GEMINI LABJP
VIDEO — Agentic video understanding reached 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite on September 1. The model navigates the timeline itself rather than sampling frames at a fixed rateTOKENS — Because it pulls transcripts, frames, or audio only when it needs them, Google measures up to 88% fewer tokens on long-form contentSCOPE — It works across both the Interactions and GenerateContent APIs. If you have costed out long-video work before, the assumptions have movedMUSIC — Lyria 3.5 entered public preview on September 3, generating full-length songs at 44.1 kHz stereoCONTROL — Lyria 3.5 accepts text and image inputs, with better musical coherence, more natural vocals, and finer control over duration and structureROBOTICS — gemini-robotics-er-2-streaming-preview is tuned for real-time streaming over the Live API, with function calling that blocks on physical robot actionsVIDEO — Agentic video understanding reached 3.7 Flash, 3.6 Flash, and 3.5 Flash-Lite on September 1. The model navigates the timeline itself rather than sampling frames at a fixed rateTOKENS — Because it pulls transcripts, frames, or audio only when it needs them, Google measures up to 88% fewer tokens on long-form contentSCOPE — It works across both the Interactions and GenerateContent APIs. If you have costed out long-video work before, the assumptions have movedMUSIC — Lyria 3.5 entered public preview on September 3, generating full-length songs at 44.1 kHz stereoCONTROL — Lyria 3.5 accepts text and image inputs, with better musical coherence, more natural vocals, and finer control over duration and structureROBOTICS — gemini-robotics-er-2-streaming-preview is tuned for real-time streaming over the Live API, with function calling that blocks on physical robot actions
TAG

indie development

40 articles
Back to all tags
Related:
Gemini API29Gemini7Cost Optimization5File Search3Android3Python2operations2Memory Bank2Memory profiles2Model Routing2Image Generation2Structured Output2
Gemini API/2026-09-07Intermediate

The day Lyria 3.5 landed, I changed how my audio folders are laid out

When Lyria 3.5 brought full-length generation, my generated takes were sitting in the same folder as the tracks I had chosen by hand. Here is the forty-line ledger gate that draws the line by hash, not by filename.

Gemini Advanced/2026-09-05Advanced

Two Kinds of Video Questions: Why I Send "Find It" and "Prove It Isn't There" Down Separate Paths

Agentic video understanding lets the model decide which parts of a video to watch. That works beautifully for finding things, and it quietly breaks when you need to prove something never appears. Here is how I split my questions, and the coverage check I now run first.

Updates/2026-09-03Intermediate

On Wear OS and Android Auto, Failure Has to Speak Too

Google Assistant starts giving way to Gemini on September 4. On Wear OS and Android Auto you cannot report a failure with a toast. Here is how I moved my error paths into media session state, and the three things I decided before the switch.

Gemini Advanced/2026-08-31Advanced

Define What Counts as a Duplicate Before Adding Embedding Search to Your Image Pipeline

My dedup check flagged two prints with identical composition but different colors as one image. Here is how I split duplicate detection into three layers, measured where perceptual hashing ends, and decided what embedding search is actually for.

Gemini Dev/2026-08-30Advanced

Why Shipped Clients Deserve a Refusal, Not a Silent Model Substitution

A model can retire, but the apps already on people's phones cannot. This is how I built a sunset ledger keyed on output contracts, and how I now back-date my own deadline from the version residue curve.

Gemini Basics/2026-08-28Beginner

What decides whether your Gemini API data trains Google's models, and the one exception on the paid tier

Whether your Gemini API prompts feed model training is not settled by the paid tier alone. Here is how AI Studio and the API define paid differently, how dataset sharing reverses the protection, and what changes by region.

Gemini API/2026-08-27Intermediate

Record what you send before you try to measure whether temperature still works

Deprecated sampling parameters still return 200 and are silently ignored. Here is how a runtime recorder caught the call sites grep and AST both missed, kept the construction site attached to each config, and turned the ledger into a CI gate.

Gemini Dev/2026-08-24Beginner

Gemini quietly drops %1$s from translations, and no reviewer catches it

Format specifiers go missing, turn full-width, or get duplicated when Gemini translates app strings. Here are the four failure modes I keep seeing in production, how to stop them at generation time, and a short check that catches the rest.

Gemini Dev/2026-08-22Intermediate

The One Call I Refuse to Hand Gemini During a Phased Release

Day one of a phased release has nowhere near the sample size to tell a healthy build from a broken one. Here is the three-state rollout gate I use, and the narrow job I give Gemini inside it.

Gemini Dev/2026-08-21Beginner

How Many Assistant-Dependent Lines Are Still in Your App?

On September 4th, Google Assistant on Android begins its replacement by Gemini. Here is how to grep your own project for every entry point an assistant can open, and how to turn that list into utterances you can actually test on a device.

Gemini Dev/2026-08-20Beginner

A minimal pre-send guard for Gemini-drafted app review replies

Store replies are risky after you hit send, not before. Here is a short Python guard that blocks unkeepable promises, leaked contact details, and register slips, plus the two false positives it produced on the first run.

Updates/2026-08-18Advanced

The Assistant Switch Is One-Way, So the Baseline Has to Be Captured Now

From September 4, Google Assistant is replaced by Gemini, and a device that has switched cannot go back. Here is how I started recording voice-originated launches inside my own apps, and the assumption about splitting before and after by date that turned out to be wrong.