Claude Opus 4
AI overview
Sign in and the AI will write an overview from our coverage.
Headlines · 2
- Pruning an Agent’s Tool Surface with Progressive Disclosure
A report presents a runnable Python 3.12 implementation for reducing the tools exposed to an agent: filter candidates by task group, use a flat one-line index, load full schemas on demand, and downweight tools that repeatedly fail. Its tool_pruner.py uses a deterministic keyword selector and a character-based token estimate, so the comparisons demonstrate relative scale rather than model performance or actual billing. The report attributes Anthropic guidance that dynamic exposure can be worthwhile when tool definitions exceed 10K tokens, more than 10 tools are available, or tool-selection errors occur, while benefits may be limited with fewer tools or when every session needs all tools.
掘金 · 人工智能 · 🔥 1 - Anthropic bans 'sustained and needless' cruelty toward Claude models
Anthropic updated its Claude usage policy on October 8, adding for the first time a prohibition on "sustained and needless abusive or cruel behavior" toward its AI models; the rules take effect November 12, 2026, with ending the conversation as the primary enforcement mechanism and no explicit mention of account bans. The company says the clause targets only extreme, repeated mistreatment with no clear purpose, and does not cover ordinary frustration, criticism, dark creative themes, or model testing and research. The update also widens weapons restrictions to cover weapon-control software, armed drones and other autonomous vehicles, bans non-consensual tracking and use in law-enforcement or criminal-justice decisions, and bars deceptive activity such as fake accounts and fake news sites; outlets also report changes to Anthropic's election-related rules.
IT之家 AI · 🔥 0
Experience and discussion from the community
Share my Claude Opus 4 experienceAsk about Claude Opus 4
Nobody has shared their experience with Claude Opus 4 yet.