Anthropic details "persona vectors", patterns of activity within an AI model's neural network that control its character traits, such as evil and sycophancy (Anthropic)

https://www.techmeme.com/feed.xml Hits: 8
Summary

About This Page This is a Techmeme archive page. It shows how the site appeared at 10:10 PM ET, August 1, 2025. The most current version of the site as always is available at our home page. To view an earlier snapshot click here and then modify the date indicated.

First seen: 2025-08-02 02:12

Last seen: 2025-08-02 09:13

Read Full Article More from this Source
Related News
Anthropic revoked OpenAI's API access to Claude, citing ToS violations; sources: OpenAI's use of the API let it compare its models' behavior against Claude's (Kylie Robison/Wired)
2025-08-01 · 11 hits
Roblox's average DAUs grew 41% YoY to 111.8M in Q2 and hours engaged rose 58% YoY to 27.4B, driven by the success of tycoon-style farming game Grow a Garden (Zaheer Kachwala/Reuters)
2025-08-02 · 6 hits
Sources: in a rare companywide meeting, Tim Cook said the AI revolution is "ours to grab", Apple's AI efforts will mirror its iPhone successes, and more (Mark Gurman/Bloomberg)
2025-08-01 · 12 hits
Meta, Alphabet, Microsoft, and Amazon have collectively spent ~$90B on capex in their most recent quarters and are expected to spend over $344B for the year (Bloomberg)
2025-08-01 · 13 hits
Subzero Labs, which is building Rialo, a blockchain designed for non-crypto developers to build "real-world" apps, raised a $20M seed led by Pantera Capital (Ben Weiss/Fortune)
2025-08-02 · 10 hits