Microsoft has introduced the most recent 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 on the market in very restricted entry as of Thursday evening: solely on Microsoft’s not too long ago launched Azure AI Foundry improvement platform, and just for analysis functions below 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 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 step by step elevated over the past a number of years.
On this case, Microsoft attributes Phi-4’s soar in efficiency to the usage of “high-quality artificial datasets,” alongside high-quality datasets of human-generated content material and a few unspecified post-training enhancements.
Many AI labs are wanting extra carefully at improvements they’ll make round artificial information and publish coaching lately. Scale AI CEO Alexandr Wang mentioned in a tweet on Thursday that “we’ve got 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. Beforehand an AI VP at Microsoft and a key determine within the firm’s Phi mannequin improvement, Bubeck left Microsoft in October to affix OpenAI.
