FlashGoogle Launches Gemini 4 Hydrogen, a High-Efficiency Model in the Gemini 4 Series
88Z AI·Nov 13
Find the right tools for everyday work and creative projects
Explore new games made with AI
Perplexity has open-sourced its latest decision models, Decider v1.3 (~27B parameters) and the distilled Decider Flash v1.3 (~4B parameters). The update introduces a "locate" feature that extracts text spans with character offsets based on instructions, significantly improving accuracy in entity extraction and classification tasks. Supporting text and image inputs with a 256K context window under the Apache 2.0 license, the models are available for free on OpenRouter until November 19, 2026.
For tasks like scheduling with multiple valid answers, traditional supervised fine-tuning is inadequate. This briefing explains how to use Amazon SageMaker AI's serverless model customization workflow and Training Sessions APIs combined with RLVR (Reinforcement Learning with Verifiable Rewards). By building verifiers with hard and soft constraints and using the GRPO algorithm, models are guided to generate compliant, high-quality solutions rather than mimicking a single ground truth.
xAI announces that Grok Bot on Mac now supports seven system apps: Messages, Mail, Notes, Reminders, Calendar, Location, and Contacts. Users can complete cross-app tasks via natural language prompts, such as finding an address and scheduling events. The feature is included in X Premium and SuperGrok subscriptions, requiring manual permission grants and user confirmation for sensitive actions.
Anthropic has announced a private beta for self-hosted Claude Managed Agents, allowing enterprises to deploy the agent harness, sandboxes, and session history in their own cloud or on-premises environments. This solution privatizes the orchestration layer rather than running the model locally, with model requests still directed to Anthropic or customer-chosen providers, addressing security needs for accessing internal code and systems.
Looki has released its self-developed multimodal model series, Loom, focusing on first-person life understanding and long-term memory. The series includes Loom Sense, Loom Moment, and Loom Memory, designed to optimize continuous perception, event segmentation, and cross-time memory retrieval. It significantly reduces inference costs and improves processing efficiency, turning fragmented observations into traceable personal context.
Alibaba's AI music platform HappyShrimp has officially launched on iOS and Android. Users can generate complete songs by inputting emotions or stories, support chat-to-song and video scoring, and use the new 'Make Same Style' feature to replicate creative ideas.
Tencent Hunyuan has released Hy Realtime, a real-time voice model that enhances spoken language understanding, instruction following, and emotional expression. It supports tool calls like web search and integrates with Tencent Music for song requests. The model is live in Yuanbao voice calls and Tencent Customer Service, with API access coming soon via Tencent Cloud.
Y Combinator-backed Taan released Taan v1-preview on November 12, 2026. The model accepts multimodal inputs like humming, MIDI, images, or scripts to generate music with precise timing control. The team reports a 96% instruction success rate, aiming to solve the lack of controllability in current AI music models.
Thinking Machines Lab has officially open-sourced the weights for its Inkling 2 Small model on Hugging Face under an Apache 2.0 license. Led by former OpenAI CTO Mira Murati, the 594-billion-parameter model supports ultra-long context and multimodal processing. This release marks the transition from closed testing to full openness, allowing developers to download and integrate the model immediately.
88Z.ai (also written 88z) is an independent AI site and is not affiliated with Zhipu z.ai.
It offers daily flash, news, a tools directory, browser games, one-line game creation, AI short dramas, and an AI model API platform with an OpenAI-compatible interface billed in CNY points.