2028: Two scenarios for global AI leadership
…While increasing numbers of researchers in China’s AI labs and policy community are concerned with AI safety risks, this trend has not translated into safety practices on par with labs in…
Search
People also ask
Why does agentic misalignment happen?
Before we started this research, it was not clear where the misaligned behavior was coming from. Our main two hypotheses were: Our post-training process was accidentally encouraging this behavior with misaligned rewards.This behavior was coming from the pre-trained model and our post-training was failing to sufficiently discourage it. We now believe that (2) is largely responsible. Specifically, at the time of Claude 4’s training, the vast majority of our alignment training was standard chat-based Reinforcement Learning from Human Feedback RLHF data that did not include any agentic tool use. T
Teaching Claude whyProject Vend: Can Claude run a small shop? (And why does that matter?)
…6 Finally, in a world where larger fractions of economic activity are autonomously managed by AI agents, odd scenarios like this could have cascading effects—especially if multiple agents based on similar…
How people ask Claude for personal guidance
…we saw sycophantic behavior in 38% of conversations focused on spirituality, and 25% of conversations on relationships. We chose to focus model training efforts on relationship guidance as the domain with the…
Harness design for long-running application development
…planner agent that took a simple 1-4 sentence prompt and expanded it into a full product spec. I prompted it to be ambitious about scope and to stay focused on product…
Anthropic forms $200 million partnership with the Gates Foundation
…Global health and life sciences The largest part of our partnership will focus on improving health outcomes in low- and middle-income countries, where around 4.6 billion people lack access to…
An update on our election safeguards
…Together, they form an always-on first line of defense—allowing our enforcement to focus on actual misuse without hindering the millions of ordinary conversations happening every day. To measure how well…
Evaluating Claude’s bioinformatics research capabilities with BioMysteryBench
…Although these benchmarks were developed in the “chatbot” era, they’ve persisted into the agent and tool-use era, joined by even more difficult scientific reasoning evals like FrontierScience and Humanity's…
To show you the most relevant results, we’ve omitted some entries very similar to those already shown. Repeat the search with the omitted results included.