Microsoft has introduced the latest addition to its Phi household of generative AI fashions.
Referred to as Phi-4, the mannequin is improved in a number of areas over its predecessors, Microsoft claims — particularly math downside fixing. That’s partly the results of improved coaching information high quality.
Phi-4 is obtainable in very restricted entry as of Thursday evening: solely on Microsoft’s lately launched Azure AI Foundry improvement platform, and just for analysis functions beneath a Microsoft analysis license settlement.
That is Microsoft’s newest small language mannequin, coming in at 14 billion parameters in measurement, and it competes with different small fashions comparable to GPT-4o mini, Gemini 2.0 Flash, and Claude 3.5 Haiku. These AI fashions are oftentimes quicker and cheaper to run, however the efficiency of small language fashions has steadily elevated over the past a number of years.
On this case, Microsoft attributes Phi-4’s bounce in efficiency to using “high-quality artificial datasets,” alongside prime quality datasets of human generated content material and a few unspecified put up coaching enhancements.
Many AI labs are trying extra intently at improvements they’ll make round artificial information and put up coaching as of late. Scale AI CEO Alexandr Wang stated in a tweet on Thursday that “now we have reached a pre-training information wall,” confirming a number of studies on the subject within the final a number of weeks.
Notably, Phi-4 is the primary Phi-series mannequin to launch following the departure of Sébastien Bubeck. Bubeck, beforehand an AI VP at Microsoft and a key determine within the firm’s Phi mannequin improvement, left Microsoft in October to hitch OpenAI.
