All AI news

AIDesign Arena says Opus 5.5 stands out for dynamic, creative animations, such as header letters floating away on scroll and a background galaxy that moves with the user. The post argues these animations enhance page content rather than inflating it.

AIDesign Arena reports that websites built by Opus 5.5 show stronger sectioning, visual hierarchy, and balance than those from its predecessor, Opus 5. The post also says Opus 5.5's motion design and animations have improved significantly over Opus 5, which was released just over 2.5 months earlier.

AIAnthropic's Claude Opus 5.5 has taken first place on four Design Arena leaderboards: Overall Frontend, Data Visualization, 3D Design, and React Native. It also ranks in the top three on the Game Dev and UI Components leaderboards, about two weeks after its release. Design Arena says developers, designers, and casual users have embraced the model.

AIAntigravity can build and test native Android apps by connecting the Stitch MCP and Android CLI. The agent imports UI designs, converts them into native Jetpack Compose components, validates them in an emulator, and runs the final build on a physical device.

AILiquid AI built 10 live-camera demos for its d1-3B model, ranging from gesture-controlled games to content moderation, each using one forward pass per frame. In collaboration with NVIDIA Robotics, the company also showed d1-3B navigating an environment in Isaac Sim, served on a Jetson in a hardware-in-the-loop setup.

AILiquid AI has released d1-omni-600M, an experimental 600M-parameter model that handles text plus image or audio input. It combines LFM2.5-Encoder-350M with vision and audio encoders and leads the company's text benchmark comparison on toxicity detection and paraphrase identification. The post suggests uses such as voice-command routing, on-device moderation, and intent classification.

AILiquid AI's d1-3B ranks first among models under 10B parameters on the Decision Index v0.2.1, a benchmark for structured decision-making. Built from LFM2.5-VL-3B, it makes decisions from text and images in a single pass. It is suited to reranking, agent guardrails, and visual inspection.

AILiquid AI released Open d1, two open-weight multimodal models in its d1 decision model family. The d1-3B model supports text and vision, while d1-omni-600M supports text plus image or text plus audio. The source says the models are meant for real-time decision making across data centers, RTX workstations, and Jetson edge devices.

AIMark Chen says the Navier-Stokes achievement matters more for the figure it shows than for the problem itself, representing a decade of mathematical progress in a single week. He says he is eager to apply these tools to life sciences, the building of OpenAI's next models, and alignment research.

AIGoogle is launching its first TPUs into orbit to test how hardware holds up under solar events, cosmic rays, and radiation-induced bitflip errors. The post says these conditions can only be tested in space.

AIGoogle launched its first test satellite carrying four TPUs into orbit last week as part of Project Suncatcher, a moonshot exploring whether machine learning infrastructure could one day operate in space. The test aims to determine whether Google's AI hardware can withstand the physical stress of spaceflight and the radiation and thermal extremes of orbit.

AINous Research has raised a Series B, as reported by the Wall Street Journal, to bring its Hermes Agent to new frontiers and build a mobile app. Investors include Nvidia, M12, Samsung Next, Robot Ventures, USV, Y Combinator, and Menlo Ventures, among others.

AIGamma announces Gamma 5, which it calls its biggest update, rebuilding its engine from the ground up. The release adds an agent for brainstorming, research, and editing, plus style control from described looks or visual inspiration. It also supports importing and exporting PowerPoints, PDFs, and company brand, with connections to Slack, Notion, Salesforce, Claude, and ChatGPT.

AILangChain Academy has published a two-minute explainer on agent skills and how they protect an agent's context window. The post promotes its Deep Agents course on the LangChain Academy site.

AITypeSafeAI's Jev reached one trillion tokens served by the Sunday after its Thursday launch, with no signs of slowing, according to Modal. Modal presents the milestone as a case study of how the team scaled Jev on its platform.

AIPerplexity reports its system reached 92.4% accuracy on MADQA, a benchmark of 500 questions over 800 PDFs. The post describes this as the top result among retrievers on that benchmark.

AIIn agentic search, a GPT-OSS-120B agent using the 9B model answers 64.0% of BrowseComp+ questions correctly, 4.9 points ahead of the next ColBERT model. It also uses fewer searches than any baseline.

AIOn the Q2D-Web benchmark of about 70,000 production-derived search queries over 190M web documents, Perplexity's 9B and 0.6B models reach 74.8% and 73.6% Recall@1000. Both outperform nemotron-embed-8b, which scores 69.3%.

AIPerplexity's 0.6B and 9B models are both distilled token by token from one 18B teacher, so they share a single embedding space. A corpus indexed with the 9B model can be searched using 0.6B queries, raising ViDoRe v3 from 62.3% to 63.5% with no added query cost.

AIPerplexity's models embed images and rendered pages directly, so PDFs, slides, and scans can be searched without OCR. This preserves tables, figures, and layout that text extraction typically drops.

AIPerplexity's pplx-embed-v2-late retains a 128-dimensional vector for each token rather than compressing a document into one vector. It scores matches with MaxSim, pairing each query token with its closest document token, which the post presents as preserving detail in long or visually dense pages.

AIMicrosoft Research introduced Agent Lightning, a tool that connects existing AI agents to reinforcement learning training. It aims to make agents easier to improve without rebuilding them, since their tools, context, and decision-making are typically managed by complex frameworks.

AIPerplexity has released pplx-embed-v2-late, two late-interaction embedding models that retrieve text, images, and pages within a shared embedding space for cross-model querying. The company says both models achieve frontier performance and are publicly available on Hugging Face.