Techlist.io - Korean Tech Blog Curator

figmaOct 6, 20252 min readCurated summary

6 Winning Figma Makes—and What You Can Learn From Them | Figma Blog

Figma’s first global Make-a-thon demonstrated how Figma Make can turn ideas into interactive prototypes quickly. More than 10,000 creators competed for $100,000 in prizes, and the winning projects were judged on creativity, innovation, execution, and prompt quality. The featured lesson is that creators should define an app’s structure and technical foundations—not merely describe the task. ## Make-a-thon and Figma Make - Figma Make is designed to bridge the gap between concepts and working, interactive creations. - The competition was held in partnership with Contra. - Entries ranged from a *Severance*-themed virtual escape room to a “Figma-Kart” racing game. - Winners showed how thoughtful prompting and experimentation can extend the tool beyond basic prototypes. ## Define the Structure, Not Just the Task - Second-place winner Sebastian Lumbi created a frame-by-frame SVG animation tool. - The app lets users: - Copy SVGs from Figma into the tool. - Build animations frame by frame. - Preview and export animations as GIFs. - His initial prompt described the product’s structure: a canvas at the top for drawing frames and a timeline below for viewing and adding frames. - Sebastian researched state management and component interaction before developing the app. - He used an iterative dialogue with the AI, beginning with two prompts and eventually adding roughly 80 more. - Figma Make’s revert feature allowed him to experiment safely and return to earlier versions when bugs or crashes occurred. ## Technical Understanding Improves AI-Generated Code - Even non-programmers benefit from understanding basic concepts relevant to their application. - Clear instructions about structure make generated code easier to debug and extend. - When technical decisions are unclear, creators can consult another AI for recommendations. - The main lesson is to establish the application’s architecture early, then use iterative prompts to refine features and solve problems. A practical approach is to describe the app’s components, state, and interactions up front, while treating AI generation as an iterative process with frequent testing and rollback.

Read original

Prototyping Figma Make Svg Animation+2

discordOct 6, 20252 min readCurated summary

New Looks for Nitro, New Looks for You. Get Yourself a Nitro-exclusive Profile Bundle!

Discord is refreshing Nitro with a space-themed visual identity featuring dark blurple and teal colors, plus a redesigned Nitro webpage and updated Wumpus branding. To celebrate Nitro members, Discord is offering a limited-edition Jet Pack Profile Bundle containing profile customization items. The bundle can be claimed on desktop through September 30, 2025, by active Nitro members, including new subscribers and trial users. ## Nitro’s Expanded Benefits and New Visual Identity - Nitro began in 2017 with four core perks: - Animated avatars - Custom emoji use everywhere - Larger file uploads - A profile badge - It has since grown to nearly 20 features, including: - HD streaming - Global access to stickers and soundboard sounds - Custom Themes - The refreshed Nitro branding uses: - Deep Discord blurple tones - Moody teal accents - A space-inspired aesthetic - An updated Wumpus featuring a jetpack ## Limited-Edition Jet Pack Profile Bundle - The bundle includes: - An Avatar Decoration - A Profile Effect - A Nameplate - Its pulsing jet flame frames the avatar without obscuring it. - The dark blurple design is intended to complement different avatars, banners, and profile color schemes. - The items remain available for use while the user has an active Nitro subscription. ## Eligibility and Claiming the Bundle - Current Nitro members, new members, and users on Nitro trials can claim the bundle. - Users who subscribe during the promotion are also eligible. - The bundle must be claimed on desktop by September 30, 2025. - It can be claimed through **User Settings > Nitro** or Discord’s profile store. - If a member later cancels Nitro, the set remains available and can be used again if they resubscribe. Nitro members should claim the bundle before the deadline through Discord’s desktop app, since the offer is time-limited even though claimed items remain tied to their account.

Read original

Discord Desktop App Profile Customization Custom Themes+1

googleOct 6, 2025Original article

Speech-to-Retrieval (S2R): A new approach to voice search (opens in new tab)

Google Research has introduced Speech-to-Retrieval (S2R), a direct speech-to-intent engine designed to overcome the fundamental limitations of traditional cascade-based voice search. By bypassing the error-prone intermediate step of text transcription, S2R significantly reduces information loss and prevents minor phonetic errors from derailing search accuracy. This shift from identifying literal words to understanding underlying intent represents an architectural change that promises faster and more reliable search experiences globally. ## Limitations of Cascade Modeling * Traditional systems rely on Automatic Speech Recognition (ASR) to convert audio into a text string before passing it to a search engine. * This "cascade" approach suffers from error propagation, where a single phonetic mistake—such as transcribing "The Scream painting" as "The Screen painting"—leads to entirely irrelevant search results. * Textual transcription often results in information loss, as the system may strip away vocal nuances or contextual cues that could help disambiguate the user's actual intent. ## The S2R Architectural Shift * S2R interprets and retrieves information directly from spoken queries, treating the audio as the primary source of intent rather than a precursor to text. * The system shifts the technical focus from "What words were said?" to "What information is being sought?", allowing the model to bridge the quality gap between current voice search and human-level understanding. * This approach is designed to be more robust across different languages and audio conditions by mapping speech features directly to a retrieval space. ## Evaluating Performance with the SVQ Dataset * Researchers used Mean Reciprocal Rank (MRR) to evaluate search effectiveness, comparing real-world ASR systems against "Cascade Groundtruth" models that use perfect, human-verified text. * The study found that Word Error Rate (WER) is often a poor predictor of search success; a lower WER does not always result in a higher MRR, as the nature of the error matters more than the frequency. * To facilitate further research, Google has open-sourced the Simple Voice Questions (SVQ) dataset, which includes audio queries in 17 languages and 26 locales. * The SVQ dataset is integrated into the new Massive Sound Embedding Benchmark (MSEB) to provide a standardized way to measure direct speech-to-intent performance. The transition to Speech-to-Retrieval signifies a major evolution in how AI handles human voice. For developers and researchers, the release of the SVQ dataset and the focus on MRR over traditional transcription metrics provide a new roadmap for building voice interfaces that are resilient to the phonetic ambiguities of natural speech.

Information Retrieval Speech To Retrieval Voice Search Automatic Speech Recognition+3

discordOct 6, 2025Original article

Discord Update: September 25, 2025 Changelog (opens in new tab)

Discord’s September 2025 update focuses on enhancing user expression and scaling server infrastructure to unprecedented levels. By introducing massive server capacity increases and highly customizable interface features, the platform aims to better support its largest communities and most active power users. Ultimately, these changes provide a more dynamic social experience through improved profile visibility, expanded pin limits, and flexible multitasking tools. ### Enhanced User Profiles and Multitasking - Desktop profiles now feature a refreshed layout designed to showcase a user's current activities and history more clearly. - Multiple concurrent activities, such as playing a game while listening to music in a voice channel, are now displayed as a "stack of cards" on the profile. - Activities can be moved into a pop-out floating window, allowing users to participate in shared experiences like "Watch Together" while navigating other servers or DMs. - A new audio cue now plays whenever a user turns their camera on to provide immediate feedback that their video stream is live. ### Massive Scaling and Embed Improvements - The default server member cap has been increased to 25 million, supported by engineering optimizations to member list loading speeds for "super-super-large" communities. - The channel pin limit has been expanded fivefold, moving from a 50-message cap to 250 messages per channel. - Native support for AV1 video attachments and embeds was integrated to improve video quality and loading performance. - Tumblr link embeds have been overhauled to include detailed descriptions and metadata for hashtags used in the original post. ### Custom Themes and Aesthetic Upgrades - Nitro users can now create custom gradient themes using up to five different colors, a feature that synchronizes across both desktop and mobile clients. - Two new Server Tag badge packs—the Pet pack and the Flex pack—introduce new iconography for server roles, including animal icons and royalty-themed badges. - Visual updates were made to Group DM icons, which the development team refers to as "facepiles," to better represent groups of friends in the chat list. Users should explore the new custom gradient settings in their Nitro preferences to personalize their workspace and take advantage of the expanded pin limits to better manage information in high-traffic channels.

User Interface Performance Optimization Desktop App Scalability+4

figmaOct 5, 20252 min readCurated summary

Turn Your ChatGPT Brainstorms Into FigJam Diagrams | Figma Blog

Figma’s new ChatGPT app turns brainstorms, sketches, uploaded files, and technical documents into editable FigJam diagrams. It supports flowcharts, sequence and state diagrams, and Gantt charts, helping users move quickly from exploration to collaborative artifacts. The feature is powered by Figma’s remote MCP server and is available to logged-in ChatGPT users outside the EU. ## Turning Conversations into Diagrams - Users can mention Figma in a prompt, such as “Figma, make a diagram from this sketch.” - ChatGPT can recommend the Figma app when diagramming is relevant. - Photos, drawings, PDFs, and other files can provide context. - Generated diagrams can be revised, expanded, or represented in alternative formats. - Figma plans to add more diagram types over time. ## Accelerating Design Iteration - Hand-drawn sketches can become shareable FigJam files. - Designers can ask ChatGPT to update diagrams or explore different visualizations. - Dense documents can be uploaded so ChatGPT can produce an initial draft. - This helps teams move ideas from informal notes or whiteboards into a collaborative workspace. ## Clarifying Technical Systems - Developers can use uploaded documentation and screenshots to create or update software architecture diagrams. - ChatGPT can research technical approaches using blogs and case studies, then visualize them. - Screenshots, such as a pricing page, can be used to map likely React component structures. - The resulting diagrams support system design discussions, technical communication, and interview preparation. ## Planning Products and User Experiences - Product managers can visualize tradeoffs, such as simplicity versus power in a permissions flow. - PRDs can be converted into user journey or process flowcharts. - Product, engineering, and design requirements can be combined into Gantt charts for launch planning. - ChatGPT supports individual exploration, while FigJam enables teams to review and iterate together. The feature is currently live for logged-in ChatGPT users outside the EU. It offers a practical workflow for using ChatGPT to generate a first visual draft and FigJam to refine, discuss, and collaborate on it.

Read original

Figma Figjam React Chatgpt+4

lineOct 3, 2025Original article

A month-long project in (opens in new tab)

This blog post explores how LY Corporation reduced a month-long development task to just five days by leveraging "vibe coding" with Generative AI tools like ChatGPT and Cursor. By shifting from traditional, rigid documentation to an iterative, demo-first approach, developers can rapidly validate multiple UI/UX solutions for complex problems like restaurant menu registration. The author concludes that AI's ability to handle frequent re-work makes it more efficient to "build fast and iterate" than to aim for perfection through long-form specifications. ### Strategic Shift to Rapid Prototyping * Traditional development cycles (spec → design → dev → fix) are often too slow to keep up with market trends due to heavy documentation and impact analysis. * The "vibe coding" approach prioritizes creating "working demos" over perfect specifications to find "good enough" answers through rapid feedback loops. * AI reduces the psychological and logistical burden of "starting over," allowing developers to refine the context and quality of outputs through repeated interaction without the friction of manual re-documentation. ### Defining Requirements and Solution Ideation * Initial requirements are kept minimal, focusing only on the core mission, top priorities, and essential data structures (e.g., product name, image, description) to avoid limiting AI creativity. * ChatGPT is used to generate a wide range of solution candidates, which are then filtered into five distinct approaches: Stepper Wizards, Live Previews with Quick Add, Template/Cloning, Chat Input, and OCR-based photo scanning. * This stage emphasizes volume and variety, using AI-generated pros and cons to establish selection criteria and identify potential UX bottlenecks early in the process. ### Detailed Design and Multi-Solution Wireframing * Each of the five chosen solutions is expanded into detailed screen flows and UI elements, such as progress bars, bottom sheets, and validation logic. * Prompt engineering is used iteratively; if an AI-generated result lacks a specific feature like "temporary storage" or "mandatory field validation," the prompt is adjusted to regenerate the design instantly. * The focus remains on defining the "what" (UI elements) and "how" (user flow) through textual descriptions before moving to actual coding. ### Implementation with Cursor and Flutter * Cursor is utilized to generate functional code based on the refined wireframes, using Flutter as the framework to ensure rapid cross-platform development for both iOS and Android. * The development follows a "skeleton-first" approach: first creating a main navigation hub with five entry points, then populating each individual solution module one by one. * Technical architecture decisions, such as using Riverpod for state management or SQLite for data storage, are layered onto the demo post-hoc, reversing the traditional "stack-first" development order to prioritize functional validation. ### Recommendation To maximize efficiency, developers should treat AI as a partner for high-speed iteration rather than a one-shot tool. By focusing on creating functional demos quickly and refining them through direct feedback, teams can bypass the bottlenecks of traditional software requirements and deliver user-centric products in a fraction of the time.

AI Large Language Models Generative AI Prompt Engineering+5

lineOct 3, 2025Original article

IUI 202 (opens in new tab)

The IUI 2025 conference highlighted a significant shift in the AI landscape, moving away from a sole focus on model performance toward "human-centered AI" that prioritizes collaboration, ethics, and user agency. The prevailing consensus across key sessions suggests that for AI to be sustainable and trustworthy, it must transcend simple automation to become a tool that augments human perception and decision-making through transparent, interactive, and socially aware design. ## Reality Design and Human Augmentation The concept of "Reality Design" suggests that Human-Computer Interaction (HCI) research must expand beyond screen-based interfaces to design reality itself. As AI, sensors, and wearables become integrated into daily life, technology can be used to directly augment human perception, cognition, and memory. * Memory extension: Systems can record and reconstruct personal experiences, helping users recall details in educational or professional settings. * Sensory augmentation: Technologies like selective hearing or slow-motion visual playback can enhance a user's natural observational powers. * Cognitive balance: While AI can assist with task difficulty (e.g., collaborative Lego building), designers must ensure that automation does not erode the human will to learn or remember, echoing historical warnings about technology-induced "forgetfulness." ## Bridging the Socio-technical Gap in AI Transparency Transparency in AI, particularly for high-risk areas like finance or medicine, should not be limited to showing mathematical model weights. Instead, it must bridge the gap between technical complexity and human understanding by focusing on user goals and social contexts. * Multi-faceted communication: Effective transparency involves model reporting (Model Cards), sharing safety evaluation results, and providing linguistic or visual cues for uncertainty rather than just numerical scores. * Counterfactual explanations: Users gain better trust when they can see how a decision might have changed if specific input conditions were different. * Interaction-based transparency: Transparency must be coupled with control, allowing users to act as "adjusters" who provide feedback that the model then reflects in its future outputs. ## Interactive Machine Learning and Human-in-the-Loop The framework of Interactive Machine Learning (IML) challenges the traditional view of AI as a static black box trained on fixed data. Instead, it proposes an interactive loop where the user and the model grow together through continuous feedback. * User-driven training: Users should be able to inspect model classifications, correct errors, and have those corrections immediately influence the model's learning path. * Beyond automation: This approach reframes AI from a replacement for human labor into a collaborative partner that adapts to specific user behaviors and professional expertise. * Impact on specialized tools: Modern applications include educational platforms where students manipulate data directly and research tools that integrate human intuition into large-scale data analysis. ## Collaborative Systems in Specialized Professional Contexts Practical applications of human-centered AI are being realized in sensitive fields like child counseling, where AI assists experts without replacing the human element. * Counselor-AI transcription: Systems designed for counseling analysis allow AI to handle the heavy lifting of transcription while counselors manage the nuance and contextual editing. * Efficiency through partnership: By focusing on reducing administrative burdens, these systems enable professionals to spend more time on high-level cognitive tasks and emotional support, demonstrating the value of AI as a supportive infrastructure. The future of AI development requires moving beyond isolated technical optimization to embrace the complexity of the human experience. Organizations and developers should focus on creating systems where transparency is a tool for "appropriate trust" and where design is focused on empowering human capabilities rather than simply automating them.

AI Large Language Models Human In The Loop Human Centered Ai+5

dropboxOct 2, 20253 min readCurated summary

A practical blueprint for evaluating conversational AI at scale

Conversational AI systems depend on many probabilistic stages, so even small changes can cause unexpected regressions. Dropbox Dash’s experience shows that evaluation should be treated like production engineering: systematic, repeatable, and required before changes are shipped. The approach combines curated datasets, actionable metrics, LLM-based judging, and human review. ## Evaluation as a Development Discipline - AI pipelines include intent classification, retrieval, ranking, prompt construction, inference, and safety filtering. - Changes to any stage can affect final answer quality in unpredictable ways. - Dropbox initially used ad-hoc testing, but shifted to a standardized process in which every model, prompt, or retrieval change had to pass evaluation before merging. - The evaluation framework covers datasets, metrics, tools, and workflows. - Future-proof evaluation must extend beyond text to images, video, and audio. ## Curating Public and Internal Datasets - Public datasets established baseline retrieval and question-answering performance: - **Natural Questions** tested retrieval from very large documents. - **MS MARCO** emphasized queries requiring multiple document hits. - **MuSiQue** tested multi-hop reasoning. - Internal datasets captured real-world usage from anonymized Dropbox employee queries and content. - Representative query sets reflected actual user behavior, using proxy labels or internal annotators. - Representative content sets focused on shared files, documentation, and connected data sources. - LLM-generated synthetic questions and answers covered tables, images, tutorials, and factual lookups. - These datasets became the foundation for automated pass/fail checks and experiment monitoring. ## Why Traditional Metrics Fall Short - Metrics such as BLEU, ROUGE, METEOR, BERTScore, and embedding similarity are fast and useful for detecting major regressions. - They often fail to measure production requirements, including: - Correct source citations - Factual accuracy - Valid file names and references - Reliable table parsing - Clear formatting - High ROUGE or BERTScore can coexist with hallucinations, missing citations, or buried factual errors. - Production evaluation therefore requires metrics tied directly to task requirements. ## Using LLMs as Evaluation Judges - LLM judges can assess dimensions traditional metrics miss, including: - Whether an answer addresses the query - Whether claims are supported by context - Citation correctness - Clarity, formatting, and tone - Judges receive the query, model answer, source context, and sometimes a hidden reference answer. - They return structured scores—scalar or categorical—alongside explanations. - Rubrics and judge models must themselves be tested, calibrated, versioned, and improved. - Specialized judges may be needed for particular languages or technical domains. ## Calibration and Human Review - Periodic manual labeling of sampled outputs created calibration sets for comparing human and judge-model decisions. - The team tracked agreement and judge drift over time. - Engineers manually reviewed 5–10% of each release’s regression suite. - Disagreements were investigated as either judge-prompt defects or model errors. - Recurring problems led to prompt revisions or more detailed scoring criteria. Dropbox’s evaluation-first approach treats AI changes like code changes: test them against realistic datasets, score them with task-specific rubrics, validate the evaluators, and retain human oversight. This makes conversational AI development more reliable as systems and modalities grow more complex.

Read original

Large Language Models Natural Language Processing Prompt Engineering RAG+4

googleOct 1, 2025Original article

A collaborative approach to image generation (opens in new tab)

Google Research has introduced PASTA (Preference Adaptive and Sequential Text-to-image Agent), a reinforcement learning agent designed to transform image generation from a single-prompt task into a collaborative, multi-turn dialogue. By learning individual user preferences through sequential interactions, the system eliminates the frustration of trial-and-error prompting to achieve a specific creative vision. ## Data Strategy and User Simulation * Researchers collected a foundational dataset featuring over 7,000 human interactions, using Gemini Flash for prompt expansion and Stable Diffusion XL (SDXL) for image generation. * To overcome the scarcity of real-world interaction data, the team developed a user simulator that generated over 30,000 additional interaction trajectories. * The simulator is built on two primary components: a utility model that predicts how much a user will like an image, and a choice model that predicts which image a user will select from a given set. ## Latent Preference Discovery * The architecture utilizes pre-trained CLIP encoders paired with user-specific components to capture nuanced aesthetic tastes. * An expectation-maximization (EM) algorithm is employed to identify "user types," allowing the system to cluster users with similar interests, such as a preference for specific artistic styles or subject matter like "Food" or "Animals." * This approach enables the model to generalize preferences quickly, allowing it to adapt to new users based on minimal initial feedback. ## The Collaborative Generation Loop * PASTA operates as a value-based reinforcement learning model that aims to maximize cumulative user satisfaction across an entire interaction session. * The workflow begins with a candidate generator creating diverse prompt expansions; a candidate selector then picks an optimal "slate" of four variations to present to the user. * Each user selection provides a feedback signal that guides the agent’s next set of suggestions, iteratively narrowing the gap between the generated output and the user's intent. ## Training and Performance Validation * The agent was trained using Implicit Q-learning (IQL) to optimize decision-making without requiring online interaction during the training phase. * Performance was measured using several metrics, including Pick-a-Pic accuracy, Spearman’s rank correlation, and cross-turn accuracy. * Results indicated that agents trained on a combination of real-world and simulated data significantly outperformed baseline models and versions trained on only one data type. PASTA demonstrates that integrating iterative feedback loops and reinforcement learning can effectively bridge the "intent gap" in generative AI. For developers building creative tools, this research suggests that move-away from static prompting toward adaptive, simulation-trained agents can provide a more satisfying and intuitive user experience.

AI Reinforcement Learning Text To Image Clip+5

datadogOct 1, 20251 min readCurated summary

Inside Husky’s query engine: Real-time access to 100 trillion events | Datadog

The provided content does not include the blog post itself. It contains Datadog’s navigation menu and a promotional link announcing its recognition as a Leader in Gartner’s Magic Quadrant for Observability Platforms, but no substantive discussion of the linked “Husky Query Architecture” article. ## Available Content ### Datadog’s Observability Platform - Datadog promotes products covering: - Infrastructure and container monitoring - Application performance monitoring - Logs and database monitoring - Security - Digital experience monitoring - CI/CD and software delivery - Incident and service management - AI and agent observability - The navigation emphasizes Datadog’s broad, integrated platform approach. ### Gartner Recognition - The page links to Datadog’s announcement that it was named a Leader in the 2026 Gartner Magic Quadrant for Observability Platforms. - The supplied text does not include the evaluation criteria, cited strengths, limitations, or Gartner’s comparative analysis. No reliable summary of the Husky query architecture can be produced without the article’s body text.

Read original

Kubernetes Observability Application Performance Monitoring Log Management+4

datadogOct 1, 20253 min readCurated summary

Inside Husky’s query engine: Real-time access to 100 trillion events

Datadog’s Husky event store is designed not merely to store more than 100 trillion events, but to make them queryable interactively at massive scale. Its query engine handles schemaless data, highly variable tenant workloads, petabytes of object-store data, and both highly selective searches and broad analytics queries. The architecture combines distributed planning, metadata-driven pruning, coordinated execution, and reader-level optimizations to minimize the data and fragments that must be scanned. ## Husky’s Data and Query Workloads - Events contain a timestamp and flexible attributes. - Data shapes vary widely: - Logs, network events, and traces have different schemas. - Tenants may produce either a few large events or enormous numbers of small events. - Most queries fall into two categories: - **Needle-in-a-haystack searches**, such as finding a specific IP connection, error message, or trace. - **Analytics-style searches**, such as time series, grouped breakdowns, and distributions. - The engine must also support raw event retrieval and more complex queries such as joins. ## Distributed Query Path Husky divides query execution among four multi-tenant services deployed across regions and data centers. ### Query Planner - Serves as the main entry point for event-store queries. - Resolves query context, validates and throttles requests, and integrates with other Datadog data stores. - Applies optimizations and statistics to split queries into time-based steps. - Schedules those steps on orchestrators and merges their results into the final response. ### Query Orchestrator - Acts as the gateway to Husky’s stored data. - Fetches fragment metadata, including: - File paths and versions - Row counts - Timestamp boundaries - Zone maps for query matching - Dispatches only relevant fragments to reader nodes. - Uses zone-map pruning to reduce downstream work by up to 60% for structured events and about 30% on average. - Aggregates results after fragment processing, which can require more computation than query planning. ### Metadata Service - Provides an abstraction over FoundationDB clusters. - Preserves atomicity during operations such as compaction, preventing duplicate data from appearing in query results. - Separates FoundationDB implementation details from the rest of the query system. - Must work within FoundationDB’s five-second transaction limit. ### Reader Service - Receives a query and selected fragments, then returns results quickly. - Performs the direct scan and execution work over fragment data. - Contains multiple optimizations intended to keep queries interactive despite scanning data stored in blob storage at extreme scale. ## Minimizing Data Scans The reader service follows the principle that the fastest query is the one that avoids unnecessary work. - Scanning less data reduces both latency and storage costs. - Touching fewer fragments limits expensive object-store operations. - This is especially important because Husky stores millions of fragments daily and cannot afford multiple blob-storage GET requests for every fragment in every query. ## Row Groups and Reader Execution - Fragments can contain millions of rows, making fully in-memory processing risky and potentially causing memory pressure or failures. - To limit data retrieval, fragments are physically organized into **row groups**. - Row groups allow the reader to fetch only portions of a fragment needed for a query rather than loading the entire file. - The reader uses an iterator-based execution model inspired by the Volcano query-processing architecture. - The provided article ends as it begins explaining how this row-group layout supports efficient iterator-based query execution.

Read original

Database Design Data Architecture Foundationdb Husky+3

googleSep 30, 2025Original article

Introducing interactive on-device segmentation in Snapseed (opens in new tab)

Google has introduced a new "Object Brush" feature in Snapseed that enables intuitive, real-time selective photo editing through a novel on-device segmentation technology. By leveraging a high-performance interactive AI model, users can isolate complex subjects with simple touch gestures in under 20 milliseconds, bridging the gap between professional-grade editing and mobile convenience. This breakthrough is achieved through a sophisticated teacher-student training architecture that prioritizes both pixel-perfect accuracy and low-latency performance on consumer hardware. ### High-Performance On-Device Inference * The system is powered by the Interactive Segmenter model, which is integrated directly into the Snapseed "Adjust" tool to facilitate immediate object-based modifications. * To ensure a fluid user experience, the model utilizes the MediaPipe framework and LiteRT’s GPU acceleration to process selections in less than 20ms. * The interface supports dynamic refinement, allowing users to provide real-time feedback by tracing lines or tapping to add or subtract specific areas of an image. ### Teacher-Student Model Distillation * The development team first created "Interactive Segmenter: Teacher," a large-scale model fine-tuned on 30,000 high-quality, pixel-perfect manual annotations across more than 350 object categories. * Because the Teacher model’s size and computational requirements are prohibitive for mobile use, researchers developed "Interactive Segmenter: Edge" through knowledge distillation. * This distillation process utilized a dataset of over 2 million weakly annotated images, allowing the smaller Edge model to inherit the generalization capabilities of the Teacher model while maintaining a footprint suitable for mobile devices. ### Training via Synthetic User Prompts * To make the model universally capable across all object types, the training process uses a class-agnostic approach based on the Big Transfer (BiT) strategy. * The model learns to interpret user intent through "prompt generation," which simulates real-world interactions such as random scribbles, taps, and lasso (box) selections. * During training, both the Teacher and Edge models receive identical prompts—such as red foreground scribbles and blue background scribbles—to ensure the student model learns to produce high-quality masks even from imprecise user input. This advancement significantly lowers the barrier to entry for complex photo manipulation by moving heavy-duty AI processing directly onto the mobile device. Users can expect a more responsive and precise editing experience that handles everything from fine-tuning a subject's lighting to isolating specific environmental elements like clouds or clothing.

AI Machine Learning Computer Vision On Device Ai+5

netflixSep 29, 2025Original article

100X Faster: How We Supercharged Netflix Maestro’s Workflow Engine | by Netflix Technology Blog | Netflix TechBlog (opens in new tab)

Netflix has significantly optimized Maestro, its horizontally scalable workflow orchestrator, to meet the evolving demands of low-latency use cases like live events, advertising, and gaming. By redesigning the core engine to transition from a polling-based architecture to a high-performance event-driven model, the team achieved a 100x increase in speed. This evolution reduced workflow overhead from several seconds to mere milliseconds, drastically improving developer productivity and system efficiency. ### Limitations of the Legacy Architecture The original Maestro architecture was built on a three-layer system that, while scalable, introduced significant latency during execution. * **Polling Latency:** The internal flow engine relied on calling execution functions at set intervals, creating a "speedbump" where tasks waited seconds to be picked up by workers. * **Execution Overhead:** The process of translating complex workflow graphs into parallel flows and sequentially chained tasks added internal processing time that hindered sub-hourly and ad-hoc workloads. * **Concurrency Issues:** A lack of strong guarantees from the internal flow engine occasionally led to race conditions, where a single step might be executed by multiple workers simultaneously. ### Transitioning to an Event-Driven Engine To support the highest level of user needs, Netflix replaced the traditional flow engine with a custom, high-performance execution model. * **Direct Dispatching:** The engine moved away from periodic polling in favor of an event-driven mechanism that triggers state transitions instantly. * **State Machine Optimization:** The new design manages the lifecycle of workflows and steps through a more streamlined state machine, ensuring faster transitions between "start," "restart," "stop," and "pause" actions. * **Reduced Data Latency:** The team optimized data access patterns for internal state storage, reducing the time required to write Maestro data to the database during high-volume executions. ### Scalability and Functional Improvements The redesign not only improved speed but also strengthened the engine's ability to handle massive, complex data pipelines. * **Isolation Layers:** The engine maintains strict isolation between the Maestro step runtime (integrated with Spark and Trino) and the underlying execution logic. * **Support for Heterogeneous Workflows:** The supercharged engine continues to support massive workflows with hundreds of thousands of jobs while providing the low latency required for iterative development cycles. * **Reliability Guarantees:** By moving to a more robust internal event bus, the system eliminated the race conditions found in the previous distributed job queue implementation. For organizations managing large-scale Data or ML workflows, moving toward an event-driven orchestration model is essential for supporting sub-hourly execution and low-latency ad-hoc queries. These performance improvements are now available in the Maestro open-source project for wider community adoption.

Distributed Systems Performance Optimization Workflow Orchestration Data Pipelines+3

googleSep 29, 2025Original article

AI as a research partner: Advancing theoretical computer science with AlphaEvolve (opens in new tab)

AlphaEvolve, an LLM-powered coding agent developed by Google DeepMind, facilitates mathematical discovery by evolving code to find complex combinatorial structures that are difficult to design manually. By utilizing a "lifting" technique, the system discovers finite structures that can be plugged into existing proof frameworks to establish new universal theorems in complexity theory. This methodology has successfully produced state-of-the-art results for the MAX-4-CUT problem and tightened bounds on the hardness of certifying properties in random graphs. ## The Role of AlphaEvolve in Mathematical Research * The system uses an iterative feedback loop to morph code snippets, evaluating the resulting mathematical structures and refining the code toward more optimal solutions. * AlphaEvolve operates as a tool-based assistant that generates specific proof elements, which can then be automatically verified by computer programs to ensure absolute mathematical correctness. * By focusing on verifiable finite structures, the agent overcomes the common "hallucination" issues of LLMs, as the final output is a computationally certified object rather than a speculative text-based proof. ## Bridging Finite Discovery and Universal Statements through Lifting * Theoretical computer science often requires proofs that hold true for all problem sizes ($\forall n$), a scale that AI systems typically struggle to address directly. * The "lifting" technique treats a proof as a modular structure where a specific finite component—such as a combinatorial gadget—can be replaced with a more efficient version while keeping the rest of the proof intact. * When AlphaEvolve finds a superior finite structure, the improvement is "lifted" through the existing mathematical framework to yield a stronger universal theorem without requiring a human to redesign the entire logical architecture. ## Optimizing Gadget Reductions and MAX-k-CUT * Researchers applied the agent to "gadget reductions," which are recipes used to map known intractable problems to new ones to prove computational hardness (NP-hardness). * AlphaEvolve discovered complex gadgets that were previously unknown because they were too intricate for researchers to construct by hand. * These discoveries led to a new state-of-the-art inapproximability result for the MAX-4-CUT problem, defining more precise limits on how accurately the problem can be solved by any efficient algorithm. ## Advancing Average-Case Hardness in Random Graphs * The agent was tasked with uncovering structures related to the average-case hardness of certifying properties within random graphs. * By evolving better combinatorial structures for these specific instances, the team was able to tighten existing mathematical bounds, providing a clearer picture of when certain graph properties become computationally intractable to verify. This research demonstrates that LLM-based agents can serve as genuine research partners by focusing on the discovery of verifiable, finite components within broader theoretical frameworks. For researchers in mathematics and computer science, this "lifting" approach provides a practical roadmap for using AI to solve bottleneck problems that were previously restricted by the limits of manual construction.

AI Large Language Models Gemini Coding Agents+5

googleSep 29, 2025Original article

The anatomy of a personal health agent (opens in new tab)

Google researchers have developed the Personal Health Agent (PHA), an LLM-powered prototype designed to provide evidence-based, personalized health insights by analyzing multimodal data from wearables and blood biomarkers. By utilizing a specialized multi-agent architecture, the system deconstructs complex health queries into specific tasks to ensure statistical accuracy and clinical grounding. The study demonstrates that this modular approach significantly outperforms standard large language models in providing reliable, data-driven wellness support. ## Multi-Agent System Architecture * The PHA framework adopts a "team-based" approach, utilizing three specialist sub-agents: a Data Science agent, a Domain Expert agent, and a Health Coach. * The system was validated using a real-world dataset from 1,200 participants, featuring longitudinal Fitbit data, health questionnaires, and clinical blood test results. * This architecture was designed after a user-centered study of 1,300 health queries, identifying four key needs: general knowledge, data interpretation, wellness advice, and symptom assessment. * Evaluation involved over 1,100 hours of human expert effort across 10 benchmark tasks to ensure the system outperformed base models like Gemini. ## The Data Science Agent * This agent specializes in "contextualized numerical insights," transforming ambiguous queries (e.g., "How is my fitness trending?") into formal statistical analysis plans. * It operates through a two-stage process: first interpreting the user's intent and data sufficiency, then generating executable code to analyze time-series data. * In benchmark testing, the agent achieved a 75.6% score in analysis planning, significantly higher than the 53.7% score achieved by the base model. * The agent's code generation was validated against 173 rigorous unit tests written by human data scientists to ensure accuracy in handling wearable sensor data. ## The Domain Expert Agent * Designed for high-stakes medical accuracy, this agent functions as a grounded source of health knowledge using a multi-step reasoning framework. * It utilizes a "toolbox" approach, granting the LLM access to authoritative external databases such as the National Center for Biotechnology Information (NCBI) to provide verifiable facts. * The agent is specifically tuned to tailor information to the user’s unique profile, including specific biomarkers and pre-existing medical conditions. * Performance was measured through board certification and coaching exam questions, as well as its ability to provide accurate differential diagnoses compared to human clinicians. While currently a research framework rather than a public product, the PHA demonstrates that a modular, specialist-driven AI architecture is essential for safe and effective personal health management. Developers of future health-tech tools should prioritize grounding LLMs in external clinical databases and implementing rigorous statistical validation stages to move beyond the limitations of general-purpose chatbots.

AI Large Language Models Gemini Multimodal AI+5