全部 AI 动态

⚠️ Frontier AI models still fall significantly short of human designers on design creativity. ⚠️ Introducing Design Creativity Bench, a new benchmark evaluating AI models’ creativity on UI design tasks. Despite rapid advances in their ability to generate functional websites and product UIs, leading AI models still struggle to make creative design decisions. We evaluated 16 frontier models across 80 open-ended UI tasks, each adapted to two distinct product domains alongside human designer references. Existing UI benchmarks often measure a single output quality metric. Instead, we measure three dimensions of design creativity: - Originality: How distinct a model's designs are from other models' outputs for the same brief. - Creative Range: How much a model adapts its design decisions when the product domain changes. - Appropriateness: How well the generated UI satisfies the functional requirements of the brief. The results reveal a substantial gap in overall creativity: The best model, @OpenAI GPT-6 Astra, scores 65.5 against a human reference of 92.3. We're publishing the full leaderboard, methodology, and reproducible evaluation framework to make design creativity a measurable dimension of frontier model capability. 📊 Benchmark Leaderboard: https://kombai.com/benchmark/ 📄 Paper: https://arxiv.org/abs/2610.11539 🤗 HuggingFace Datasets: https://huggingface.co/datasets/Kombai/design-creativity-bench 🔗 Github: https://github.com/kombai-io/design-creativity-bench/

We are open-sourcing RISE, our red-teaming algorithm that breaks the safeguards of the latest image models from OpenAI, DeepMind, and others. RISE uses readily available models like Qwen and Gemini Flash under the hood, with no additional training required. Read more: https://whitecircle.com/research/breaking-frontier-image-models

Your LLM agent has to think out loud, token by token, before it can search, run code, or act in the world. We humans don’t. We ponder in silence and speak when it matters. Human language was never meant to be the limit of machine thought. Introducing 🌗Hybrid Reasoning Agents - Think in latent space, act through text - Two modes, one unified multi-turn flow - No black box, fully readable latent thoughts - Any LLM can become a HybridAgent

Today we're publishing the first draft of the Agent Baseline Software Factory Reference Architecture! An opinionated blueprint for securing increasingly autonomous software factories, built with folks across the community. It's open for feedback and contributions! https://agentbaseline.org/reference-architecture

We are open-sourcing RISE, our red-teaming algorithm that breaks the safeguards of the latest image models from OpenAI, DeepMind, and others. RISE uses readily available models like Qwen and Gemini Flash under the hood, with no additional training required. Read more: https://whitecircle.com/research/breaking-frontier-image-models

We’ve found 2 new families of counterexamples to the long-standing (nearly 60-year-old) Grad’s conjecture in plasma physics using Gemini 4 Argon in our new paper, with Jonathan Citrin, Brendan Tracey, Matt Landreman at the University of Maryland: https://arxiv.org/abs/2610.07304!

Your LLM agent has to think out loud, token by token, before it can search, run code, or act in the world. We humans don’t. We ponder in silence and speak when it matters. Human language was never meant to be the limit of machine thought. Introducing 🌗Hybrid Reasoning Agents - Think in latent space, act through text - Two modes, one unified multi-turn flow - No black box, fully readable latent thoughts - Any LLM can become a HybridAgent

1/10 Can anonymized user behavior advance LLM intelligence? Excited to share Vela: turning behavior from real-world scenarios into training signals. Our 35B model improves over its base on all 10 benchmarks: +11.5 pts on VelaBench and +4.0 pts on general benchmarks on average.

Models cost millions to train and minutes to copy. Fine-tuning and distillation can erase where they came from. Introducing the Fingerprinting Leaderboard, an open benchmark for model provenance — built so the proof lives in the weights, not the paperwork. https://fingerprint.sentient.foundation

Recursive self-improvement needs agents that can build their own training environments. But researchers still part of the loop, making it hard to scale. We introduce AutoEnvScaling, which turns Data Flywheel into a terminal task: a proposer agent builds complete Harbor tasks and sandbox. It builds just like human researchers. This enables self-play RL for terminal agents: one model improves as both builder and solver, without human-in-the-loop.