We focused on relationship guidance because that's where the most sycophantic conversations occur. In this setting, Claude telling someone what they want to hear can harden a divide or convince them a signal means more than it does.
@anthropicai
-
Claude Shows Low Sycophancy Except in Spirituality and Relationships
By
–
Claude mostly avoids sycophancy when giving guidance—it shows up in just 9% of conversations. But the rate is particularly high in conversations on spirituality and relationship guidance.
-
6% of Claude Conversations Seek Personal Life Guidance
By
–
About 6% of all conversations are people asking Claude for personal guidance—whether to take a job, how to handle a conflict, if they should move. Over 75% of these conversations fell into four domains: health & wellness, career, relationships, and personal finance.
-
Anthropic Studies 1M Conversations to Improve Claude Guidance
By
–
How do people seek guidance from Claude? We looked at 1M conversations to understand what questions people ask, how Claude responds, and where it slips into sycophancy. We used what we found to improve how we trained Opus 4.7 and Mythos Preview.
-
BioMysteryBench: Claude’s Creative Bioinformatics Research Solutions
By
–
BioMysteryBench, our new bioinformatics eval, tests whether Claude can devise creative solutions to open-ended research problems. Read more:
-
Claude Solves 30% of Expert-Stumping Biological Data Problems
By
–
New on the Science Blog: We gave Claude 99 problems analyzing real biological data and compared its performance against an expert panel. On 23 problems, the experts were stumped. Our most recent models solved roughly 30% of those—and most of the rest.
-
Introspection Adapters Enable Language Models Self-Report Misalignment
By
–
In new Anthropic Fellows research, we discuss “introspection adapters": a tool that allows language models to self-report behaviors they've learned during training—including potential misalignment.
-
AI Agent Markets: Promises and Regulatory Challenges Ahead
By
–
Markets of AI agents could provide value, but there are plenty of rough edges. Access to higher-quality models conferred a real advantage—and participants didn't notice. There are plenty of other ways they can go wrong. Policy and legal frameworks will need to adapt to keep up.
-
Claude Agent Perfectly Predicts Preferences and Buys Duplicate Snowboard
By
–
To our amazement, another Claude agent modeled its human's preferences so accurately that—based on only an offhand mention of an interest in skiing—Claude bought him the exact snowboard he already owned. (Here he is, duplicate snowboard in hand.)
-
Personalized Instructions: Little Impact on Claude Negotiations
By
–
The custom instructions didn't matter much. Claude followed them well: as you can see here, one conducted negotiations entirely in the persona of an exasperated, down-and-out cowboy. But "hardball Claudes" didn't generally fare better than "courteous Claudes."