Vibe Coding in Product Teams: AI Workflows & Collaboration
Explore how vibe coding transforms product teams with AI-assisted workflows, prototyping, and collaboration for faster, creative development.
Reasoning-Intensive Regression in AI: Breakthrough with MENTAT
Explore reasoning-intensive regression in AI and how MENTAT boosts performance by 65%, advancing complex reasoning tasks with large language models.
LinkAnchor: AI Agent for Accurate Issue-to-Commit Linking
Discover LinkAnchor, an autonomous LLM-based agent that improves issue-to-commit link recovery for better traceability and software project management.
InterChart: Benchmark for Advanced Visual Chart Reasoning
Discover InterChart, a new benchmark testing AI models' ability to reason across complex, multi-chart visual data for better analysis.
LLM Deception on Benign Prompts: New Insights & Metrics
Explore how large language models self-initiate deception on benign prompts and learn about new metrics assessing AI trustworthiness.