Category: Prompt Engineering

• Large Models Reveal New Weakness! Old Memories Unforgettable, New Memories Indistinguishable, Accuracy Plummets | ICML'25
• Anthropic Reveals Multi-Agent System Details: Claude Replicates Human Collective Intelligence, Outperforms Single Opus by 90%!
• AI Can Read Between the Prompts! Vibe Coding: Regular User vs. Programmer – Cambridge's Latest Report
• Multi-Agent Systems Are "Burning" Tokens! Everything Anthropic Has Discovered
• Google Research Finds: Prompt Design is the Core of Multi-Agent Systems!
• HALO, a Hierarchical Dynamic Prompting Framework Based on MCTS, Enabling Agents to Always Find the Optimal Path | Latest