Skip to content
Live
Models
Nov 14Sat
  1. The Decoder

    Former Anthropic researcher Coxon: Anthropic can now retrain the Mythos model using 'a small portion of the original computing resources'

    Former Anthropic and OpenAI researcher Jacob Coxon said the IPO roadshow slides for Anthropic were the main reason for his departure, as they showed that after a major leap in capabilities for its Mythos model in the spring, it could be retrained using 'a small portion of the original computing resources,' indicating that algorithm efficiency was accelerating.

  3. The Decoder65

    Runway open-sources robot control model Praxis-1

    Runway has released the open-source robot control model Praxis-1, which learns to control robots through video and has shown excellent performance in its own tests, scoring 46.2% on the Nvidia RoboLab-120 evaluation, leading similar models. The model requires additional training to adapt to new robot systems, the standard version requires an 80GB memory GPU, and it has been made available on Hugging Face.

    Same story · 2 outlets
  4. MarkTechPost

    Best AI video generation models in 2026: Elo ranking, per-second price, and open-source weight analysis

    The Elo ranking shows Alibaba Wan 3.0 (1175 T2V Elo) at the top with a price of $0.20 per second; Utopai X (1170 T2V Elo) is second but has no API; MiniMax H3 (1161 T2V Elo) is the first open-source video model with a price of $0.08 per second, but it is regionally restricted. The ranking is based on blind human preference tests, combined with the price per second of the API and the status of weighted licenses.

Nov 13Fri
  1. QbitAI

    Unbounded Frontiers opensources Fx-Bio-1031, life science RSI model surpassing GPT-6-Astra and Opus-5

    The boundaryless front-end open-source biological information large model Fx-Bio-1031 achieved 70.59% Pass@5 on the BioMysteryBench benchmark test, significantly outperforming GPT-6-Astra (47.06%) and Claude Opus-5 (52.94%). Fx-Bio-1031 adopts an efficient MoE architecture with 125B parameters and supports localized deployment, suitable for drug development, multi-omics analysis, and other scenarios.

  4. Ant Group inclusionAI · Hugging Face new models

    inclusionAI/Duo-1.0-causal-base released: A multimodal world model for full-duplex interaction

    inclusionAI releases Duo 1.0 causal-base model, a full-duplex multimodal world model for real-time audio-video interaction, including implementation weights and backbones, intent models and adapters, audio-video encoders, speech recognizers, and forced aligners. The model weights are based on MiniMax H3 initialization and are open-sourced.

  6. Hacker News · AI hot posts86

    Edge0 open sources 145B and 120B edge-side models and inference frameworks.

    Edge0 open-sourced the Edge0-145B and Edge0-120B two edge models, and also released a unified inference framework and deployment tools. Officially, the 145B model can run locally on compatible laptops, with peak memory of 29GB, decoding speed of 80+ tokens/s, pre-filling speed of 1100+ tokens/s, supporting context lengths of 128K–256K.

    Why it matters: The original text provides actual memory, speed, and multiple benchmark comparisons of the edge 145B model, which can be used to judge the practical boundaries of running cutting-edge models locally.

  7. Hacker News · 300+82

    Google launches Gemini 4 Hydrogen and Orchestrator in Antigravity.

    Google has launched Gemini 4 Hydrogen in Antigravity and added an Orchestrator model option, combining Hydrogen with stronger models like Gemini 4 Carbon for long-period tasks.

    Same story · 6 outlets
  8. The Verge · AI82

    Google releases Gemini 4 Hydrogen, capable of breaking down complex problems into multiple parts

    Google has released the Gemini 4 Hydrogen model, claiming it can better answer complex questions that involve multiple parts, spelling errors, or highly specific requirements, and will break down the problem and respond item by item.

    Same story — showing the featured version《Google Search has integrated Gemini 4 Hydrogen and is now open to global users.》

  9. Hacker News · 300+

    Gemini 4 Hydrogen released: bringing cutting-edge intelligence and efficiency to daily coding and agent workflows

    Gemini 4 Hydrogen has been released, boosting the Artificial Analysis Intelligence Index score to 51 at the default high reasoning level (Argon is 50, with a maximum of 54), and typically outperforming similar models in task execution speed.

    Same story · 6 outlets
  10. The Decoder88

    Google released Gemini 4 Hydrogen, surpassing larger Argon on benchmarks after four weeks

    Same story · 6 outlets
  11. Ars Technica · AI82

    Google launched Gemini 4 Hydrogen, replacing 3.8 Flash

    Google releases Gemini 4 Hydrogen, replacing Gemini 3.8 Flash in its own products, with access restrictions more relaxed than previous Argon and Carbon, available for use upon release

    Same story · 6 outlets
  12. Hugging Face Blog71

    IBM releases LLMON markup language and Granite 4.1 3B/8B preview models

    IBM released LLMON (LLM Object Notation) markup language on Hugging Face and launched two experimental preview models based on Granite 4.1: granite-4.1-3b-LLMON-preview and granite-4.1-8b-LLMON-preview, while also open-sourcing a GitHub toolkit.

    Why it matters: The original text provides the design motivation for the LLMON markup language and the two preview models, allowing readers to understand how separating instructions and data can reduce the risk of indirect prompt injection.

  13. ITHome · AI87

    Google releases Gemini 4 Hydrogen model, focusing on daily programming and intelligent agent workflows

    Same story · 6 outlets
  14. Google DeepMind87

    Google DeepMind releases Gemini 4 Hydrogen model

    Google DeepMind releases Gemini 4 Hydrogen, targeting daily coding and intelligent agent workflows, with an Artificial Analysis intelligence index of 51 at the default high thinking level, higher than Argon's 50, and reaching 54 at the xhigh level

    Same story · 6 outlets

    Why it matters: Google provides the division of labor and positioning of Hydrogen, Carbon, and Argon, as well as the actual differences in cost and speed between multi-model arrangements.

Nov 12Thu
  1. QbitAI82

    MiniMax open-source image model H3-Image: Native 4K, supports 16 reference images

    MiniMax's open-source image model H3-Image supports native 4K (4096×4096 pixels) generation and can take up to 16 reference images. The author tested that it can deduce orthogonal three-view drawings and mechanical exploded views based on product appearance images, and reduce the plasticity on details such as pores and freckles on human faces. The API price is 50% to 70% lower than that of mainstream competitors, with a 50% discount on the first week's 16MP requests.

    Same story · 2 outlets
  2. ITHome · AI

    Runway launches robot model Praxis-1, 15.6 times faster and cost reduced to 1/51

    Runway has launched the robot model Praxis-1, based on the Runway video foundation model with 27 billion parameters. In the RoboLab-120 benchmark test, it achieved a success rate of approximately 46.2%, with a speed increase of 15.6 times and a cost reduction to 1/51. This model is licensed under Apache 2.0 and both weights and code are open-sourced.

    Same story · 2 outlets
  5. ITHome · AI67

    Google DeepMind releases next-generation genome AI model AlphaGenome 2: from tissue prediction to single-cell analysis, identifying gene expression variation capabilities nearly double

    Google DeepMind has launched the AlphaGenome 2 model, which can predict the effects of DNA variations on specific cell types, nearly doubling its ability to identify gene expression variations to 30% (from 16%), and accurately predicting the direction of gene expression changes to 43% (from 23%). It supports cross-modal data inference and has opened API access to non-commercial research.

    Same story · 3 outlets
  6. The Decoder78

    Google launches Gemini Decision 1 and Gemini Decisions API, capable of processing 1000 issues at a time

    Google DeepMind launches Gemini Decisions API, targeting yes/no, multiple choice, and scale scoring for closed-form judgments. The underlying model, Gemini Decision 1, can handle up to 1000 independent questions at once, covering text, images, audio, video, and PDF.

    Same story · 2 outlets
  8. The Verge · AI65

    Google DeepMind has released the AlphaGenome 2 model, analyzing how DNA affects different cells.

    Google DeepMind releases AlphaGenome 2 model, predicting gene variation impacts on different cell types and states by analyzing over 100 million cell outline data, identifying nearly double the variable gene expression mutations compared to the previous generation model

    Same story · 3 outlets
Nov 11Wed
  2. Google DeepMind66

    DeepMind releases AlphaGenome 2, predicting DNA variation impacts by cell type

    Google DeepMind releases AlphaGenome 2, a conditional DNA sequence model that can predict the impact of DNA mutations on gene expression for specific cell types or states.

    Same story · 3 outlets

    Why it matters: Officially disclosed the conditional architecture modification and single-cell level evaluation comparison, which can understand how the model localizes the effect of mutation to specific cell types.

  3. The Decoder

    Anthropic claims AI has weakened NVIDIA's CUDA advantage, reducing the time to switch to AMD chips to three days.

    Anthropic claims to have reduced the time to migrate its AI model, Claude, to AMD GPUs from several months to three days with almost no human intervention, thereby breaking its reliance on NVIDIA. The company states that the AI model Mythos has completed 99% of the kernel migration or writing work, allowing the new hardware to reach a usable performance level in three days, while traditional engineering methods require six to twelve months.

    Same story · 2 outlets
  4. Hacker News · AI hot posts

    Google SWE uses 48 AI agents to analyze NASA radar data, discovering unreported Mayan pyramids in Mexico within 72 hours

    Google SWE uses 48 AI agents to analyze NASA radar data, discovering unreported Mayan pyramids in Mexico within 72 hours; the agents process 1,200 km² of radar images, identifying suspected pyramids, plazas, and reservoir structures with right angles and sharp corners, which have been confirmed by the National Institute of Anthropology and History of Mexico as not being in the registered records.

  5. IBM Research Blog48

    IBM Quantum Nighthawk r2 released: Quantum advantage breaks through again, supporting accurate circuits with over 7,500 quantum operations

    IBM Quantum Nighthawk r2 has been released, featuring a 120 programmable qubit (458 physical qubits) processor that achieves a throughput of 100,000 samples per second, a 25-fold improvement over Heron, supporting circuits with over 7,500 quantum operations with high accuracy, with customers running over 3.4 billion circuits reporting a performance improvement of 19-fold.

  7. ITHome · AI

    Anthropic Claude completes AI model adaptation for AMD GPU in just 3 days, challenging NVIDIA's CUDA moat.

    Anthropic Claude Mythos Preview model completed adaptation to AMD MI355X GPU in just 3 days, traditional adaptation requires 6-12 months; GPUs are trending towards general computing power resources, challenging NVIDIA's CUDA moat.

    Same story · 2 outlets
  8. Ant Group inclusionAI · Hugging Face new models

    inclusionAI/ZoomGain-4B-GGUF released: Multimodal model supporting image input

    inclusionAI/ZoomGain-4B-GGUF is a 175B parameter multimodal model supporting image input, using FP16, Q8_0, and Q4_K_M precision quantization. The model includes a language model and mmproj visual encoder/projector, converted to GGUF format via llama.cpp. It provides llama-mtmd-cli for command-line inference and llama-server for network chat functionality.

  9. Ant Group inclusionAI · Hugging Face new models

    inclusionAI/ZoomGain-9B-GGUF Released GGUF Format Weights

    The GGUF format weights for inclusionAI/ZoomGain-9B have been released, converted using llama.cpp, with the language model in FP16, Q8_0, Q4_K_M. The visual encoder and projector (mmproj) also adopt this quantization scheme. Both the language model and mmproj files need to be provided for image input, supporting CLI inference (llama-mtmd-cli) and Web Chat (llama-server) deployment.

  11. Ant Group inclusionAI · Hugging Face new models

    inclusionAI/SingVL_S1_4B released: A multimodal decision-making model based on Qwen3.5

    Sing VL S1 is a multimodal decision-making model based on Qwen3.5, capable of answering named entity questions with text or JSON and up to four images, scoring options for each question using a single Transformers forward pass, performing excellently on 43 text datasets and 11 visual datasets, supporting Python 3.12 and PyTorch inference.