The LGTM (Page 115)

The LGTM

Sign in Subscribe

Gemini 3.1 Deep Think Is Google’s Answer to the Frontier Benchmark Knife Fight

Google’s Gemini 3.1 Deep Think update is not interesting because another lab found another benchmark where it can print a bigger number. That game is now mostly a knife fight in a spreadsheet. It is interesting because Google is no longer asking developers to believe Gemini is catching

Gemini 3.1 Flash-Lite Makes the Cheap Model the Architecture Decision

The most important model in a production AI system is often not the smartest one. It is the cheap, fast, good-enough model that gets called 40 times before the expensive model ever sees the request. That is why Gemini 3.1 Flash-Lite deserves more attention than its name will probably