GEMINI LABJP
3.8LIVE — Two audio-to-audio models reached GA for the Live API: gemini-3.8-live as the low-latency default, and -extended-thinking for background reasoning mid-conversation09/30 — Thirteen days until gemini-omni-flash-preview shuts down. The replacement is gemini-omni-1.1-flash, so count your call sites before you swapMCP — A timeout written as ten minutes on the extension side is reportedly cutting out at one. Anyone handing long work to an MCP server runs straight into itNEW — When an AI function in Sheets refuses to generate, suspect where the file lives before you blame the 24-hour capGEM — When a Gem built for your team will not share, walk the admin settings and the Drive sharing settings in a set order10/16 — Twenty-nine days until Gemini 2.5 Pro, Flash and Flash-Lite shut down together. The path forward is the 3.5 Flash line3.8LIVE — Two audio-to-audio models reached GA for the Live API: gemini-3.8-live as the low-latency default, and -extended-thinking for background reasoning mid-conversation09/30 — Thirteen days until gemini-omni-flash-preview shuts down. The replacement is gemini-omni-1.1-flash, so count your call sites before you swapMCP — A timeout written as ten minutes on the extension side is reportedly cutting out at one. Anyone handing long work to an MCP server runs straight into itNEW — When an AI function in Sheets refuses to generate, suspect where the file lives before you blame the 24-hour capGEM — When a Gem built for your team will not share, walk the admin settings and the Drive sharing settings in a set order10/16 — Twenty-nine days until Gemini 2.5 Pro, Flash and Flash-Lite shut down together. The path forward is the 3.5 Flash line
TAG

schema design

1 articles
Back to all tags
Related:
Gemini API1Memory Bank1Memory profiles1agent design1indie development1
Gemini API/2026-08-03Advanced

Measuring Update Policies for Memory Profiles: The Guard That Cost Me 16 Points of Accuracy

Memory profiles went GA in Memory Bank, making structured memory available to downstream code. I built three update policies and compared them under identical conditions. The one that looked obviously correct turned out to be the worst. Full harness code and the path to per-field TTLs.