How AI Is Transforming Work at Anthropic
…Related content Making Claude a chemist Coding agents in the social sciences Results from a survey of 1,260 social scientists about AI and coding agent use. Project Glasswing: An initial update…
Search
Related topics:
Claude
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 Glasswing: An initial update
…Teaching Claude why New research on how we've reduced agentic misalignment. Natural Language Autoencoders: Turning Claude’s thoughts into text AI models like Claude talk in words but think in numbers…
From shortcuts to sabotage: natural emergent misalignment from reward hacking
…Claude a chemist Coding agents in the social sciences Results from a survey of 1,260 social scientists about AI and coding agent use. Project Glasswing: An initial update An early update…
Measuring LLMs' impact on N-day exploits
…Related content Agentic coding and persistent returns to expertise Paving the way for agents in biology Making Claude a chemist
Estimating AI productivity gains
…Related content Making Claude a chemist Coding agents in the social sciences Results from a survey of 1,260 social scientists about AI and coding agent use. Project Glasswing: An initial update…
LLMs and biorisk
…Benchling is using Claude to help researchers structure data, ask better questions, generate insights faster, and spend more time on science. Biomni is using Claude to speed up bioinformatics analysis and even…
Emergent introspective awareness in large language models
…Related content Making Claude a chemist Coding agents in the social sciences Results from a survey of 1,260 social scientists about AI and coding agent use. Project Glasswing: An initial update…
Anthropic Economic Index report: Learning curves
…Claude Code’s agentic architecture splits coding work into smaller API calls, which are labeled as distinct tasks. So while coding’s overall share of API traffic has grown, it is spread…
Assessing Claude Mythos Preview’s cybersecurity capabilities
…In order to increase the diversity of bugs we find—and to allow us to invoke many copies of Claude in parallel—we ask each agent to focus on a different file…
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.