This paper examines the syntactic distribution of degree modifiers in both spoken and written English. The results of the empirical case studies show that degree modifiers, both amplifiers (e.g., very, extremely) and downtoners (e.g., quite, pretty), are generally more often used in predication than in attribution, a result that is in line with earlier observations of the distribution of individual modifiers. This synchronic trend is also evident in diachronic developments: corpus data show that the recent frequency increase of intensifying this and that has largely taken place in predication, and the adjectivization of a class of -ed participles (e.g., interested, scared) can also be connected to their frequent co-occurrence with degree modifiers after be. Finally, the connection between degree modifiers and predicative usage has recently become stronger for a subset of modifiers (e.g., so, this, that) due to the decline of the “Big Mess” construction (e.g., so good an idea). From a theoretical perspective, this paper promotes a dynamic, usage-based model of word classes where frequency of use plays a role in categorization. The data investigated in the article are mainly discussed from the perspective of usage-based Construction Grammar, and the theoretical implications of the findings are examined both in light of a more traditional Construction Grammar network model of language and some recent ideas of overlapping word classes.