Experimental News Clipping Site

Tag: benchmarking

  • Simon Willison’s Weblog: Qwen3-30B-A3B-Thinking-2507

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Jul/30/qwen3-30b-a3b-thinking-2507/ Source: Simon Willison’s Weblog Title: Qwen3-30B-A3B-Thinking-2507 Feedly Summary: Qwen3-30B-A3B-Thinking-2507 Yesterday was Qwen3-30B-A3B-Instruct-2507. Qwen are clearly committed to their new split between reasoning and non-reasoning models (a reversal from Qwen 3 in April), because today they released the new reasoning partner to yesterday’s model: Qwen3-30B-A3B-Thinking-2507. I’m surprised at how poorly this reasoning mode…

  • Simon Willison’s Weblog: Qwen/Qwen3-235B-A22B-Instruct-2507

    —

    by

    Kurt Seifried
    in

    Source URL: https://simonwillison.net/2025/Jul/22/qwen3-235b-a22b-instruct-2507/#atom-everything Source: Simon Willison’s Weblog Title: Qwen/Qwen3-235B-A22B-Instruct-2507 Feedly Summary: Qwen/Qwen3-235B-A22B-Instruct-2507 Significant new model release from Qwen, published yesterday without much fanfare. This is a follow-up to their April release of the full Qwen 3 model family, which included a Qwen3-235B-A22B model which could handle both reasoning and non-reasoning prompts (via a /no_think toggle).…

  • Microsoft Security Blog: Transparency on Microsoft Defender for Office 365 email security effectiveness

    —

    by

    Kurt Seifried
    in

    Source URL: https://www.microsoft.com/en-us/security/blog/2025/07/17/transparency-on-microsoft-defender-for-office-365-email-security-effectiveness/ Source: Microsoft Security Blog Title: Transparency on Microsoft Defender for Office 365 email security effectiveness Feedly Summary: Microsoft believes in transparently sharing performance data from Microsoft Defender for Office 365, and other ecosystem providers, to help customers evaluate email security solutions and make decisions to layer for defense in depth. The post…

  • Slashdot: Google Rolls Out New Gemini Model That Can Run On Robots Locally

    —

    by

    Kurt Seifried
    in

    Source URL: https://hardware.slashdot.org/story/25/06/24/2150256/google-rolls-out-new-gemini-model-that-can-run-on-robots-locally?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: Google Rolls Out New Gemini Model That Can Run On Robots Locally Feedly Summary: AI Summary and Description: Yes Summary: Google DeepMind has introduced Gemini Robotics On-Device, an advanced language model allowing robots to execute complex tasks locally without needing internet access. This development is significant for AI security…

  • Slashdot: Salesforce Study Finds LLM Agents Flunk CRM and Confidentiality Tests

    —

    by

    Kurt Seifried
    in

    Source URL: https://yro.slashdot.org/story/25/06/16/2054205/salesforce-study-finds-llm-agents-flunk-crm-and-confidentiality-tests Source: Slashdot Title: Salesforce Study Finds LLM Agents Flunk CRM and Confidentiality Tests Feedly Summary: AI Summary and Description: Yes Summary: A recent Salesforce study highlights significant limitations of LLM-based AI agents in real-world CRM tasks, achieving only 58% success on simple tasks and 35% on multi-step tasks. The findings indicate a…

  • Cloud Blog: Accelerate your gen AI: Deploy Llama4 & DeepSeek on AI Hypercomputer with new recipes

    —

    by

    Kurt Seifried
    in

    Source URL: https://cloud.google.com/blog/products/ai-machine-learning/deploying-llama4-and-deepseek-on-ai-hypercomputer/ Source: Cloud Blog Title: Accelerate your gen AI: Deploy Llama4 & DeepSeek on AI Hypercomputer with new recipes Feedly Summary: The pace of innovation in open-source AI is breathtaking, with models like Meta’s Llama4 and DeepSeek AI’s DeepSeek. However, deploying and optimizing large, powerful models can be  complex and resource-intensive. Developers and…