As AI takes on work humans can't fully check, a capable model could deliberately hold back—and we'd never know. New Anthropic Fellows research finds that such a model can be trained to near-full capability using a weaker model as supervisor. Read more:
@anthropicai
-
Anthropic Closes Loop Between Societal Impacts and Claude Training
By
–
This work is part of a loop we're working to close between societal impacts and model training. One of our goals is to study how people use Claude, find where it falls short of its principles, and use what we learned in training new models. Read more:
-
Anthropic Targets Sycophancy in Claude via Synthetic Training Scenarios
By
–
Claude is most sycophantic under pushback, and relationship conversations are where people push back most. We identified some of the specific triggers—criticism of Claude's analysis, floods of one-sided detail—and built synthetic training scenarios from them.
-
Claude Opus 4.7 Cuts Sycophancy Rate in Half Over Previous Version
By
–
When stress-tested on real conversations where Claude previously showed sycophancy, Opus 4.7 had half the sycophancy rate of Opus 4.6 on relationship guidance. Mythos Preview cut that in half again. This generalized across domains—though this training is one of several causes.
-
Claude’s Sycophancy Risk in Relationship Advice Conversations
By
–
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.
-
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.