Anthropic
1120
101
GEPA-Curator: Curated Learning for Self Improving Agents
Large Language Models (LLMs) are increasingly used in multi-turn agentic workloads that require sustained interaction with complex environments. Existing reflective prompt optimizers such as GEPA learn from failed rollouts, but agentic failures can also come from prompt weaknesses, harness limitations, stochastic execution, or noisy judges. We argue that such failures may not provide useful learning signal, and may even be harmful; and thus it is essential to curate which tasks are provided to the prompt optimizer for better performance. We introduce GEPA-Curator, a framework that augments the prompt optimizer to select which agent experiences should shape prompt optimization. In particular, GEPA-Curator consists of two components: task curation, which filters out tasks that are likely to provide noisy or unreliable learning signals, and prior success retrieval, which selectively retrieves past successful trajectories for a task and provides them as additional context to the prompt optimizer. We evaluate GEPA-Curator on GoBrowse, ALFWorld, AppWorld, and τ-bench, using both Gemini 3.1 Pro and Claude Opus 5 as optimizer models. GEPA-Curator matches or exceeds the mean performance of both baselines, with gains of up to 20.7% over GEPA and 21.2% over ACE.
Anthropic’s elaborate plan to keep Wall Street at bay
Anthropic wants to have it both ways. With its impending IPO, it wants to tap the vast riches of the public markets and insists it…
Exowatt beats frontier models on accuracy with SageMaker serverless model customization
In this post, we show how Exowatt used Amazon SageMaker AI serverless model customization to build a repeatable AI pipeline that produces task-specific fine-tuned models for two deployment targets, edge and cloud, achieving higher accuracy than frontier models at up to 49x lower cost.
Data center backlash is uniting America
If there's one issue that seems to activate all kinds of voters in 2026, it's data centers. The rapid buildout of these massive server storage…
Expanding our partnership with GSA to bring Claude to all levels of government
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
Anthropic is burning gas to feed the AI boom
As it prepares to go public, Anthropic's S-1 filing makes generative AI's methane dependency glaringly obvious. "Competition for access to electrical supply and data center…
Build agentic retrieval on a Managed Amazon Bedrock Knowledge Base with CDK
Build enterprise agentic retrieval on a Managed Amazon Bedrock Knowledge Base with the AWS CDK: an agent that routes across two knowledge bases, retrieves through the AgentCore Gateway, and returns grounded, cited answers, with seven layers of observability and both on-demand and continuous evaluation, all deployed as a single CDK application.
Five weird details from Anthropic’s IPO filing
Anthropic has finally filed its S-1 prospectus with the SEC, a document designed to give investors a look under the hood of its business, from…
SEMA-Auto: Sighted and Efficient Multi-Turn Attack with Autonomy
Existing jailbreak attackers fall into two classes: static planners fix their single- or multi-turn adversarial plans in advance, remaining simple but losing sight of the victim's replies, wasting turns and limiting transferability; interactive generators read each victim reply to generate the next-turn attack but require in-loop evaluators for success signals or hints, incurring substantial costs and inflated performance. Bridging this gap, we propose SEMA-Auto, a sighted and efficient multi-turn attacker with autonomy, interacting with the victim model and terminating the session by itself upon success. To stabilize its behaviors and boost its capabilities, SEMA-Auto is trained in two stages. Synthetic bootstrap tuning installs the notion of attack targets and conforming decisions by fine-tuning the base model with bootstrapped trajectories. Decision-supervised reinforcement learning then optimizes two objectives jointly yet separately, reinforcing the attack with higher jailbreak reward while supervising the decision at each turn against an absolute target. Our method achieves state-of-the-art (SOTA) attack success rates (ASR) across multiple datasets, victims, and judges, outperforming all static and interactive baselines, within almost the fewest turns, demonstrating both effectiveness and efficiency. For example, SEMA-Auto performs a 76.0\% ASR@1 within an average of 3.0 turns against DeepSeek-V4-Flash on AdvBench, while the best static baseline is 54.8\% with fixed 7 turns and the best interactive baseline is 43.8\% in 3.7 turns. Against safety-hardened frontier models, GPT-oss-120B, GPT-5.4, Claude-Haiku-4.5, and GPT-6-Astra, our counter-trained attacker achieves an average 59.6\% ASR@1 on HarmBench, 13.8\% over prior SOTA. Our code is available at: https://github.com/microsoft/SEMA
Anthropic’s IPO filing reveals its strategy for keeping enterprise customers hooked
Anthropic’s S-1 shows more than half of its $100,000-plus customers now use both the Claude Platform and a first-party app, a cross-selling playbook reminiscent of…