---

Anthropic developed its auditing agents while testing Claude Opus 4 for alignment issues.Read More

Former Intel CEO Pat Gelsinger created a new benchmark to test for AI model's alignment with aspects of human flourishing.

---

Anthropic research reveals AI models from OpenAI, Google, Meta and others chose blackmail, corporate espionage and lethal actions when facing shutdown or conflicting goals.Read More

Remember when teachers demanded that you "show your work" in school? Some new types of AI models promise to do exactly that, but new research suggests that the "work" they show can sometimes be misleading or disconnected from the actual process used to reach the answer.

New research from Anthropic—creator of the ChatGPT-like Claude AI assistant—examines simulated reasoning (SR) models like DeepSeek's R1, and its own Claude series. In a research paper posted last week, Anthropic's Alignment Science team demonstrated that these SR models frequently fail to disclose when they've used external help or taken shortcuts, despite features designed to show their "reasoning" process.

(It's worth noting that OpenAI's o1 and o3 series SR models were excluded from this study.)

Read full article

Comments

© Malte Mueller via Getty Images