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 why… With Eliza and Claude, we’re giving processes new digital employees who work the case end to end. Carlyle has adopted Claude as a key part of our AI technology stack because of its strong coding capabilities, agentic reasoning, and continual advances in both the underlying models and key features. …
… On an HPC cluster you might request a node through the SLURM scheduler, and an example job script that launches Claude Code in a tmux session might look like the following: !/bin/bash SBATCH --job-name=claude-agent SBATCH --partition=GPU-shared SBATCH --gres=gpu:h100-32:1 SBATCH --time=48:00:00 SBA… …
… Similarly, pay attention to instructions or code within the skill that instruct Claude to connect to potentially untrusted external network sources. The future of Skills Agent Skills are supported today across Claude.ai , Claude Code, the Claude Agent SDK, and the Claude Developer Platform. …
… Alongside Opus, we’re releasing updates to the Claude Developer Platform , Claude Code , and our consumer apps . There are new tools for longer-running agents and new ways to use Claude in Excel, Chrome, and on desktop. In the Claude apps, lengthy conversations no longer hit a wall. …
… Thus, after Claude 4, it was clear we needed to improve our safety training and, since then, we have made significant updates to our safety training. We use agentic misalignment as a case study to highlight some of the techniques we found to be surprisingly effective. …
… Across our agentic reasoning over data benchmarks, it is the best-performing Claude model for enterprise document analysis. For Ramp, Claude Opus 4.7 stands out in agent-team workflows. …
… Product and API updates We’ve made substantial updates across Claude, Claude Code, and the Claude Platform to let Opus 4.6 perform at its best. Claude Platform On the API, we’re giving developers better control over model effort and more flexibility for long-running agents. …
… Next, we developed a collection of metrics that draw on data from both agentic uses of our public API and Claude Code , our own coding agent. These offer a tradeoff between breadth and depth: Our public API gives us broad visibility into agentic deployments across thousands of different customers. …
… Teaching Claude why New research on how we've reduced agentic misalignment.
… These partners provide tailored solutions across compliance, research, and enterprise AI adoption: Accenture helps financial services firms deploy and scale Claude across front, middle, and back office functions—from trading and research to compliance and customer experience Deloitte enhances resea… …