#LLM
Too Good to Be Bad: Study Shows Why AI Struggles to Convincingly Roleplay Villains
Researchers from Tencent and Sun Yat-sen University have found that built-in safety mechanisms prevent large language models from effectively roleplaying negative characters, replacing subtle manipulation with generic aggression.
GLM-5 Released: Zhipu AI's Open Model Reaches Top-Tier Performance in Agentic Coding
Zhipu AI and Tsinghua University have introduced GLM-5, a powerful open MoE model with 744 billion parameters capable of autonomously writing code, conducting deep web search, and tackling complex multi-step tasks on par with proprietary flagships.
ClawBench Benchmark Exposes AI Agent Weaknesses: Top Real-Web Success Rate Reaches Just 33%
The new ClawBench benchmark evaluated autonomous web agents on live websites. The best-performing model successfully completed only one-third of the practical tasks.
Anthropic Releases Claude Sonnet 5: Focus on Autonomous Agents, Coding, and Hidden Costs
Anthropic has introduced Claude Sonnet 5, a new language model optimized for multi-step autonomous workflows and coding. Despite attractive base pricing, reasoning patterns and a redesigned tokenizer may make real-world usage more expensive than expected.
The Race for a Personal AI Companion: Strategies of OpenAI, Apple, Yandex, and Meta
Tech giants are moving from isolated chatbots to end-to-end personal AI assistants. We explore how wearables are evolving and why user digital memory will become the ultimate asset in this battle.