NewsBlogsTechTech EngineeringCanalsScienceResearchProgrammingAI

Feeds

    100RApple Machine LearningArXiv (cs.CV)BairBBC - Top StoriesBBC TechnologyBen EvansCisco EngineeringDaring FireballDatabricksDiamond GeezerDropbox TechEngineering at MetaGitHubHackadayHacker NewsHugging FaceIan VisitsIEEE SpectrumInk & SwitchInstagram EngineeringKDnuggetsLWN.netLyft EngineeringMacRumorsMattBitsNetflix EngineeringOllamaOMG UbuntuOnTheCutOpenAIPythonQuanta MagazineRachel by the BayRustSalesforce EngineeringShopify EngineeringSimon WillisonSpotify EngineeringThe ConversationThe Fly BlogThe TimesTorrentFreakTowards Data ScienceUber EngineeringWillowWiredZed

Ollama

  • OpenAI gpt-oss-safeguard
    10/29/2025 at 00:00
  • MiniMax M2
    10/28/2025 at 00:00
  • NVIDIA DGX Spark performance
    10/23/2025 at 00:00
  • New coding models & integrations
    10/16/2025 at 00:00
  • Qwen3-VL
    10/14/2025 at 00:00
  • NVIDIA DGX Spark
    10/13/2025 at 00:00
  • Web search
    9/24/2025 at 00:00
  • New model scheduling
    9/23/2025 at 00:00
  • Cloud models
    9/19/2025 at 00:00
  • OpenAI gpt-oss
    8/5/2025 at 00:00
  • Ollama's new app
    7/30/2025 at 00:00
  • Secure Minions: private collaboration between Ollama and frontier models
    6/3/2025 at 00:00
  • Thinking
    5/30/2025 at 00:00
  • Streaming responses with tool calling
    5/28/2025 at 00:00
  • Ollama's new engine for multimodal models
    5/15/2025 at 00:00
  • Minions: where local and cloud LLMs meet
    2/25/2025 at 00:00
  • Structured outputs
    12/6/2024 at 00:00
  • Ollama Python library 0.4 with function calling improvements
    11/25/2024 at 00:00
  • Llama 3.2 Vision
    11/6/2024 at 00:00
  • IBM Granite 3.0 models
    10/21/2024 at 00:00
  • Llama 3.2 goes small and multimodal
    9/25/2024 at 00:00
  • Reduce hallucinations with Bespoke-Minicheck
    9/18/2024 at 00:00
  • Tool support
    7/25/2024 at 00:00
  • Google Gemma 2
    6/27/2024 at 00:00
  • An entirely open-source AI code assistant inside your editor
    5/31/2024 at 00:00
  • Google announces Firebase Genkit with Ollama support
    5/20/2024 at 00:00
  • Llama 3 is not very censored
    4/19/2024 at 00:00
  • Llama 3
    4/18/2024 at 00:00
  • Embedding models
    4/8/2024 at 00:00
  • Ollama now supports AMD graphics cards
    3/14/2024 at 00:00