InCoder-32B-Thinking: Advanced Industrial Code Model
Discover InCoder-32B-Thinking, an industrial code model using error-driven reasoning to optimize chip design, GPU, and embedded systems development.
AI-Driven Unit Test Writing and Code Refactoring Case Study
Explore how AI accelerates unit test writing and enables safe, test-driven code refactoring to improve software quality and maintainability.
Comprehensive Security Analysis of OpenClaw AI Agents
Explore a detailed security evaluation of OpenClaw and its variants, revealing key vulnerabilities and risks in AI agent frameworks.
Domain-Adapted Retrieval Boosts Pedagogical Dialogue Annotation
Improve automated pedagogical dialogue annotation with domain-adapted retrieval, enhancing accuracy without fine-tuning generative models.
Kimi K2.5 Safety Evaluation: Risks & Findings
Explore the independent safety evaluation of Kimi K2.5, highlighting risks like CBRNE misuse, cybersecurity, bias, and political censorship.