Microsoft develops MAI-Base-2 model with 2 trillion parameters
SiliconANGLE: Microsoft reveals cutting-edge MAI-Base-2 model with 2T parameters
Microsoft Corp. has developed a new large language model that it says is significantly more efficient than leading open-source alternatives. The company’s artificial intelligence research group detailed the algorithm on Thursday. MAI-Base-2 is not a full-fledged LLM but rather a base model, a kind of no-frills prototype. Developers turn base models into LLMs by putting […] The post Microsoft reveals cutting-edge MAI-Base-2 model with 2T parameters appeared first on SiliconANGLE.
Get smart on it
Microsoft has developed MAI-Base-2, a base model with 2 trillion parameters that serves as a prototype for building large language models. The model uses a mixture of experts architecture that only activates a subset of its artificial neurons when processing prompts, making it up to 12 times more hardware-efficient than the leading open-source alternative while outperforming it on benchmarks containing science, programming, and math questions. The company trained the model over 38 days using specialized hardware and a massive dataset, and plans to license it to trusted partners through its cloud platform while using it to power new language models.
Relevant courses
Want to go deeper than the news? Explore live, cohort-based AI courses taught by practitioners.
Browse AI courses on MavenRelated news
Gemini 4 Argon: Built to solve your hardest problems
The new model aims to handle complex reasoning tasks where current systems often struggle or fail completely.
Also reported by The Verge, Ars Technica, The Decoder and SiliconANGLE
Welcome Muse Spark Open: open-weight frontier multimodal mixture-of-experts model from Meta
Open-weight models let researchers and companies build AI systems without relying on proprietary providers, potentially accelerating innovation across industries.
Also reported by The Verge, The Decoder, TechCrunch and SiliconANGLE
Reflection AI open-sources Beam’s weights, post-training recipes
Startup Reflection AI Inc. today made the weights of Beam, its first large language model, available on Hugging Face. The company also released technical resources that will enable developers to customize the algorithm. Originally introduced last week, Beam is one of the industry’s most advanced open-source LLMs. It features about 500 billion parameters, yet approaches […] The post Reflection AI open-sources Beam’s weights, post-training recipes appeared first on SiliconANGLE.
Open From Data Center to Desktop: NVIDIA Expands Nemotron Family With Highest Efficiency Super VL and Bolt Models
NVIDIA today released Nemotron 3.5 Super VL, an open 120-billion-parameter model that delivers the fastest task completion and highest accuracy for specialized always-on agents. Joining it are two new edge models: Nemotron 3.5 Bolt 74B-A9B 24GB, optimized to balance intelligence and speed per GB for local agentic workloads, and Nemotron 3.5 Bolt E4B 4GB, optimized for intelligence per GB for fast conversational agents. Super VL and Bolt 74B-A9B are available now, with Bolt E4B coming Oct. 23. T
Also reported by The Decoder, SiliconANGLE and MarkTechPost
OpenAI will reportedly ship at least one model this year but its flagship still needs alignment work
OpenAI is racing to finish its next flagship model, which uses the same looped transformer technique as Astra to boost math and coding performance. The tradeoff is that looping makes safety monitoring harder. Microsoft accidentally revealed details about how the technique works on a public page. Whether or not the flagship is ready in time, employees say one or two new models will likely ship by year's end. The article OpenAI will reportedly ship at least one model this year but its fla
Welcome Beam: a 501B open model you can own, customize, and scale
Open-source alternatives to proprietary AI systems could shift control over large language models from commercial labs to individual organizations and researchers.