Eric Schmidt Launches AI-Focused Venture Capital Firm
Former Google CEO Eric Schmidt has launched a new venture capital firm focused on AI startups. The firm aims to invest in cutting-edge AI technologies and applications across various industries.
Archive
All 3,502 AI stories, newest first · page 136 of 146
ArcDeck: AI Framework Transforms Research Papers into Structured Slides
Researchers introduce ArcDeck, a multi-agent system that converts academic papers into slides by reconstructing their narrative flow. Unlike direct summarization tools, it preserves logical structure through discourse trees and iterative refinement.
Anthropic Co-Founder Reveals Briefings to Trump Admin on Mythos Amid Lawsuit
Anthropic co-founder Jack Clark confirmed the company briefed the Trump administration on its AI model Mythos, despite ongoing legal action against the U.S. government. The revelation highlights the complex relationship between AI firms and federal regulators.
AlphaEval: A New Framework for Evaluating AI Agents in Production
Researchers introduce AlphaEval, a methodology to assess AI agents in real-world scenarios. It addresses gaps in current benchmarks that fail to capture production complexities.
Allbirds Ditches Shoes, Stock Soars 430% After AI Pivot
Allbirds has sold its shoe business for $39 million and rebranded as NewBird AI. The move sent its stock up 430% in a single day as it shifts focus to AI infrastructure.
via @BullTheoryio on X#Investment
Adobe shifts to conversational AI editing with Firefly AI Assistant
Adobe introduces Firefly AI Assistant, allowing users to edit creations via natural language prompts. The company calls this a fundamental shift in creative workflows.
VibeDrift: Tracking Drift in AI-Generated Codebases
VibeDrift is a new tool designed to measure drift in AI-generated codebases. It helps developers monitor changes and maintain consistency in code produced by AI models.
Turing Test on Screen: Benchmarking Human-Like Mobile GUI Agents
Researchers introduce a new benchmark for evaluating the humanization of mobile GUI agents, framing the challenge as an optimization problem. This work highlights the need for agents to evade detection in human-centric digital ecosystems.
Soul.md: Open Format for AI Agent Identity
Soul.md is a new open format designed to give AI agents persistent identities. It aims to standardize how AI agents are identified and remembered across different platforms.
Self-Calibrating LLMs via Test-Time Discriminative Distillation
Researchers propose a method to improve the calibration of large language models (LLMs) without labeled data. The technique leverages the models' internal signals to reduce overconfidence in answers.
Researchers Propose Standardized Framework for AI Log Analysis
A new arXiv paper outlines a seven-step pipeline for analyzing AI system logs to assess capabilities and behaviors. The framework includes practical code examples and highlights common pitfalls.
Proactive AI Agents Reduce On-Call Support Burden with Continuous Learning
Researchers developed proactive AI agents that assist human support teams by learning from unresolved issues and improving continuously. This approach could significantly reduce the workload on human analysts in large-scale cloud service platforms.
Postiz Emerges as Low-Cost Open-Source Alternative to Social Media Scheduling Tools
Postiz, an open-source tool, challenges established social media management platforms with a fraction of the cost. It offers a comprehensive solution beyond basic scheduling, potentially disrupting the market.
OpenFlo: AI Agent Simulates Human Web Interaction for UX Evaluation
Researchers introduce OpenFlo, an AI agent that simulates human web interactions to evaluate usability. Unlike traditional tools, OpenFlo grounds actions and observations for coherent user journey tracing.
OpenAI Expands Trusted Access with GPT-5.4-Cyber for Cyber Defense
OpenAI has introduced GPT-5.4-Cyber to its Trusted Access for Cyber program, enhancing AI-driven cybersecurity for vetted defenders. This move underscores the growing importance of advanced AI in cyber defense.
OOWM: A New Framework for Robotic Reasoning via Object-Oriented World Modeling
Researchers introduce Object-Oriented World Modeling (OOWM), a framework that enhances embodied reasoning in robots by structuring world modeling through software principles. This approach addresses the limitations of traditional Chain-of-Thought prompting in complex planning tasks.
Nous: A New Compiled Language for Self-Healing AI Agents
Nous is a compiled language designed to create self-healing AI agents. It aims to revolutionize AI development by enabling agents to autonomously repair and optimize themselves.
New Spatial Competence Benchmark Challenges AI's 3D Reasoning
Researchers introduce SCBench, a rigorous new benchmark to evaluate AI's spatial reasoning. Existing tests fall short in assessing real-world navigation and planning. The benchmark spans three hierarchical capability buckets, testing executable outputs with deterministic checkers.
New Architecture Solves AI Agent Identity Crisis with Multi-Anchor Memory System
Researchers propose a multi-anchor architecture to prevent AI agents from losing their 'self' due to memory overflow. This approach draws inspiration from human memory systems to ensure continuity and resilience.
Microsoft Explores OpenClaw-Like AI Bots for Copilot
Microsoft is testing OpenClaw-style autonomous AI features in Copilot to enable 24/7 task completion. This move aims to enhance productivity by allowing AI to act independently on behalf of users.
Leopardracer Reveals Groundbreaking AI Research on X
Leopardracer shared a significant AI research update on X, hinting at a major breakthrough. The details remain scarce, but the implications could be transformative for the field.
LABBench2: New Benchmark Measures AI's Real-World Biology Research Capabilities
Researchers introduce LABBench2, a benchmark to evaluate AI systems' ability to perform practical biology research. The new benchmark focuses on real-world capabilities beyond just knowledge and reasoning.
HumorGen: AI Researchers Develop Framework for Better Humor Generation
Researchers introduce the Cognitive Synergy Framework to improve humor generation in LLMs. The approach uses six cognitive personas to create humorous content, addressing the challenge of incongruity in standard training methods.
GIANTS: New Benchmark Tests AI's Ability to Predict Scientific Breakthroughs
Researchers introduce GiantsBench, a dataset to evaluate AI's ability to anticipate scientific insights. The benchmark includes 17,000 examples across eight domains, challenging models to predict future discoveries from foundational papers.