Anthropic introduces copyright indemnity and new Messages API beta
Anthropic updated its Commercial Terms of Service to include copyright indemnification, allowing customers to retain ownership of outputs and receive legal defense against infringement claims for authorized use. Simultaneously, Anthropic launched a beta Messages API with a structured message format replacing the older prompt-string approach, designed to reduce prompt construction errors and enable upcoming features like function calling. The new terms take effect January 1, 2024 for direct API customers and January 2 for Amazon Bedrock users.
Related guides (4)
Related events (8)
Anthropic Updates Usage Policy: Agentic Use, Cybersecurity, and Political Content
Anthropic has revised its Usage Policy effective September 15, 2025, with changes addressing agentic and cybersecurity risks, political content restrictions, law enforcement use clarity, and high-risk consumer-facing requirements. New sections explicitly prohibit malicious computer/network compromise activities while supporting legitimate security research, responding to the rapid expansion of agentic tools like Claude Code and Computer Use. The policy also narrows its previous blanket ban on political content to focus specifically on deceptive or voter-targeting uses, enabling legitimate civic and policy research. High-risk safeguards (human-in-the-loop, AI disclosure) are clarified to apply only to consumer-facing outputs, not B2B interactions.
Anthropic updates Usage Policy with election integrity, high-risk use case, and privacy rules
Anthropic revised its Acceptable Use Policy (renamed Usage Policy), effective June 6, 2024, consolidating prohibited-use categories into 'Universal Usage Standards.' Key changes include explicit bans on AI-assisted election interference and political campaigning, new safety requirements for high-risk use cases (healthcare, legal), expanded access for minors via API partners with safety disclosures, and stronger privacy protections including prohibitions on biometric inference and government-directed censorship. The update reflects both evolving regulatory context and Anthropic's stated safety mission.
Anthropic enables fine-tuning of Claude 3 Haiku via Amazon Bedrock
Anthropic announced that Claude 3 Haiku can now be fine-tuned through Amazon Bedrock using custom prompt-completion pairs, with general availability reached November 1, 2024. The capability targets specialized business workflows, with Anthropic citing a case study showing classification accuracy improvement from 81.5% to 99.6% and 85% token reduction on a content moderation task. Early enterprise adopters include SK Telecom and Thomson Reuters, both reporting measurable performance gains. Fine-tuning is available in the US West (Oregon) region with text support up to 32K context, with vision fine-tuning planned.
Anthropic introduces computer use capability, upgraded Claude 3.5 Sonnet, and Claude 3.5 Haiku
Anthropic announced three major developments: an upgraded Claude 3.5 Sonnet with significant coding improvements (SWE-bench Verified rising from 33.4% to 49.0%, surpassing all publicly available models including reasoning models), a new Claude 3.5 Haiku that matches Claude 3 Opus performance at Haiku-tier speed, and a public beta of 'computer use' — a capability allowing Claude to control computers by viewing screens, moving cursors, clicking, and typing. Computer use is available via the Anthropic API, Amazon Bedrock, and Google Cloud Vertex AI, with early adopters including Replit, The Browser Company, and Cognition. Both safety institutes (US AISI and UK AISI) conducted pre-deployment testing, and the model was assessed as remaining within ASL-2 under Anthropic's Responsible Scaling Policy.
Anthropic Commits Claude to Remaining Ad-Free, Citing Alignment and User Trust
Anthropic has published a policy statement declaring that Claude will not carry advertising, sponsored content, or third-party product placements in conversations. The company argues that ad-based incentives are structurally incompatible with Claude's constitution and the goal of acting unambiguously in users' interests, citing the sensitive and personal nature of many AI conversations. Anthropic's revenue model relies on enterprise contracts and paid subscriptions, and the post signals openness to agentic commerce features where Claude acts on a user's behalf rather than on behalf of advertisers. The company acknowledges other AI companies may reach different conclusions and commits to transparency if this policy changes.
Anthropic publishes framework for safe and trustworthy agent development
Anthropic released a formal framework for responsible agent development, articulating principles around human oversight, transparency, value alignment, and privacy for autonomous AI agents. The document draws on Claude Code as a reference implementation and cites enterprise deployments at Trellix and Block as real-world examples. The framework is positioned as a contribution to emerging industry standards for agentic AI systems, acknowledging open technical challenges in value alignment measurement and oversight calibration.
Anthropic launches Projects feature for Claude.ai Pro and Team users
Anthropic introduced Projects for Claude.ai Pro and Team subscribers, allowing users to organize chats with curated knowledge bases, custom instructions, and a 200K context window per project. The feature also includes Artifacts (a side-by-side content generation and preview pane) and team-level conversation sharing via activity feeds. Projects are powered by Claude 3.5 Sonnet and include a privacy commitment that shared data will not be used for model training without explicit consent.
Anthropic launches AI for Science program offering free API credits to researchers
Anthropic is launching an AI for Science program that provides free API credits to qualified researchers at academic institutions, with a focus on biology, life sciences, drug discovery, and agricultural productivity. Researchers are selected based on scientific contribution, potential impact, and AI's ability to accelerate their work. The initiative aligns with Dario Amodei's 'Machines of Loving Grace' vision and represents a structured philanthropic/access program rather than a technical release.