Microsoft has introduced the latest addition to its Phi household of generative AI fashions.
Called Phi-4, the mannequin is improved in a number of areas over its predecessors, Microsoft claims — particularly math drawback fixing. That’s partly the results of improved coaching knowledge high quality.
Phi-Four is offered in very restricted entry as of Thursday night time: solely on Microsoft’s just lately launched Azure AI Foundry improvement platform, and just for analysis functions below a Microsoft analysis license settlement.
This is Microsoft’s newest small language mannequin, coming in at 14 billion parameters in dimension, and it competes with different small fashions equivalent to GPT-4o mini, Gemini 2.0 Flash, and Claude 3.5 Haiku. These AI fashions are oftentimes sooner and cheaper to run, however the efficiency of small language fashions has regularly elevated over the past a number of years.
In this case, Microsoft attributes Phi-4’s bounce in efficiency to using “high-quality synthetic datasets,” alongside high-quality datasets of human-generated content material and a few unspecified post-training enhancements.
Many AI labs are trying extra carefully at improvements they will make round artificial knowledge and put up coaching today. Scale AI CEO Alexandr Wang stated in a tweet on Thursday that “we have reached a pre-training data wall,” confirming a number of stories on the subject within the final a number of weeks.
Notably, Phi-Four is the primary Phi-series mannequin to launch following the departure of Sébastien Bubeck. Previously an AI VP at Microsoft and a key determine within the firm’s Phi mannequin improvement, Bubeck left Microsoft in October to hitch OpenAI.
