AI | Techlist.io

figmaJun 30, 20252 min readCurated summary

Figma Files Registration Statement for Proposed IPO | Figma Blog

Figma announced on July 1, 2025, that it publicly filed an S-1 registration statement with the SEC for a proposed initial public offering. The company plans to list its Class A common stock on the New York Stock Exchange under the symbol “FIG,” though the offering size, share price, and timing remain undecided. The IPO is subject to SEC review and market conditions. ## Public Filing and Proposed Listing - Figma’s filing follows its confidential submission of a draft S-1 in April 2025. - The proposed offering covers Figma’s Class A common stock. - The company has applied to list on the NYSE under the ticker **FIG**. - No share count or price range has been announced. - Figma cautions that the IPO may be delayed, changed, or not completed. ## Underwriters and Offering Restrictions - Morgan Stanley, Goldman Sachs, Allen & Company, and J.P. Morgan will serve as joint lead book-running managers. - BofA Securities, Wells Fargo Securities, and RBC Capital Markets will act as book-running managers. - William Blair and Wolfe | Nomura Alliance will be co-managers. - Shares may only be offered through a prospectus after the registration statement becomes effective. - The announcement itself is not an offer to sell or a solicitation to buy securities. ## Figma’s Business Positioning - Founded in 2012, Figma describes itself as a collaborative platform for digital product development. - The company has expanded beyond design software into an AI-powered platform. - Its tools support ideation, design, development, and product shipping. - Figma emphasizes collaboration, efficiency, and keeping product teams aligned. The announcement marks a significant step toward Figma becoming publicly traded, but investors must wait for the finalized prospectus and effective registration statement for details about valuation, financial performance, pricing, and the IPO timetable.

Read original

AI Figma Prototyping Product Development+1

figmaJun 30, 20252 min readCurated summary

Bill McDermott joins Figma’s Board of Directors | Figma Blog

Bill McDermott, ServiceNow’s Chairman and CEO, has joined Figma’s Board of Directors. Figma says his experience scaling enterprise companies and building global business ecosystems will support its continued growth. The appointment reflects Figma’s ambition to expand from a design tool into a broader, AI-powered platform for product development. ## McDermott’s Leadership Experience - McDermott has led major technology companies, including: - ServiceNow, where he positioned the company as an AI platform for business transformation. - SAP, where he built global business ecosystems. - During his leadership, both ServiceNow and SAP more than tripled their market capitalizations. - Both companies are also Figma customers, giving McDermott direct familiarity with the platform and its enterprise users. - Figma CEO Dylan Field highlighted McDermott’s operating experience, humility, authenticity, and ability to lead at scale. ## Figma’s Board of Directors McDermott joins a board that includes: - Dylan Field, Figma co-founder and CEO - Mamoon Hamid of Kleiner Perkins - Kelly Kramer, former Cisco EVP and CFO - John Lilly of Greylock and former Mozilla CEO - Andrew Reed of Sequoia - Danny Rimer of Index Ventures - Lynn Vojvodich Radakovich, former Salesforce EVP and CMO ## Figma’s Continued Expansion - Founded in 2012, Figma has expanded beyond collaborative interface design. - The company now describes itself as a connected, AI-powered platform covering ideation, design, development, and product shipping. - McDermott’s enterprise expertise is expected to help Figma scale its business and serve large organizations more effectively. Figma’s appointment of McDermott adds seasoned enterprise leadership to its board as the company pursues broader platform growth and deeper adoption among large customers.

Read original

AI Figma Digital Product Design Servicenow+1

googleJun 29, 2025Original article

How we created HOV-specific ETAs in Google Maps (opens in new tab)

Google Maps has enhanced its routing capabilities by introducing HOV-specific ETAs, addressing the significant speed differences between carpool and general lanes. This was achieved through a novel unsupervised learning approach that classifies historical trips into HOV or non-HOV categories without initial manual labels. The resulting system enables more precise travel predictions, helping users optimize their commutes and supporting the shift toward sustainable travel modes. ### Segment-Level Speed Distribution * The model analyzes trip segments within short, 15-minute time windows to identify patterns in aggregated, anonymized traffic data. * During peak traffic hours, researchers often observe a bimodal speed distribution where HOV lanes maintain significantly higher average speeds compared to general lanes. * The classification system distinguishes between "Scenario A," where the speed gap is dramatic (e.g., 65 mph vs. 25 mph), and "Scenario B," where HOV lanes are only marginally faster, ensuring accurate modeling even when benefits are minimal. * Individual trip points, including speed and observation time, are processed collectively to determine if a specific segment of a journey occurred in a restricted lane. ### Incorporating Lateral Distance and Soft Clustering * To refine accuracy beyond simple speed metrics, the model incorporates the estimated lateral distance of a vehicle from the center of the road. * While GPS data is inherently noisy, this spatial information helps identify lane-specific behaviors by mapping trip points to the known physical location of HOV lanes (e.g., the far-left lanes). * The system employs soft clustering techniques, calculating the probability of a point belonging to a specific cluster rather than using hard binary assignments, which better manages borderline data points. * Temporal clustering via a weighted median approach is used to prioritize more recent traffic observations, ensuring the model accounts for the most current road conditions and availability constraints. By integrating these segment-level classifications into full-trip analyses, Google Maps can train its ETA prediction models on high-fidelity, lane-specific data. This implementation provides users with a more realistic view of their travel options, encouraging the use of high-occupancy lanes to reduce individual travel time, urban congestion, and overall emissions.

AI Machine Learning Traffic Analysis Unsupervised Learning+5

googleJun 26, 2025Original article

REGEN: Empowering personalized recommendations with natural language (opens in new tab)

Google Research has introduced REGEN, a benchmark dataset designed to evolve recommender systems from simple item predictors into conversational agents capable of natural language interaction. By augmenting the Amazon Product Reviews dataset with synthetic critiques and narratives using Gemini 1.5 Flash, the researchers provide a framework for training models to understand user feedback and explain their suggestions. The study demonstrates that integrating natural language critiques significantly improves recommendation accuracy while enabling models to generate personalized, context-aware content. ### Composition of the REGEN Dataset * The dataset enriches the existing Amazon Product Reviews archive by adding synthetic conversational elements, specifically targeting the gap in datasets that support natural language feedback. * **Critiques** are generated for similar item pairs within hierarchical categories, allowing users to guide the system by requesting specific changes, such as a different color or increased storage. * **Narratives** provide contextual depth through purchase reasons, product endorsements, and concise user summaries, helping the system justify its recommendations to the end-user. ### Unified Generative Modeling Approaches * The researchers framed a "jointly generative" task where models must process a purchase history and optional critique to output both a recommended item ID and a supporting narrative. * The **FLARE (Hybrid)** architecture uses a sequential recommender for item prediction based on collaborative filtering, which then feeds into a Gemma 2B LLM to generate the final text narrative. * The **LUMEN (Unified)** model functions as an end-to-end system where item IDs and text tokens are integrated into a single vocabulary, allowing one LLM to handle critiques, recommendations, and narratives simultaneously. ### Performance and Impact of User Feedback * Incorporating natural language critiques consistently improved recommendation metrics across different architectures, demonstrating that language-guided refinement is a powerful tool for accuracy. * In the Office domain, the FLARE hybrid model's Recall@10—a measure of how often the desired item appears in the top 10 results—increased from 0.124 to 0.1402 when critiques were included. * Results indicate that models trained on REGEN can achieve performance comparable to state-of-the-art specialized recommenders while maintaining high-quality natural language generation. The REGEN dataset and the accompanying LUMEN architecture provide a path forward for building more transparent and interactive AI assistants. For developers and researchers, utilizing these conversational benchmarks is essential for moving beyond "black box" recommendations toward systems that can explain their logic and adapt to specific user preferences in real time.

AI Large Language Models Gemini Natural Language Processing+4

figmaJun 25, 20253 min readCurated summary

6 Skills Every Engineer Needs for the AI Era | Figma Blog

AI should not merely automate engineering work; it should expand how developers explore problems, collaborate, and create better products. Figma argues that engineers who thrive in the AI era will combine technical judgment with user empathy, experimentation, and the ability to direct AI effectively. The goal is to automate repetitive work while preserving—and strengthening—the meaningful parts of product development. ## Use AI for More Than Automation - AI should maximize engineers’ capabilities rather than simply reduce costs. - Developers still need to identify the right problems, understand users, and apply care and craft to their solutions. - Automating tedious tasks frees teams to focus on product meaning, collaboration, and user value. - Employers increasingly value engineers who understand why they are building something, not just how. ## Use Vibe Coding to Explore Possibilities - Vibe coding is presented as a way to explore the problem space, not just generate production code. - Conversational development lets teams test more possible solutions in parallel and quickly produce visual artifacts. - Tools such as Figma Make support rapid prototyping, iteration, and refinement across design and code. - AI-assisted exploration can improve user experience by helping teams consider user needs earlier rather than automating away that consideration. ## Harness Agentic Capabilities - The Model Context Protocol (MCP) enables AI tools such as Cursor and Copilot to communicate with other software. - Figma’s MCP server supplies design context to language models, improving design-informed code generation. - Better context can increase visual fidelity and help developers follow established component libraries and accessibility practices. - Agentic tools are most effective when they have access to the conventions and information that guide the product. ## Audit Your Own Pull Requests - Engineers can use LLMs as a pre-review sounding board before submitting a pull request. - Models familiar with the codebase can identify duplicated implementations, unnecessary rewrites, and other issues. - This self-review improves code quality while reducing the burden on human reviewers. - AI-assisted review can increase engineering throughput without replacing team review. ## Coordinate Teams of AI Agents - Developers are learning to divide complex problems into smaller tasks for multiple AI agents. - They must then evaluate and integrate the agents’ separate solutions. - A key emerging skill is writing detailed Markdown instructions and providing context, much like guiding an intern. - The supplied article ends mid-section, so the sixth skill and the remainder of this discussion are not included. Engineers should treat AI as a partner for exploration, feedback, and coordination—not simply as a code generator. Strong results depend on clear problem framing, relevant context, human judgment, and continued attention to users.

Read original

AI Large Language Models AI Agents Model Context Protocol+2

lineJun 24, 2025Original article

Hosting the Tech Conference Tech- (opens in new tab)

LY Corporation is hosting its global technology conference, Tech-Verse 2025, on June 30 and July 1 to showcase the engineering expertise of its international teams. The event features 127 sessions centered on core themes of AI and security, offering a deep dive into how the group's developers, designers, and product managers solve large-scale technical challenges. Interested participants can register for free on the official website to access the online live-streamed sessions, which include real-time interpretation in English, Korean, and Japanese. ### Conference Overview and Access * The event runs for two days, from 10:00 AM to 6:00 PM (KST), and is primarily delivered via online streaming. * Registration is open to the public at no cost through the Tech-Verse 2025 official website. * The conference brings together technical talent from across the LY Corporation Group, including LINE Plus, LINE Taiwan, and LINE Vietnam. ### Multi-Disciplinary Technical Tracks * The agenda is divided into 12 distinct categories to cover the full spectrum of software development and product lifecycle. * Day 1 focuses on foundational technologies: AI, Security, Server-side development, Private Cloud, Infrastructure, and Data Platforms. * Day 2 explores application and management layers: AI Use Cases, Frontend, Mobile Applications, Design, Product Management, and Engineering Management. ### Key Engineering Case Studies and Sessions * **AI and Data Automation:** Sessions explore the evolution of development processes using AI, the shift from "Vibe Coding" to professional AI-assisted engineering, and the use of Generative AI to automate data pipelines. * **Infrastructure and Scaling:** Presentations include how the "Central Dogma Control Plane" connects thousands of services within LY Corporation and methods for improving video playback quality for LINE Call. * **Framework Migration:** A featured case study details the strategic transition of the "Demae-can" service from React Native to Flutter. * **Product Insights:** Deep dives into user experience design and data-driven insights gathered from LINE Talk's global user base. Tech-Verse 2025 provides a valuable opportunity for developers to learn from real-world deployments of AI and large-scale infrastructure. Given the breadth of the 127 sessions and the availability of real-time translation, tech professionals should review the timetable in advance to prioritize tracks relevant to their specific engineering interests.

AI Generative AI Security Data Pipeline+4

googleJun 23, 2025Original article

From research to climate resilience (opens in new tab)

Google Research is leveraging advanced artificial intelligence to transform climate science from theoretical exploration into scalable, real-world resilience tools. By developing sophisticated models for floods, cyclones, and hyper-local weather, the initiative provides critical lead times that empower communities to protect lives and livelihoods against increasingly frequent environmental threats. This transition from "impossible" research to global implementation highlights AI's capacity to bridge data gaps in the world's most vulnerable regions. ## AI-Powered Global Flood Forecasting * Google developed a global hydrological AI model, recently published in *Nature*, which enables riverine flood forecasts up to seven days in advance. * The system utilizes "virtual gauges" to analyze historical data and provide predictions in regions where physical water-monitoring infrastructure is non-existent. * The Flood Hub platform now covers over 100 countries and 700 million people, providing an expert data layer and API access for local governments and researchers. ## Cyclone Tracking and Intensity Prediction * Collaborative research between Google DeepMind and Google Research has produced models that predict storm existence, track, intensity, and size up to 15 days in advance. * The AI generates up to 50 different possible scenarios for each storm, providing a more nuanced view of potential impact than traditional physics-based supercomputer simulations. * Through the new Weather Lab website, these experimental models are being shared with the US National Hurricane Center to assist in forecasting during the Atlantic hurricane season. ## Global Nowcasting with MetNet-3 * The MetNet-3 state-of-the-art neural weather model provides hyper-local precipitation forecasts with a 5km resolution, updated every 15 minutes. * By utilizing satellite observations instead of traditional ground-based radar, the system delivers reliable weather data to regions like Africa that lack extensive physical infrastructure. * These 12-hour "nowcasting" windows are integrated directly into Google Search, specifically helping agricultural communities react to changing conditions to improve crop yields and reduce waste. These advancements demonstrate that the "art of the possible" is rapidly expanding, offering a future where data-scarce regions can access the same life-saving predictive capabilities as developed nations through global partnerships and satellite-based modeling.

AI Machine Learning Neural Networks Weather Forecasting+4

googleJun 22, 2025Original article

Unlocking rich genetic insights through multimodal AI with M-REGLE (opens in new tab)

Google Research has introduced M-REGLE, a multimodal AI framework designed to analyze diverse health data streams simultaneously to uncover the genetic underpinnings of complex diseases. By jointly modeling complementary signals—such as electrocardiograms (ECG) and photoplethysmograms (PPG)—the method captures shared biological information and reduces noise more effectively than unimodal approaches. This integrated analysis significantly enhances the discovery of genetic associations and improves the prediction of cardiovascular conditions like atrial fibrillation. ## Technical Architecture and Workflow M-REGLE utilizes a multi-step process to transform raw physiological waveforms into actionable genetic insights: * **Multimodal Integration:** Instead of processing data types in isolation, the model combines multiple inputs, such as the 12 leads of an ECG or paired ECG and PPG data, to capture overlapping signals. * **Latent Representation Learning:** The system employs a convolutional variational autoencoder (CVAE) to compress these high-dimensional waveforms into a low-dimensional "signature" or latent factors. * **Statistical Refinement:** Principal component analysis (PCA) is applied to the CVAE-generated signatures to ensure the learned factors are independent and uncorrelated. * **Genetic Mapping:** These independent factors are analyzed via genome-wide association studies (GWAS) to identify significant correlations between physiological signatures and specific genetic variations. ## Improved Data Reconstruction and Genetic Sensitivity The transition from unimodal (U-REGLE) to multimodal modeling has led to substantial gains in both data accuracy and biological discovery: * **Error Reduction:** M-REGLE achieved a 72.5% reduction in reconstruction error for 12-lead ECGs compared to analyzing each lead separately, indicating a much higher fidelity in capturing essential waveform characteristics. * **Increased Discovery Power:** In a study involving over 40,000 participants from the UK Biobank, the multimodal approach identified 3,251 significant genetic loci associated with 12-lead ECGs, a notable increase over the 2,215 loci found by unimodal methods. * **Novel Findings:** The model identified specific genetic links, such as the *RBM20* locus, which were previously missed by standard clinical measurements but are known to be critical for heart muscle function. ## Interpretability and Disease Prediction Beyond identifying associations, M-REGLE offers generative capabilities that help clinicians understand the relationship between latent data and physical health: * **Waveform Synthesis:** By altering specific coordinates within the learned embeddings, researchers can observe how individual latent factors correspond to physical changes in a patient's ECG T-wave or PPG peaks. * **Clinical Utility:** The model identified specific embeddings (positions 4, 6, and 10) that distinguish patients with atrial fibrillation (AFib) from those without. * **Predictive Performance:** M-REGLE’s embeddings outperformed traditional clinical polygenic risk scores (PRS) in predicting AFib, demonstrating the value of incorporating raw waveform data into risk assessments. ## Practical Applications Researchers and clinicians can leverage M-REGLE to extract richer insights from existing biobank data and wearable device outputs. By integrating multiple modalities into a single analytical pipeline, the framework provides a more comprehensive view of organ system health, facilitating the identification of therapeutic targets and more accurate disease screening protocols.

AI Multimodal AI Deep Learning Genomics+5

figmaJun 16, 20252 min readCurated summary

Make your site interactive with code layers | Figma Blog

Figma’s new code layers let designers add custom React-powered interactions directly within Figma Sites. They bridge the gap between static canvas designs and production-like experiences by combining AI-assisted coding, direct code editing, and reusable components. The feature is intended to make advanced interactions—such as drag-and-drop systems, animations, calculators, maps, shaders, and 3D effects—accessible without external developer support. ## Customizing Existing Designs - Code layers extend Figma Sites’ built-in responsive elements and interactions. - Designers can convert an existing element into a code layer through the Figma Make icon in the Design panel. - AI chat can then generate or modify behaviors such as: - Spinning or bouncing animations - Animated counters and text effects - Loan calculators and price estimators - Hover effects, ripples, and color changes - Code layers can be duplicated with **Command D** to create and compare multiple interaction variations. - Example use case: a flower shop could let visitors duplicate, drag, rotate, and layer flower images to create custom bouquets. ## Creating Code Layers from Scratch - Designers can use the Make tool or press **E** to draw a standalone code layer on a blank canvas. - A modal opens for generating the layer through AI prompts or writing code directly. - Suggested prompts and starter components—such as buttons, image galleries, and navigation menus—provide ready-made starting points. - These components can be used as-is or customized to match an existing design. ## Reusable and Extensible Components - Code layers support customizable properties, including strings, numbers, and references to other components. - AI can generate these properties automatically, or users can request specific controls. - A code layer can be converted into a reusable Figma component for use across pages, projects, and team design systems. - Designers can import npm packages such as `motion` and `@react-three/fiber` to add advanced animation, 3D rendering, and other functionality. ## Code Layers Compared with Figma Make - **Figma Make** is suited to building a functional app from a prompt without relying heavily on precise canvas design. - **Code layers in Figma Sites** are designed for adding custom interaction and motion to an existing visual design. - Together, the tools support both prompt-first development and design-first experimentation. Code layers are available to all Figma Sites users, offering a practical way to prototype and publish richer web experiences directly from the Figma canvas.

Read original

AI Prototyping React Web Development+4

figmaJun 16, 20252 min readCurated summary

Welcoming Payload to the Figma Team | Figma Blog

Figma has welcomed the team behind Payload, an open-source headless CMS and application framework, to strengthen its developer tools and connect design more closely with development. Payload will remain open source, with continued investment and no immediate changes for users. The partnership supports Figma’s broader vision of letting teams design, build, and deploy digital products within a collaborative ecosystem. ## Why Figma Chose Payload - Payload is known for its highly customizable architecture, extensibility, and strong developer experience. - It has become one of the leading open-source projects in its category and is used by several Fortune 100 companies. - Figma was especially impressed by Payload’s active open-source community and its practice of incorporating developer feedback into the product. - Both companies emphasize collaboration, community participation, and continuous improvement. ## What Happens to Payload - Payload will remain an open-source product. - There will be no immediate changes for existing users. - Figma plans to continue investing in the project and improving it. - Figma and Payload users will receive ongoing communication as the combined CMS strategy and product roadmap develop. ## Bridging Design and Development - Figma aims to become a central hub where teams can create and deploy digital products. - Payload’s CMS and framework capabilities can help connect Figma’s design tools with production websites and applications. - As AI accelerates the generation of code and content, controlling deployments and refining user experiences across channels becomes increasingly important. - The partnership is intended to reduce the traditional gap between designers and developers. ## The Broader Context - The announcement follows Figma’s push into web publishing through Figma Sites. - Payload’s flexibility and developer-focused tools could expand what developers can build across Figma’s platforms. - The companies expect their combined teams and communities to create more integrated design, development, and content workflows. Figma’s acquisition of the Payload team is positioned as a long-term investment in collaborative, developer-friendly product creation, while preserving Payload’s open-source identity and existing user experience.

Read original

AI Figma Open Source Web Development+4

lineJun 13, 2025Original article

AI and Writer's Partnership (opens in new tab)

LY Corporation is addressing the chronic shortage of high-quality technical documentation by treating the problem as an engineering challenge rather than a training issue. By utilizing Generative AI to automate the creation of API references, the Document Engineering team has transitioned from a "manual craftsmanship" approach to an "industrialized production" model. While the system significantly improves efficiency and maintains internal context better than generic tools, the team concludes that human verification remains essential due to the high stakes of API accuracy. ### Contextual Challenges with Generic AI Standard coding assistants like GitHub Copilot often fail to meet the specific documentation needs of a large organization. * Generic tools do not adhere to internal company style guides or maintain consistent terminology across projects. * Standard AI lacks awareness of internal technical contexts; for example, generic AI might mistake a company-specific identifier like "MID" for "Member ID," whereas the internal tool understands its specific function within the LY ecosystem. * Fragmented deployment processes across different teams make it difficult for developers to find a single source of truth for API documentation. ### Multi-Stage Prompt Engineering To ensure high-quality output without overwhelming the LLM's "memory," the team refined a complex set of instructions into a streamlined three-stage workflow. * **Language Recognition:** The system first identifies the programming language and specific framework being used. * **Contextual Analysis:** It analyzes the API's logic to generate relevant usage examples and supplemental technical information. * **Detail Generation:** Finally, it writes the core API descriptions, parameter definitions, and response value explanations based on the internal style guide. ### Transitioning to Model Context Protocol (MCP) While the prototype began as a VS Code extension, the team shifted to using the Model Context Protocol (MCP) to ensure the tool was accessible across various development environments. * Moving to MCP allows the tool to support multiple IDEs, including IntelliJ, which was a high-priority request from the developer community. * The MCP architecture decouples the user interface from the core logic, allowing the "host" (like the IDE) to handle UI interactions and parameter inputs. * This transition reduced the maintenance burden on the Document Engineering team by removing the need to build and update custom UI components for every IDE. ### Performance and the Accuracy Gap Evaluation of the AI-generated documentation showed strong results, though it highlighted the unique risks of documenting APIs compared to other forms of writing. * Approximately 88% of the AI-generated comments met the team's internal evaluation criteria. * The specialized generator outperformed GitHub Copilot in 78% of cases regarding style and contextual relevance. * The team noted that while a 99% accuracy rate is excellent for a blog post, a single error in a short API reference can render the entire document useless for a developer. To successfully implement AI-driven documentation, organizations should focus on building tools that understand internal business logic while maintaining a strict "human-in-the-loop" workflow. Developers should use these tools to generate the bulk of the content but must perform a final technical audit to ensure the precision that only a human author can currently guarantee.

AI Large Language Models Generative AI Model Context Protocol+4

figmaJun 10, 20252 min readCurated summary

The Long and Short of It: Issue no.11 | Figma Blog

AI is changing how people build, but Figma argues that it does not replace craft, quality, or emotional connection. The issue highlights tools and practices that combine automation with design intent, context, safety, and care. Its central conclusion is that meaningful work still requires human judgment and deliberate practice. ## Building with Figma Make - Figma Make is a prompt-to-code tool that turns natural-language prompts or static designs into interactive prototypes. - It can be used at different stages of the design and development process. - Figma recommends experimenting with prompts and applying practical techniques to get better results. ## Bringing Design Context into Coding - Agentic coding tools are limited when they lack context about the intended design. - Figma’s MCP server connects Figma files to AI coding tools. - It gives language models access to variables, components, and styles, helping them generate code that better reflects design intent. - This positions AI as part of the developer workflow rather than an isolated automation tool. ## When Efficiency Undermines Care - The issue examines the idea that excessive focus on efficiency can weaken connection and emotional investment in creative work. - Themes from Config 2025 include AI evolving from a tool into a teammate and the importance of reaching “minimum viable play.” - The broader message is that faster production should not come at the expense of thoughtful, resonant design. ## Designing AI with Trust and Transparency - Headspace’s Ebb AI mental-health companion was designed with trust and safety as priorities. - Product and brand teams considered details such as the character’s name, visual identity, and conversational guidelines. - The goal was to keep Ebb’s AI nature visible while ensuring users felt supported. - The example illustrates the additional responsibility involved in creating AI products for sensitive contexts. ## Craft Requires Practice - Figma’s third annual Config publication, *Practice*, explores how designers develop mastery. - It emphasizes patience, precision, experimentation, and a willingness to push boundaries. - The accompanying microsite, created with Other Means, includes a custom font by Kia Tasbihgou. ## Rabbit Hole - The issue closes with a visual collection of colorful abstract forms, collages, and photography, extending its focus on experimentation and creative inspiration. AI can accelerate making, but strong results still depend on context, care, taste, and practice. Figma’s recommendation is to use AI as a creative partner while preserving the human attention that gives work its meaning.

Read original

AI Figma Large Language Models Prototyping+3

googleJun 5, 2025Original article

Optimizing LLM-based trip planning (opens in new tab)

Google Research has developed a hybrid planning system that combines Large Language Models (LLMs) with traditional optimization algorithms to solve complex trip-planning tasks. While LLMs excel at interpreting qualitative user preferences—such as a desire for "lesser-known museums"—they often struggle with hard quantitative constraints like travel logistics and fluctuating opening hours. By using an LLM to generate an initial draft and a secondary algorithm to refine it against real-world data, the system produces itineraries that are both highly personalized and logistically feasible. ## The Hybrid Planning Architecture * The process begins with a Gemini model generating an initial trip plan based on the user's natural language query, identifying specific activities and their perceived importance. * This draft is grounded using live data, incorporating up-to-date opening hours, transit schedules, and travel times between locations. * Search backends simultaneously retrieve alternative activities to serve as potential substitutes if the LLM's original suggestions prove logistically impossible. ## Two-Stage Optimization Algorithm * The first stage focuses on single-day scheduling, using dynamic programming and exhaustive search to find the most efficient sequence for subsets of activities. * Each potential daily schedule is assigned a quality score based on its feasibility and how closely it aligns with the LLM's original intent. * The second stage addresses the multi-day itinerary as a weighted variant of the "set packing problem," which ensures that activities do not overlap across different days. * Because multi-day optimization is NP-complete, the system employs local search heuristics to swap activities between days, iteratively improving the total score until the plan converges. ## Balancing Intent and Feasibility * In practical testing, the system demonstrated a superior ability to handle nuanced requests, such as finding "lesser-known" museums in NYC, which traditional retrieval systems often fail by suggesting famous landmarks like the Met. * The optimization layer specifically corrects geographical inefficiencies, such as the LLM suggesting a "zig-zag" route across San Francisco, by regrouping activities into logical clusters to minimize travel time. * The system maintains the "spirit" of the LLM's creative suggestions—like visiting a specific scenic viewpoint—while ensuring the user doesn't arrive after the gates have closed. This hybrid approach suggests that the most reliable AI planning tools do not rely on LLMs in isolation. By using LLMs as creative engines for intent interpretation and delegating logistical verification to rigid algorithmic frameworks, developers can create tools that are both imaginative and practically dependable.

AI Large Language Models Gemini Dynamic Programming+4

googleJun 4, 2025Original article

Zooming in: Efficient regional environmental risk assessment with generative AI (opens in new tab)

Google Research has introduced a dynamical-generative downscaling method that combines physics-based climate modeling with probabilistic diffusion models to produce high-resolution regional environmental risk assessments. By bridging the resolution gap between global Earth system models and city-level data needs, this approach provides a computationally efficient way to quantify climate uncertainties at a 10 km scale. This hybrid technique significantly reduces error rates compared to traditional statistical methods while remaining far less computationally expensive than full-scale dynamical simulations. ## The Resolution Gap in Climate Modeling * Traditional Earth system models typically operate at a resolution of ~100 km, which is too coarse for city-level planning regarding floods, heatwaves, and wildfires. * Existing "dynamical downscaling" uses regional climate models (RCMs) to provide physically realistic 10 km projections, but the computational cost is too high to apply to large ensembles of climate data. * Statistical downscaling offers a faster alternative but often fails to capture complex local weather patterns or extreme events, and it struggles to generalize to unprecedented future climate conditions. ## A Hybrid Dynamical-Generative Framework * The process begins with a "physics-based first pass," where an RCM downscales global data to an intermediate resolution of 50 km to establish a common physical representation. * A generative AI system called "R2D2" (Regional Residual Diffusion-based Downscaling) then adds fine-scale details, such as the effects of complex topography, to reach the target 10 km resolution. * R2D2 specifically learns the "residual"—the difference between intermediate and high-resolution fields—which simplifies the learning task and improves the model's ability to generalize to unseen environmental conditions. ## Efficiency and Accuracy in Risk Assessment * The model was trained and validated using the Western United States Dynamically Downscaled Dataset (WUS-D3), which utilizes the "gold standard" WRF model. * The dynamical-generative approach reduced fine-scale errors by over 40% compared to popular statistical methods like BCSD and STAR-ESDM. * A key advantage of this method is its scalability; the AI requires training on only one dynamically downscaled model to effectively process outputs from various other Earth system models, allowing for the rapid assessment of large climate ensembles. By combining the physical grounding of traditional regional models with the speed of diffusion-based AI, researchers can now produce granular risk assessments that were previously cost-prohibitive. This method allows for a more robust exploration of future climate scenarios, providing essential data for farming, water management, and community protection.

AI Generative AI Diffusion Models Climate Modeling+5

lineMay 23, 2025Original article

Implementing a RAG-based (opens in new tab)

To address the operational burden of handling repetitive user inquiries for the AWX automation platform, LY Corporation developed a support bot utilizing Retrieval-Augmented Generation (RAG). By combining internal documentation with historical Slack thread data, the system provides automated, context-aware answers that significantly reduce manual SRE intervention. This approach enhances service reliability by ensuring users receive immediate assistance while allowing engineers to focus on high-priority development tasks. ### Technical Infrastructure and Stack * **Slack Integration**: The bot is built using the **Bolt for Python** framework to handle real-time interactions within the company’s communication channels. * **LLM Orchestration**: **LangChain** is used to manage the RAG pipeline; the developers suggest transitioning to LangGraph for teams requiring more complex multi-agent workflows. * **Embedding Model**: The **paraphrase-multilingual-mpnet-base-v2** (SBERT) model was selected to support multi-language inquiries from LY Corporation’s global workforce. * **Vector Database**: **OpenSearch** serves as the vector store, chosen for its availability as an internal PaaS and its efficiency in handling high-dimensional data. * **Large Language Model**: The system utilizes **OpenAI (ChatGPT) Enterprise**, which ensures business data privacy by preventing the model from training on internal inputs. ### Enhancing LLM Accuracy through RAG and Vector Search * **Overcoming LLM Limits**: Traditional LLMs suffer from "hallucinations," lack of up-to-date info, and opaque sourcing; RAG fixes this by providing the model with specific, trusted context during the prompt phase. * **Embedding and Vectorization**: Textual data from wikis and chats are converted into high-dimensional vectors, where semantically similar phrases (e.g., "Buy" and "Purchase") are stored in close proximity. * **k-NN Retrieval**: When a user asks a question, the bot uses **k-Nearest Neighbors (k-NN)** algorithms to retrieve the top *k* most relevant snippets of information from the vector database. * **Contextual Generation**: Rather than relying on its internal training data, the LLM generates a response based specifically on the retrieved snippets, leading to higher accuracy and domain-specific relevance. ### AWX Support Bot Workflow and Data Sources * **Multi-Source Indexing**: The bot references two main data streams: the official internal AWX guide wiki and historical Slack inquiry threads where previous solutions were discussed. * **Automated First Response**: The workflow begins when a user submits a query via a Slack workflow; the bot immediately processes the request and provides an initial AI-generated answer. * **Human-in-the-Loop Validation**: After receiving an answer, users can click "Issue Resolved" to close the ticket or "Call AWX Admin" if the AI's response was insufficient. * **Efficiency Gains**: This tiered approach filters out "RTFM" (Read The F***ing Manual) style questions, ensuring that human administrators only spend time on unique or complex technical issues. Implementing a RAG-based support bot is a highly effective strategy for SRE teams looking to scale their internal support without increasing headcount. For the best results, organizations should focus on maintaining clean internal documentation and selecting embedding models that reflect the linguistic diversity of their specific workforce.

AI Python RAG Vector Db+5