments: https://transformer-circuits.pub/2024/august-update/index.html#self-explaining-sae… 1 1 69 17K Anthropic @AnthropicAI · 20h And finally, you might have seen our collaboration with Anthropic’s Societal Impacts team on Feature Steering, also published today: Quote Anthropic @AnthropicAI · Oct 25 New Anthropic research: Evaluating feature steering. In May, we released Golden Gate Claude: an AI fixated on the Golden Gate Bridge due to our use of “feature steering”. We've now done a deeper study on the effects of feature steering. Read the post: http://anthropic.com/research/evaluating-feature-steering… Show more 2 4 90 27K Anthropic @AnthropicAI · Oct 25 New Anthropic research: Evaluating feature steering. In May, we released Golden Gate Claude: an AI fixated on the Golden Gate Bridge due to our use of “feature steering”. We've now done a deeper study on the effects of feature steering. Read the post: http://anthropic.com/research/evaluating-feature-steering… 22 185 1.1K 132K Show more replies Anthropic @AnthropicAI · Oct 25 Finally, we discovered a feature that significantly reduces bias scores across nine social dimensions within the sweet spot. This did come with a slight capability drop, which highlights potential trade-offs in feature steering. 4 15 145 48K Anthropic @AnthropicAI · Oct 25 We hope our preliminary findings inspire further research on steering methods for safer, more reliable model outputs. Read the full research blog for detailed results, insights, and limitations: "Evaluating feature steering: A case study in mitigating social biases" From anthropic.com 5 4 94 15K Anthropic @AnthropicAI · Oct 24 Claude can now write and run code. We've added a new analysis tool. The tool helps Claude respond with mathematically precise and reproducible answers. You can then create interactive data visualizations with Artifacts. Enable the feature preview: https://claude.ai/new?fp=1. 171 945 4.6K 515K NEW TO X? Sign up now to get your own personalized timeline! Sign up with Apple Create account By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use. YOU MIGHT LIKE * Sam Altman @sama Follow Click to Follow sama * Geoffrey Hinton @geoffreyhinton Follow Click to Follow geoffreyhinton * Hugging Face @huggingface Follow Click to Follow huggingface Show more Something went wrong. Try reloading. Retry Terms of ServicePrivacy PolicyCookie PolicyAccessibilityAds info More © 2024 X Corp.