标签：#Gemini

Gemini 3.8 Flash is interesting to me for a slightly unusual reason. It didn’t get a dramatically larger context window. It didn’t suddenly become a different class of model. Instead, Google seems to have spent most of the upgrade budget on something that matters more in real agent workflows: making the model stick with difficult tasks for longer. Gemini 3.7 Flash already had a 1M-token context window. Gemini 3.8 Flash keeps roughly the same context envelope, with up to 1,048,576 input tokens and 65,536 output tokens. So if you’re looking at 3.8 purely because the model number is higher, I don’t think that’s a good enough reason to migrate. The more interesting question is whether your workload benefits from a model that reasons longer, calls tools more persistently, and is more willing to recover when the first attempt doesn’t work. The upgrade is mostly behavioral This is the part I find more useful than the spec sheet. Imagine a coding agent working through a real repository. It might need to inspect several files, make an edit, run the tests, discover that something broke, read the error, change its approach, and try again. A weaker agent can look good for the first few steps and then quietly fall apart once the workflow gets messy. Gemini 3.8 Flash is clearly aimed more at that second half of the task. Google reports 73.7% on DeepSWE v1.1, compared with 65.3% for Gemini 3.7 Flash. That’s a meaningful jump, but the benchmark itself is less interesting to me than what it suggests: the Flash tier is becoming much more capable at completing longer coding workflows rather than just producing good first-pass answers. That changes where I’d consider using it. “Flash” doesn’t mean what it used to I still instinctively associate Flash models with cheap, fast requests. Classification. Extraction. Simple summaries. High-volume API traffic. Gemini 3.8 Flash makes that mental model less useful. It can take text, images, video, audio, and PDFs as input, while also working wi

This is a submission for Weekend Challenge: Generosity Edition What I Built Community Solar Energy Bank is a platform that lets people and businesses with residential or commercial solar panels donate their surplus energy credits directly to low-income families in Brazil, through NGOs connected to each family's utility company. The idea: in Brazil's net-metering system, a solar panel owner who generates more than they use accumulates credits with their utility company, credits that often just sit there, underused. At the same time, low-income families served by the very same utility struggle with expensive electricity bills. This project connects the two without anyone touching real money, you're not buying anything, you're redirecting energy credit you already own. I wanted the project to be upfront about what's real and what's a demo. States and utility companies are real data (Light in RJ, Enel in SP/CE/GO, Cemig in MG, Equatorial in MA/PA/PI, Amazonas Energia in AM, Roraima Energia in RR, Neoenergia Pernambuco in PE), though coverage is deliberately partial, states without a registered utility show an honest empty state instead of fake data. NGOs are entirely fictional, and every card says so. No real money or energy transfer happens anywhere, the donation flow is a simulation end to end. Demo Live demo: https://solar-credit-exchange.vercel.app Flow: pick your state on the map, choose the utility company serving it, pick an NGO linked to that utility, enter how many kWh of surplus credit you want to donate, review an AI-generated checklist of what that utility typically requires, confirm, and see it reflected on the aggregated impact dashboard. Code claudiofilho87 / solar-credit-exchange Community Solar Energy Bank A demo platform that lets people and businesses donate their surplus solar energy credits directly to low-income families served by NGOs in Brazil. Built for the DEV Weekend Challenge: Generosity Edition hackathon. This is a hackathon demo. No real ut

This is a submission for Weekend Challenge: Generosity Edition I wanted to build something for this challenge that didn't just talk about generosity but actually meant something, and felt beneficial. This tool can make it easier to go from "I have food to donate" to "I'm donating food". You take a picture of your pantry shelf, Gemini figures out what's actually in it, and the app turns that into a recipe for whoever receives it, a handwritten-style note of kindness, a real way to find a food bank near you, and a printable manifest to hand over at drop-off. What I Built PantryBridge is a small AI-powered toolkit for food donation. The flow is: 1. Scan your pantry. Upload a photo (or pick one of three one-click sample hauls if you don't have a pantry photo handy). Gemini does multimodal image analysis and returns a structured inventory: item names, categories, estimated quantities, dietary tags, urgency, and packaging condition. ( Sorry, GIPHY messed up my gif ) 2. Review the inventory. Everything shows up in a clean table with donation-readiness stats and a volunteer tip generated specifically for that haul. (If you need to, you can delete or add items!) 3. Find a real drop-off location. Enter your zip code and the app confirms your city/state (via a real geocoding lookup) and links you straight to Feeding America's actual food bank locator, so you're finding a real place to donate, not a mock one. 4. Get a recipe and a kindness note. Gemini writes a short recipe using mostly what you're donating, plus a genuinely warm, non-patronizing note to include with the box. 5. Print a donation manifest. A little printable card with the itemized contents and a mock barcode/QR for quick intake logging, with confetti when you pledge or print. Demo Try the Live App If you'd rather run it yourself: git clone https://github.com/780s/pantrybridge.git cd pantrybridge npm install npm run dev Drop a GEMINI_API_KEY into .env.local to hit the real Gemini API. Without one, every route qui

This is a submission for Weekend Challenge: Generosity Edition What I Built Handover takes a plain description of what is going wrong inside a small charity and works out the role that would fix it. Not the role they asked for. The one they actually need. You type something like "our books are a mess, and we have missed two filing deadlines". It comes back with a full trustee role: the diagnosis, what the person would do, a deliberately short list of essential skills, an honest time commitment, and an advert you can paste straight into your newsletter. Then a volunteer pastes their CV, badly, and gets scored against every open role with a reason and an honest note on where the fit is thin. Why A couple of days ago I got an email saying Reach Volunteering is closing after 45 years. It genuinely hurt to read. Reach connected small UK charities with people who wanted to give them professional skills. Last year it placed 5,996 volunteers and trustees across 2,440 organisations. The people it placed contributed around £60 million in expertise. Ninety-six per cent of those organisations ran on under £1 million a year, and nearly half on under £50,000. It is not closing because the work stopped mattering. It is closing because funding for the infrastructure that helps small charities build capacity has dried up. Reach was the largest single source of trustees in the sector, and it is shutting at the peak of its impact. I volunteer as a digital navigator, which mostly means sitting with people who have been handed a system that assumes a confidence nobody ever gave them. You watch someone decide they are the problem, when the thing in front of them was just badly built. Reach existed to stop small charities from feeling like that about their own gaps, and now it is shutting down. I cannot rebuild 45 years of relationships in a weekend. So I picked the one piece of what Reach did that was pure expertise rather than headcount, and rebuilt that. The thing everyone gets wrong E

This is a submission for Weekend Challenge: Generosity Edition What I Built Karibu Give (Swahili for Welcome, Give ) is a USSD micro-donation platform that works on a kabambe phone(feature phone) with no data, no app, no account , just a phone number and a mobile-money PIN. Built for the International Day of Charity. Two things stop generosity from scaling in Kenya and across Africa: You need a smartphone to give. Most donation platforms are web-forms that assume Chrome, data bundles, and card rails. 40% of Kenyan adults still use feature phones. You need trust to give again. Donations disappear into a black box. Donors never see where 50 KES actually went. Karibu Give attacks both: Dial *384*6120# → 1. Donate → Pick a cause → Enter 50 → Confirm → M-Pesa STK prompt in 2 seconds. No internet, no app store, no signup. Session state is managed server-side via sessionId (Africa's Talking USSD callback at POST /ussd ). Real M-Pesa money movement — STK Push is triggered via my dedicated M-Pesa Service https://mpesa-service-3s2d.onrender.com/stkpush , which wraps Daraja API ( POST {phone:"2547...", amount} → CheckoutRequestID:"ws_CO_..." ). SQLite = source of truth, Snowflake = audit trail — every pending → completed/failed transition via POST /payment-callback ( Body.stkCallback.CheckoutRequestID Daraja shape + AT shape) is synced to DONATIONS_ANALYTICS in Snowflake with phone_hash = SHA256(phone).slice(0,16) , never raw PII. POST /admin/sync-snowflake batch-retries unsynced rows. Only 3 causes can be active at a time — admin ( /admin behind ADMIN_USER/PASSWORD Basic Auth) creates charities ( name, emoji, target_amount, description ), toggles active, edits, deletes (blocked if donations exist). USSD and landing page render only active causes , so the choice stays focused. The limit is enforced in SQLite ( countActive()<3 ) and in the UI ( Activate disables at 3/3). Two separate AI cards — not one bolted-on feature: ✨ Google AI Impact Summary (Gemini 1.5 Flash via @google/

This is a submission for Weekend Challenge: Generosity Edition What I Built My late...

The first version of a RAG system always looks convincing. You connect a document loader, a vector database, and a large model, ask a question, and the answer comes back with impressive confidence. Then production happens. A support agent asks about a refund policy that changed last week, and the bot answers with the old policy. A user from the finance team sees chunks they should never see. Gemini starts returning 429 errors during a reindex. A 3,000-document ingestion workflow fails at document 2,412, and you have no idea how to resume safely. That is the gap between a RAG demo and a production RAG pipeline. This walkthrough focuses on building a maintainable retrieval-augmented generation pipeline using n8n for orchestration, Qdrant for vector storage and filtered retrieval, and Gemini for embedding and answer generation. The goal is not just “make it answer.” The goal is to make it operable: idempotent ingestion, access-controlled retrieval, retry-safe automation, grounded answers, and a path for evaluation. TL;DR Treat RAG as two separate pipelines : ingestion and query. Store more than vectors in Qdrant: source_id , acl , version , updated_at , chunk_index , and text. Make ingestion idempotent so reprocessing documents does not create duplicate truth. Use Qdrant filters for permissions, freshness, and document status. Force Gemini to answer only from retrieved evidence and return citations. Add retries, timeouts, dead-letter handling, and evaluation before users do the testing for you. 📋 Table of Contents The Production Problem with Demo RAG 1. Split RAG Into Two Pipelines Before You Automate Anything 2. Design the Qdrant Collection Around Access Control and Freshness 3. Chunk for Retrieval, Not for Reading 4. Make Ingestion Idempotent and Resumable 5. Embed in Controlled Batches Without Dropping Documents 6. Retrieve With Filters, Not Blind Similarity 7. Make Gemini Prove It Used the Evidence 8. Add the Production Guardrails: Retries, Timeouts, and Dead Lette

The sheriff’s office said the hikers “were advised by Gemini to bring far less food and water than their group required."

Adding citations to an AI answer feels like the moment the system becomes trustworthy. The response looks researched. Source links appear beside the text. The model is no longer answering only from its training data. But a cited answer can still be wrong. A citation may support a nearby sentence rather than the claim the user cares about. A source may be authoritative while the retrieved passage is stale. File Search may query the wrong store or document version. The model may retrieve good evidence and then write a conclusion that goes beyond it. Grounding is a capability. Trust still requires an application contract. Series note: This is Part 6 of Reliable Google AI Agents in TypeScript . The Interactions API examples use its post-May-2026 steps schema and were checked against @google/genai 2.21.0. The API remains beta, so pin and retest the SDK before copying production code. Retrieval success is not answer success Gemini can ground responses with Google Search for current public information and File Search for indexed domain-specific documents. The Interactions API exposes the execution steps and inline citation annotations, giving the application more evidence than a text completion alone. A minimal Google Search interaction looks like this: import { GoogleGenAI } from " @google/genai " ; const ai = new GoogleGenAI ({}); const interaction = await ai . interactions . create ({ model : process . env . GEMINI_MODEL ?? " gemini-3.8-flash " , input : " What changed in the public policy this week? " , tools : [{ type : " google_search " }], }); The synthesized text is only one part of the result. The steps show whether search occurred and where citations attach. type Citation = { title ?: string ; url ?: string ; citedText : string ; }; const citations : Citation [] = []; for ( const step of interaction . steps ?? []) { if ( step . type !== " model_output " ) continue ; for ( const contentBlock of step . content ?? []) { if ( contentBlock . type !== " text " ) contin

Gemini Spark can edit and curate photo albums, create shared collections, turn photos into calendar events, and handle other Google Photos tasks for AI Pro and Ultra subscribers.

Users can search for emails or draft documents using the new conversational feature

Mixing Gemini and Claude for better code The single-agent mirage A few weeks ago, I started building an app called PhrasePulse to visualize some data I was tracking. To speed things up, I spun up a single Gemini agent using the Gemini Enterprise Agent Platform (an agentic development platform that I absolutely love). At first, it felt like magic. I asked the agent to build a graph showing when specific phrases popped up in my datasets. The results came back and they were flawless. The graph looked exactly like I had envisioned. I was practically ready to declare victory and ship it. But then, the illusion shattered. I decided to pass a totally different set of words into the graph just to double-check the logic. I refreshed the page and... nothing changed. Different words, exact same output metrics. I rolled up my sleeves, dug into the codebase myself, and discovered the frustrating truth. The agent hadn't actually written the dynamic logic to solve my problem. Instead, it had simply hardcoded the results to make the graph look perfect for my initial test case! It was optimizing for a quick pat on the back rather than building a robust solution. Darn it. I realized right then that having an AI write code is great, but without critical friction, it's just going to tell you what you want to hear. I didn't just need a coder anymore, I needed an architect to keep my coder honest. Assembling the Bridge Deck To fix this hardcoding habit, I realized I needed two distinct roles: one agent to write the code, and another to ruthlessly review it. But first, I needed an environment where we could all collaborate. I wanted a customized chat room where every piece of communication was totally visible to me. I had my original Gemini agent build a local app that I dubbed the Bridge Deck . Once it was up and running, I dropped myself and two new Gemini agents into the mix. To make sure they didn't step on each other's toes, I gave them highly specific, boundaried personas: "You are

Google's Pro model updates are seemingly paused, but there's yet another Gemini Flash today.

I wrote this post for my entry to the All Things Agentic Hackathon. TLDR: I built a five-agent design team on Gemini (Including Gemini Flash 3.7 and Gemma 4) that takes a brief and a folder of photographs and returns finished, editable pages. The interesting engineering was not the prompts. It was deciding wh ere the run's progress lives. Code: github.com/minhthanhdang/vibes-ai . What it does Vibes AI is a design co-pilot. Upload photographs, describe what the thing is for, and it designs the pages: real crops, generated backgrounds, type in any Google Fonts family, all written as geometry that can be dragged afterwards. There are five agents. An orchestrator holds the other four as tools, so every hop is request and response, and the user reads one reply instead of a transcript of agents talking to each other. A property analyzer reads each upload in six design dimensions. An image editor cuts. An image generator draws the picture the gallery does not have. A design assistant does the actual designing. The part I want to write about is the unattended run. One form (purpose, page count, palette, vibe, size) and then no further human input until the pages are done. One long request was the wrong shape Designing six pages is minutes of model calls, not milliseconds. My first instinct was one request that loops over the pages and returns when it is finished. That shape gives nothing back. No honest progress, no Stop button that means anything, and a failure at page four throws away pages one to three. So a page became the unit of work. One job designs one page. The job is a row in an AgentRun table, a worker claims it under a lease, and when it settles it enqueues the next page inside the same transaction that marks the current one done: const chained = await db . $transaction ( async ( tx ) => { const won = await tx . agentRun . updateMany ({ where : { id : run . id , status : RunStatus . RUNNING , startedAt : run . claimedAt }, data : { status : RunStatus . SUCCEEDED

Gemini function calling makes tool use look simple. You describe a function, provide its input schema, and let the model decide whether the user's request requires it. A traveler asks, "Find hotels in Paris under $250," Gemini requests search_hotels , your application executes it, and the model turns the result into a useful answer. That is an important capability, but it is not an agent runtime. Function calling tells your application what the model proposes to do. It does not decide whether the action is authorized, whether the arguments are trustworthy, whether the same action already succeeded, or whether a retry would make the situation worse. The model proposes. The runtime disposes. What Gemini actually gives you With the Google Gen AI SDK, a function declaration can look like this: import { GoogleGenAI , Type } from " @google/genai " ; const ai = new GoogleGenAI ({ apiKey : process . env . GEMINI_API_KEY , }); const searchHotels = { name : " search_hotels " , description : " Search available hotels in a city under an optional nightly price " , parameters : { type : Type . OBJECT , properties : { city : { type : Type . STRING , description : " City and country, for example Paris, France " , }, maxNightlyPriceUsd : { type : Type . NUMBER , description : " Maximum nightly price in US dollars " , }, }, required : [ " city " ], }, }; const response = await ai . models . generateContent ({ model : " gemini-2.5-flash " , contents : " Find hotels in Paris under $250 per night " , config : { tools : [{ functionDeclarations : [ searchHotels ] }], }, }); const proposedCall = response . functionCalls ?.[ 0 ]; The returned function call contains a name and structured arguments. Google is explicit about the next boundary: the model does not execute your business function. Your application is responsible for executing it and returning the result. That boundary is where production engineering begins. User request │ ▼ Gemini proposes a function call │ ▼ Schema validation → a

Waymo has launched Gemini in Waymo , a beta in-car conversational assistant for riders using its Ojai robotaxi experience . Accessed through a Gemini icon on the cabin screen, the feature lets riders use natural language and voice to adjust parts of the cabin, ask about their journey and get information about nearby places or broader topics. The important boundary is clear: Gemini is a rider-facing assistant, not part of the autonomous driving system. Waymo Driver continues to control the vehicle , while Gemini operates separately and does not influence driving decisions. For riders, the integration turns the cabin display into a more conversational interface. For the wider automotive market, it is a concrete example of generative AI being deployed inside a commercial mobility service without being assigned responsibility for vehicle control. Waymo describes the feature in its official Gemini in Waymo announcement . The company says Gemini stays inactive until a rider chooses to engage it. It does not access real-time driving data unless the rider explicitly asks for information related to the ride. What Gemini in Waymo can do today Gemini in Waymo is designed around requests that are useful during a trip, rather than around autonomous navigation. A rider can tap or press the Gemini icon and speak to the assistant. The initial beta supports interactions such as: Cabin-control requests , including asking to set the air conditioning to a specified temperature. Ride-related questions , such as seeking information about the current journey. Information about surroundings , including questions about local sites. General knowledge queries through a hands-free conversational interface . This scope matters because it places Gemini in the passenger experience layer. The assistant can make a ride feel more responsive without creating confusion about which system is responsible for safety-critical driving functions. Area Gemini in Waymo Waymo Driver Primary role Rider-facing c

Google has introduced a dedicated Student Hub in the Gemini ecosystem , bringing study notebooks, flashcards and interactive practice quizzes into one in-app space. The central idea is to connect a learner's course materials with Gemini's AI tools, reducing the work of moving between separate note-taking, revision and question-generation tools. The official Gemini for Students page presents the hub as a gateway to Gemini's education-focused capabilities. It is part of a broader Google education AI initiative that also involves NotebookLM and Google for Education resources, rather than a standalone feature with no connection to the rest of Google's products. For students, the practical value is straightforward: uploaded learning materials can become organized revision assets. For businesses that create internal training or support education programs, the release is also a useful example of how generative AI can consolidate material preparation, knowledge review and self-assessment into a more connected workflow. Google has not, however, confirmed a specific learning management system integration in the supplied materials. How Gemini Student Hub connects learning materials and AI tools The Student Hub is designed as a dedicated space where courses and content connect with Gemini. Its core tools include a study notebook, flashcard creation and quick practice quizzes. Google says Gemini notebooks can take uploaded course materials, including PDFs, slides and notes, and generate study aids such as flashcards, quizzes and study guides. A significant detail is the use of inline citations to user-provided sources for those generated materials. That does not remove the need for learners to check the results, but it gives them a way to trace an AI-produced prompt or explanation back to the material they uploaded. In a learning workflow, that is more useful than treating a general-purpose chatbot response as an unanchored answer. NotebookLM is an important part of the wider wo

Google is offering eligible college students in the United States 12 months of Google AI Pro at no charge . The offer, announced on August 19, 2026, gives students access to the paid Gemini plan that Google values at $19.99 per month. It is redeemable through December 31, 2026, and standard Google AI Pro pricing applies after the free year unless the student cancels. The program is aimed at academic work, but it also matters for the wider Gemini ecosystem . It puts higher-capacity AI tools, Google app integrations and substantial cloud storage in the hands of students who may carry those workflows into internships, startups and future workplaces. For businesses, the immediate lesson is not that Google has announced a broader pricing reduction. It has not. Rather, teams should expect more new users to become familiar with Gemini and the ways it connects with everyday Google tools. What Google AI Pro includes for eligible US students According to Google's official student offer announcement , eligible US college students who claim the promotion receive one year of Google AI Pro. Google says the plan includes four times higher usage limits within Gemini , Gemini Spark, integrations with Google apps such as Gmail and Docs , and 5 TB of Google One storage. Google has also introduced a student hub in the Gemini app for participating students. The hub is intended to support learning with features including study notebooks and Deep Research in Gemini Live. These tools are presented as part of a student-focused experience, rather than as a separate business plan or a new API offering. The distinction matters. Access to Gemini through this offer does not, by itself, establish access to every Google AI product or developer service. Students and organizations considering Gemini for a particular workflow should check the relevant product terms and capabilities rather than assuming that an app subscription covers all Google AI services. Offer detail Eligible college students in t

Previously I have a macOS App I use myself, gemini-live-translate-macos . It uses ScreenCaptureKit to directly capture audio from a specified App, eliminating the need for virtual sound cards like BlackHole. It then sends the audio to the Gemini Live API for real-time translation, outputting Traditional Chinese subtitles while playing Chinese audio. I've written two posts about the development process: the first one was about building it from scratch using AGY CLI, and the second one was about using Claude Code to take it from "functional" to "user-friendly." The starting point for this new addition was simple: I saw a document for "Real-time Transcription" added to the Live API. Since I was already connected to the Live API, I thought adding a pure transcription mode would just be a matter of changing a few parameters. However, after checking the documentation, I realized that Google released two models with very similar names but very different capabilities at once. The specific feature I actually wanted (speaker diarization) wasn't available at all on the model I originally thought it was. Two Models with Names Differing by Only Two Words Let's lay out the differences first; this is the part I spent the most time figuring out: gemini-3.5-transcribe-live gemini-3.5-transcribe API Used Live API (WebSocket streaming) Interactions API (Standard HTTP request) Usage Scenario Transcribe while speaking Upload the whole file after recording Speaker Diarization Not supported Up to 8 speakers Word-level Timestamps Not supported Supported Audio Length 10 minutes per session 1 hour (30 mins with diarization) Smart Mode SMART available smart is mutually exclusive with diarization Interim Subtitles Has interimInputTranscription Not applicable The official documentation on the Live page's limitations section is very blunt: Speaker diarization is not supported in live streaming sessions. For speaker diarization, use the non-streaming Audio transcription endpoint. So, "seeing who

Google has introduced a new interactive visualization capability in the Gemini app that can turn questions and complex topics into manipulable models and simulations inside a chat. Rather than returning only a written explanation or a static illustration, Gemini can create visuals that users explore through prompts and on-screen controls. The update is designed to make concepts easier to investigate in context. Google describes examples including rotating molecular structures and physics simulations where users can adjust variables such as initial velocity and gravity to see the results immediately. That shift from a fixed diagram to a live, prompt-driven model is the important change for people using Gemini to learn, explain, or test an idea. From static diagrams to interactive models In its April 9, 2026, official announcement of interactive simulations and models , Google said the Gemini app can generate custom visualizations directly within a conversation. Users can ask Gemini to “show me” or “help me visualize” a concept after selecting the Pro model in the prompt bar. The capability is rolling out globally to Gemini app users. Google also notes an important availability limitation: it is not yet available for Education and Workspace accounts . The announcement identifies the Pro model as the route to access the feature, but it does not set out pricing details for this specific visualization capability. The practical elements Google has confirmed are: Interactive simulations and models generated within the Gemini chat experience. Prompt-based requests to visualize a question or concept. Direct manipulation of visual variables and controls, including sliders in relevant simulations. A global rollout for Gemini app users, excluding Education and Workspace accounts for now. Approach Static diagram or written answer Gemini interactive visualization How users explore a topic Read or view a fixed explanation Manipulate a model within the chat Changing assumptions Req