Claude Fable 5 and Claude Mythos 5
…risk posed by such dual-use capabilities. Our priority was to safely release Fable as soon as we could, even at the cost of overly broad safeguards. Therefore, for the time being…
Search
The Long-Term Benefit Trust
…Common examples of costs include pollution from factories, systemic financial risk from banks, and national security risks from weapons manufacturers. Examples of positive spillover effects include the societal benefits of education that…
Core views on AI safety: When, why, what, and how
…At the same time, it’s important to keep our eyes on the risks associated with the research itself. The research is unlikely to carry serious risks if it is being performed…
Trustworthy agents in practice
…But the autonomy that makes agents useful also introduces a range of new risks. Agents act with less human oversight, so there is more room for them to misread users’ intent and…
An update on our election safeguards
…appropriately 90% and 94% of the time. Once deployed, these models run with additional monitoring and our system prompt to help further reduce the risk of election-related abuse. Ahead of launching…
2028: Two scenarios for global AI leadership
…And since AI is advancing more quickly by the day, we have only a limited period of time to set the conditions of the competition—and determine whether and how those threats…
Next-generation Constitutional Classifiers: More efficient protection against universal jailbreaks
…Over time, we’ve implemented a variety of protections that have made our models much less likely to assist with dangerous user queries—in particular relating to the production of chemical, biological…
From shortcuts to sabotage: natural emergent misalignment from reward hacking
…natural emergent misalignment from reward hacking Nov 21, 2025 Read the paper In the latest research from Anthropic’s alignment team, we show for the first time that realistic AI training processes…
Introducing Claude Opus 4.7
…Last week we announced Project Glasswing , highlighting the risks—and benefits—of AI models for cybersecurity. We stated that we would keep Claude Mythos Preview’s release limited and test new cyber…
What 81,000 people told us about the economics of AI
…In some cases, AI has enabled them to start businesses, or given them time for more important things; in others, AI feels stifling, or imposed on them by their employers. The survey…