figma·Jan 25, 2026·2 min readCurated summary

Think Outside of the Box—with Claude and FigJam | Figma Blog

Figma and Anthropic have integrated FigJam with Claude so teams can turn AI conversations into editable diagrams. Users can generate flows, timelines, architecture diagrams, and other visual artifacts from prompts, PDFs, images, screenshots, documentation, or code. The integration is intended to make AI-assisted thinking more collaborative by moving ideas from a private chat into a shared workspace where teams can refine and act on them. ## Turning Conversations into Diagrams - Claude can create editable FigJam diagrams directly from written prompts and uploaded materials. - Product teams can generate user flows from PRDs to identify friction, edge cases, and missing steps. - Visualizing ideas reduces copy-pasting and context switching while making abstract concepts easier to discuss. - Teammates can comment, react, and build on the generated diagrams in FigJam’s shared canvas. ## Supporting Product Planning - Product managers can use Claude and FigJam to create initial project plans and Gantt charts. - Generated timelines can map milestones, dependencies, and sequencing. - Early visual drafts help teams spot planning problems, unblock work, and align more quickly. ## Helping Engineers Explain Complex Systems - Claude can generate diagrams from technical documentation or uploaded code files. - Diagrams can represent: - System architecture - Services and APIs - Databases and dependencies - Request and response flows - Sequence and state transitions - These diagrams provide shared context for front-end and back-end teams and help reduce implementation risk. - Claude can compare system patterns and suggest suitable visualization styles. ## FigJam as a Collaborative Workflow - Ideas generated in Claude can move into the broader Figma ecosystem: - Refined in Figma Design - Shared through Figma Slides - Translated into code - Figma is also improving FigJam with more advanced shape collections and connector types. - Anthropic has released a UI kit for designing Claude MCP apps in Figma. - The workflow connects brainstorming, planning, refinement, and execution in one process. ## AI as an Ongoing Collaborator - Multi-turn conversations let teams iteratively develop user journeys, prioritization strategies, and implementation plans. - Claude can propose alternative solutions and recommend chart formats such as decision trees, Gantt charts, sequence diagrams, and state diagrams. - FigJam diagrams become shared, evolving artifacts rather than one-off AI outputs. - Figma presents this integration as a step toward making complex systems easier for teams to understand and improve together. Teams can access the feature through the Figma Connector in Claude’s browser or desktop apps, with support listed for Claude Opus 4.5 and Sonnet 4.5.

Read original(opens in new tab)

AIFigjamClaudeFigma Mcp+3

toss·Jan 21, 2026Original article

Will developers be replaced by AI? (opens in new tab)

The current AI hype cycle is a significant economic bubble where massive infrastructure investments of $560 billion far outweigh the modest $35 billion in generated revenue. However, drawing parallels to the 1995 dot-com era, the author argues that while short-term expectations are overblown, the long-term transformation of the developer role is inevitable. The conclusion is that developers won't be replaced but will instead evolve into "Code Creative Directors" who manage AI through the lens of technical abstraction and delegation. ### The Economic Bubble and Amara’s Law * The industry is experiencing a 16:1 imbalance between AI investment and revenue, with 95% of generative AI implementations reportedly failing to deliver clear efficiency improvements. * Amara’s Law suggests that we are overestimating AI's short-term impact while potentially underestimating its long-term necessity. * Much of the current "AI-driven" job market contraction is actually a result of companies cutting personnel costs to fund expensive GPU infrastructure and AI research. ### Jevons Paradox and the Evolution of Roles * Jevons Paradox indicates that as the "cost" of producing code drops due to AI efficiency, the total demand for software and the complexity of systems will paradoxically increase. * The developer’s identity is shifting from "code producer" to "system architect," focusing on agent orchestration, result verification, and high-level design. * AI functions as a "power tool" similar to game engines, allowing small teams to achieve professional-grade output while amplifying the capabilities of senior engineers. ### Delegation as a Form of Abstraction * Delegating a task to AI is an act of "work abstraction," which involves choosing which low-level details a developer can afford to ignore. * The technical boundary of what is "hard to delegate" is constantly shifting; for example, a complex RAG (Retrieval-Augmented Generation) pipeline built for GPT-4 might become obsolete with the release of a more capable model like GPT-5. * The focus for developers must shift from "what is easy to delegate" to "what *should* be delegated," distinguishing between routine boilerplate and critical human judgment. ### The Risks of Premature Abstraction * Abstraction does not eliminate complexity; it simply moves it into the future. If the underlying assumptions of an AI-generated system change, the abstraction "leaks" or breaks. * Sudden shifts in scaling (traffic surges), regulation (GDPR updates), or security (zero-day vulnerabilities) expose the limitations of AI-delegated work, requiring senior intervention. * Poorly managed AI delegation can lead to "abstraction debt," where the cost of fixing a broken AI-generated system exceeds the cost of having written it manually from the start. To thrive in this environment, developers should embrace AI not as a replacement, but as a layer of abstraction. Success requires mastering the ability to define clear boundaries for AI—delegating routine CRUD operations and boilerplate while retaining human control over architecture, security, and complex business logic.

AILarge Language ModelsGenerative AIPrompt Engineering+3

aws·Jan 20, 2026Original article

Announcing Amazon EC2 G7e instances accelerated by NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs (opens in new tab)

Amazon has announced the general availability of EC2 G7e instances, a new hardware tier powered by NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs designed for generative AI and high-end graphics. These instances deliver up to 2.3 times the inference performance of their G6e predecessors while providing significant upgrades to memory and bandwidth. This launch aims to provide a cost-effective solution for running medium-sized AI models and complex spatial computing workloads at scale. **Blackwell GPU and Memory Advancements** * The G7e instances feature NVIDIA RTX PRO 6000 Blackwell GPUs, which provide twice the memory and 1.85 times the memory bandwidth of the G6e generation. * Each GPU provides 96 GB of memory, allowing users to run medium-sized models—such as those with up to 70 billion parameters—on a single GPU using FP8 precision. * The architecture is optimized for both spatial computing and scientific workloads, offering the highest graphics performance currently available in the EC2 portfolio. **High-Speed Connectivity and Multi-GPU Scaling** * To support large-scale models, G7e instances utilize NVIDIA GPUDirect P2P, enabling direct communication between GPUs over PCIe interconnects with minimal latency. * These instances offer four times the inter-GPU bandwidth compared to the L40s GPUs found in G6e instances, facilitating more efficient data transfer in multi-GPU configurations. * Total GPU memory can scale up to 768 GB within a single node, supporting massive inference tasks across eight interconnected GPUs. **Networking and Storage Performance** * G7e instances provide up to 1,600 Gbps of network bandwidth, a four-fold increase over previous generations, making them suitable for small-scale multi-node clusters. * Support for NVIDIA GPUDirect Remote Direct Memory Access (RDMA) via Elastic Fabric Adapter (EFA) reduces latency for remote GPU-to-GPU communication. * The instances support GPUDirect Storage with Amazon FSx for Lustre, achieving throughput speeds up to 1.2 Tbps to ensure rapid model loading and data processing. **System Specifications and Configurations** * Under the hood, G7e instances are powered by Intel Emerald Rapids processors and support up to 192 vCPUs and 2,048 GiB of system memory. * Local storage options include up to 15.2 TB of NVMe SSD capacity to handle high-speed data caching and local processing. * The instance family ranges from the g7e.2xlarge (1 GPU, 8 vCPUs) to the g7e.48xlarge (8 GPUs, 192 vCPUs). For developers ready to transition to Blackwell-based architecture, these instances are accessible through AWS Deep Learning AMIs (DLAMI). They represent a major step forward for organizations needing to balance the high memory requirements of modern LLMs with the cost efficiencies of the G-series instance family.

AIGenerative AIAmazon Ec2Gpu Acceleration+5

aws·Jan 20, 2026Original article

AWS Weekly Roundup: Kiro CLI latest features, AWS European Sovereign Cloud, EC2 X8i instances, and more (January 19, 2026) (opens in new tab)

The January 19, 2026, AWS Weekly Roundup highlights significant advancements in sovereign cloud infrastructure and the general availability of high-performance, memory-optimized compute instances. The update also emphasizes the maturing ecosystem of AI agents, focusing on enhanced developer tooling and streamlined deployment workflows for agentic applications. These releases collectively aim to satisfy stringent regulatory requirements in Europe while pushing the boundaries of enterprise performance and automated productivity. ## Developer Tooling and Kiro CLI Enhancements * New granular controls for web fetch URLs allow developers to use allowlists and blocklists to strictly govern which external resources an agent can access. * The update introduces custom keyboard shortcuts to facilitate seamless switching between multiple specialized agents within a single session. * Enhanced diff views provide clearer visibility into changes, improving the debugging and auditing process for automated workflows. ## AWS European Sovereign Cloud General Availability * Following its initial 2023 announcement, this independent cloud infrastructure is now generally available to all customers. * The environment is purpose-built to meet the most rigorous sovereignty and data residency requirements for European organizations. * It offers a comprehensive set of AWS services within a framework that ensures operational independence and localized data handling. ## High-Performance Computing with EC2 X8i Instances * The memory-optimized X8i instances, powered by custom Intel Xeon 6 processors, have moved from preview to general availability. * These instances feature a sustained all-core turbo frequency of 3.9 GHz, which is currently exclusive to the AWS platform. * The hardware is SAP certified and engineered to provide the highest memory bandwidth and performance for memory-intensive enterprise workloads compared to other Intel-based cloud offerings. ## Agentic AI and Productivity Updates * Amazon Quick Suite continues to expand as a workplace "agentic teammate," designed to synthesize research and execute actions based on organizational insights. * New technical guidance has been released regarding the deployment of AI agents on Amazon Bedrock AgentCore. * The integration of GitHub Actions is now supported to automate the deployment and lifecycle management of these AI agents, bridging the gap between traditional DevOps and agentic AI development. These updates signal a strategic shift toward highly specialized infrastructure, both in terms of regulatory compliance with the Sovereign Cloud and raw performance with the X8i instances. Organizations looking to scale their AI operations should prioritize the new deployment patterns for Bedrock AgentCore to ensure a robust CI/CD pipeline for their autonomous agents.

AIAI AgentsAWSAmazon Bedrock+5

stripe·Jan 16, 2026·3 min readCurated summary

The three biggest agentic commerce trends from NRF 2026

Agentic commerce is moving from an experimental idea to an implementation priority for retailers. At NRF, roughly 75% of attendees said they were implementing or planning agentic commerce, while major platforms such as Microsoft and Google introduced new shopping infrastructure and protocols. Retailers are responding by gradually preparing their catalogs and building both third-party agent integrations and proprietary AI shopping experiences. ## Retailers Are Moving from “If” to “How” - Retailers are now focused on scaling agentic commerce while preserving trust, brand identity, and control. - Stripe reported adoption by brands including URBN, Etsy, Coach, Kate Spade, Revolve, and Abt Electronics. - More than 25 ecosystem partners, including Salesforce, Squarespace, and PwC, endorsed Stripe’s Agentic Commerce Protocol (ACP). - Microsoft’s Copilot Checkout will let users purchase from Etsy and URBN brands without leaving the chat. - Google introduced the Universal Commerce Protocol (UCP), joining ACP and other emerging agentic commerce standards. - Stripe says its Agentic Commerce Suite will support multiple protocols through a single integration. ## Retailers Are Building Agent-Ready Catalogs Incrementally - Effective agent shopping depends on structured, current product feeds containing accurate descriptions, prices, availability, attributes, and taxonomy. - Large retailers may have thousands or millions of products, making full catalog optimization impractical as a first step. - URBN began with high-impact categories such as dresses and denim. - The company standardized product language, attributes, and taxonomy in those categories before expanding. - This focused approach allows retailers to demonstrate value quickly rather than attempting a costly catalog-wide transformation. ## Retailers Are Developing Their Own AI Shopping Experiences - Retailers are concerned that relying exclusively on third-party agents could weaken customer relationships and loyalty. - First-party AI tools can use customer and purchase data unavailable to external platforms. - Home Depot’s Magic Apron provides website-based, personalized assistance grounded in the retailer’s existing customer relationship. - Ralph Lauren’s Ask Ralph creates shoppable outfit combinations based on customer prompts. - The emerging model combines third-party agents for product discovery with first-party experiences for deeper personalization and brand engagement. ## Infrastructure for Agentic Commerce - Stripe’s Agentic Commerce Suite connects a retailer’s product catalog to selected AI agents through the Stripe Dashboard. - It supports checkout, payments, fraud detection, and order events. - Retailers can continue using their existing commerce systems while adding agent-based sales channels. Retailers should treat agentic commerce as a practical, staged rollout: begin with high-value product categories, improve catalog data incrementally, support major commerce protocols, and build first-party AI experiences alongside third-party integrations.

Read original(opens in new tab)

AIAI AgentsStripeAgentic Commerce+3

kakao·Jan 15, 2026Original article

Kanana-2 Development Log ( (opens in new tab)

Kakao’s development of the Kanana-2 model family represents a strategic shift toward Agentic AI, prioritizing complex reasoning and execution capabilities over simple conversational fluency. By implementing a sophisticated post-training pipeline—including a specialized Mid-training stage and refined reinforcement learning—the team successfully enhanced the model's instruction-following and tool-calling performance. This methodology ensures that the 30B parameter models excel in logical tasks and real-world agentic environments while maintaining high linguistic stability in both English and Korean. ## Mid-training and Catastrophic Forgetting Prevention * A 250B token Mid-training stage was introduced between Pre-training and Post-training to bridge the gap in reasoning, coding, and tool-calling capabilities. * The dataset comprised 200B tokens of high-quality reasoning data (Chain-of-Thought math and code) and 50B tokens of "replay" data from the original pre-training set. * This replay strategy specifically targeted "Catastrophic Forgetting," preventing the model from losing its Korean linguistic nuances and performance on benchmarks like KoMT-bench while it gained English-heavy reasoning skills. * Experimental results indicated that Mid-training serves as a foundational "force multiplier," leading to faster convergence and higher performance ceilings during subsequent Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) stages. ## Enhanced Instruction Following and Tool Calling * To optimize for Agentic AI, the developers focused on Instruction Following (IFEval) by synthesizing high-quality, long-form responses that strictly adhere to complex constraints. * Tool-calling capabilities were improved using "Rejection Sampling" (Iterative SFT), where model-generated trajectories are validated in a real execution environment; only successful outcomes are retained for training. * The training data was categorized into distinct buckets—such as Chat, Math, Code, and Tool Calling—allowing for a more balanced recipe compared to previous Kanana versions. * This approach specifically addressed multi-turn and multi-tool scenarios, ensuring the model can handle the recursive logic required for autonomous agents. ## Parallel Reinforcement Learning and Calibration Tuning * A "Parallel RL" framework was adopted to optimize different capabilities simultaneously: the "Chat" track focused on helpfulness and safety, while the "Logic" track focused on accuracy in math and programming. * The pipeline moved beyond standard SFT to include Reinforcement Learning from Human Feedback (RLHF), utilizing DPO and PPO-style methods to align the model with human preferences. * A final "Calibration Tuning" step was implemented to ensure the model’s internal confidence levels match its actual accuracy, effectively reducing hallucinations and improving reliability in technical tasks. * Comparative benchmarks show that the Kanana-2 Instruct and Thinking models significantly outperform earlier versions and rival larger open-source models in reasoning and coding benchmarks like HumanEval and GSM8K. The Kanana-2 development cycle demonstrates that achieving "Agentic" performance requires more than just scaling data; it requires a structured transition from general language understanding to execution-verified reasoning. For organizations building AI agents, the Kanana-2 post-training recipe suggests that integrating environment-validated feedback and balancing reasoning data with foundational language "replays" is critical for creating reliable, multi-functional models.

AILarge Language ModelsAI AgentsReinforcement Learning+5

meta·Jan 14, 2026Original article

Adapting the Facebook Reels RecSys AI Model Based on User Feedback (opens in new tab)

Meta has enhanced the Facebook Reels recommendation engine by shifting focus from traditional engagement signals, like watch time and likes, to direct user feedback. By implementing the User True Interest Survey (UTIS) model, the system now prioritizes content that aligns with genuine user preferences rather than just short-term interactions. This shift has resulted in significant improvements in recommendation relevance, high-quality content delivery, and long-term user retention. **Limitations of Engagement-Based Metrics** * Traditional signals like "likes" and "watch time" are often noisy and may not reflect a user’s actual long-term interests. * Models optimized solely for engagement tend to favor short-term value over the long-term utility of the product. * Internal research found that previous heuristic-based interest models only achieved 48.3% precision in identifying what users truly care about. * Effective interest matching requires understanding nuanced factors such as production style, mood, audio, and motivation, which implicit signals often miss. **The User True Interest Survey (UTIS) Model** * Meta collects direct feedback via randomized, single-question surveys asking users to rate video interest on a 1–5 scale. * The raw survey data is binarized to denoise responses and weighted to correct for sampling and nonresponse bias. * The UTIS model functions as a lightweight "alignment model layer" built on top of the main multi-task ranking system. * The architecture uses existing model predictions as input features, supplemented by engineered features that capture content attributes and user behavior. **Integration into the Ranking Funnel** * **Late Stage Ranking (LSR):** The UTIS score is used as an additional input feature in the final value formula, allowing the system to boost high-interest videos and demote low-interest ones. * **Early Stage Ranking (Retrieval):** The model aggregates survey data to reconstruct user interest profiles, helping the system source more relevant candidates during the initial retrieval phase. * **Knowledge Distillation:** Large sequence-based retrieval models are aligned using UTIS predictions as labels through distillation objectives. **Performance and Impact** * The deployment of UTIS has led to a measurable increase in the delivery of niche, high-quality content. * Generic, popularity-based recommendations that often lack depth have been reduced. * Meta observed robust improvements across core metrics, including higher follow rates, more shares, and increased user retention. * The system now offers better interpretability, allowing engineers to understand which specific factors contribute to a user’s sense of "interest match." To continue improving the Reels ecosystem, Meta is focusing on doubling down on personalization by tackling challenges related to sparse data and sampling bias while exploring more advanced AI architectures to further diversify recommendations.

AIMachine LearningRecommendation SystemsInformation Retrieval+5

google·Jan 14, 2026Original article

Unlocking health insights: Estimating advanced walking metrics with smartwatches (opens in new tab)

Google researchers have validated that smartwatches are a highly reliable and accurate platform for estimating complex spatio-temporal gait metrics, rivaling the performance of smartphone-based methods. By utilizing a multi-head deep learning model, the study demonstrates that wrist-worn devices can provide continuous, lab-grade health insights into a user's walking speed, step length, and balance without requiring the specific pocket placement or specialized laboratory equipment previously necessary for such data. ## Multi-Head Deep Learning for Wrist-Based Sensors * The researchers developed a temporal convolutional network (TCN) architecture designed to process raw inertial measurement unit (IMU) data, specifically 3-axis accelerometer and gyroscope signals sampled at 50 Hz. * Unlike traditional models that only track temporal events and are prone to integration drift, this multi-head approach directly estimates both unilateral and bilateral metrics simultaneously. * The model architecture extracts embeddings from the IMU signals and concatenates them with user height (a demographic scalar input) to improve the precision of spatial predictions. * The system estimates a comprehensive suite of metrics, including gait speed, double support time (the proportion of time both feet are on the ground), step length, swing time, and stance time. ## Large-Scale Validation and Study Protocol * To ensure rigorous results, the study involved a diverse cohort of 246 participants across two international sites, generating approximately 70,000 walking segments. * Ground truth measurements were captured using a professional-grade Zeno Gait Walkway system to provide high-precision reference data for comparison. * The study protocol included various walking conditions to test the model's versatility: a self-paced six-minute walk test (6MWT), fast-paced walking, and induced physical asymmetry created by wearing hinged knee braces at specific angles. * Researchers employed a five-fold cross-validation strategy, ensuring that all data from a single participant remained within a single split to prevent data leakage and ensure the model generalizes to new users. ## Clinical Validity and Comparative Performance * Smartwatch estimates demonstrated strong validity and excellent reliability, with Pearson correlation coefficients (r) and intraclass correlation coefficients (ICC) exceeding 0.80 for most metrics. * Performance comparisons showed non-significant differences in Mean Absolute Percentage Error (MAPE) between the Pixel Watch and Pixel phone, establishing the smartwatch as a viable alternative to smartphone-based tracking. * While double support time showed slightly lower but acceptable reliability (ICC 0.56–0.60), other metrics like step length and gait speed proved highly consistent across different walking speeds and styles. * The model’s success suggests that smartwatches can effectively bridge the gap in gait analysis, providing a more practical and consistent platform for continuous health tracking than handheld devices. This research establishes smartwatches as a powerful tool for longitudinal health monitoring, enabling the detection of neurological or musculoskeletal changes through passive, continuous gait analysis in everyday environments.

AIDeep LearningWearablesHealth Tech+5

line·Jan 14, 2026Original article

Building an Enterprise LLM (opens in new tab)

LY Corporation’s engineering team developed an AI assistant for their private cloud platform, Flava, by prioritizing "context engineering" over traditional prompt engineering. To manage a complex environment of 260 APIs and hundreds of technical documents, they implemented a strategy of progressive disclosure to ensure the LLM receives only the most relevant information for any given query. This approach allows the assistant to move beyond simple RAG-based document summarization to perform active diagnostics and resource management based on real-time API data. ### Performance Limitations of Long Contexts * Research indicates that LLM performance can drop by 13.9% to 85% as context length increases, even if the model technically supports a large token window. * The phenomenon of "context rot" occurs when low-quality or irrelevant information is mixed into the input, causing the model to generate confident but incorrect answers. * Because LLMs are stateless, maintaining conversation history and processing dense JSON responses from multiple APIs quickly exhausts context windows and degrades reasoning quality. ### Progressive Disclosure and Tool Selection * The system avoids loading all 260+ API definitions at once; instead, it analyzes the user's intent to select only the necessary tools, such as loading only Redis-related APIs when a user asks about a cluster. * Specific product usage hints, such as the distinction between private and CDN settings for Object Storage, are injected only when those specific services are invoked. * This phased approach significantly reduces token consumption and prevents the model from being overwhelmed by irrelevant technical specifications. ### Response Guidelines and the "Mock Tool Message" Strategy * The team distinguished between "System Prompts" (global rules) and "Response Guidelines" (situational instructions), such as directing users to a console UI before suggesting CLI commands. * Injecting specific guidelines into the system prompt often caused "instruction conflict," where the LLM might hallucinate information to satisfy a guideline while ignoring core requirements like using search tools. * To resolve these conflicts, the team utilized "ToolMessages" to inject guidelines; by formatting instructions as if they were results from a tool execution, the LLM treats the information as factual context rather than a command that might override the system prompt. To build a robust enterprise LLM service, developers should focus on dynamic context management rather than static prompt optimization. Treating operational guidelines as external data via mock tool messages, rather than system instructions, provides a scalable way to reduce hallucinations and maintain high performance across hundreds of integrated services.

AILarge Language ModelsPrompt EngineeringRAG+4

google·Jan 12, 2026Original article

Next generation medical image interpretation with MedGemma 1.5 and medical speech to text with MedASR (opens in new tab)

Google Research has introduced MedGemma 1.5 4B and MedASR, expanding its suite of open medical AI models to support more complex clinical workflows. These updates significantly enhance the interpretation of high-dimensional imaging and medical speech-to-text, providing a compute-efficient foundation for healthcare developers to build upon. By maintaining an open-access model available on Hugging Face and Vertex AI, Google aims to accelerate the integration of multimodal AI into real-world medical applications. ### Multimodal Advancements in MedGemma 1.5 The latest update to the MedGemma 4B model focuses on high-dimensional and longitudinal data, moving beyond simple 2D image interpretation. * **3D Medical Imaging:** The model now supports volumetric representations from CT scans and MRIs, as well as whole-slide histopathology imaging. * **Longitudinal Review:** New capabilities allow for the review of chest X-ray time series, helping clinicians track disease progression over time. * **Anatomical Localization:** Developers can use the model to identify and localize specific anatomical features within chest X-rays. * **Document Understanding:** Enhanced support for extracting structured data from complex medical lab reports and documents. * **Edge Capability:** The 4B parameter size is specifically designed to be small enough to run offline while remaining accurate enough for core medical reasoning tasks. ### Medical Speech-to-Text with MedASR MedASR is a specialized automated speech recognition (ASR) model designed to bridge the gap between clinical dialogue and digital documentation. * **Clinical Dictation:** The model is specifically fine-tuned for medical terminology and the unique nuances of clinical dictation. * **Integrated Reasoning:** MedASR is designed to pair seamlessly with MedGemma, allowing transcribed text to be immediately processed for advanced medical reasoning or summarization. * **Accessibility:** Like other HAI-DEF models, it is free for research and commercial use and hosted on both Hugging Face and Google Cloud’s Vertex AI. ### Performance Benchmarks and Community Impact Google is incentivizing innovation through improved performance metrics and community-driven challenges. * **Accuracy Gains:** Internal benchmarks show MedGemma 1.5 improved disease-related CT classification by 3% and MRI classification by 14% compared to the previous version. * **MedGemma Impact Challenge:** A Kaggle-hosted hackathon with $100,000 in prizes has been launched to encourage developers to find creative applications for these multimodal tools. * **Model Collection:** The update complements existing tools like the MedSigLIP image encoder and the larger MedGemma 27B model, which remains the preferred choice for complex, text-heavy medical applications. Developers and researchers are encouraged to utilize MedGemma 1.5 for tasks requiring efficient, offline multimodal processing, while leveraging MedASR to automate clinical documentation. By participating in the MedGemma Impact Challenge, the community can help define the next generation of AI-assisted medical diagnostics and workflows.

AIGenerative AIMultimodal AISpeech To Text+5

google·Jan 11, 2026Original article

NeuralGCM harnesses AI to better simulate long-range global precipitation (opens in new tab)

NeuralGCM represents a significant evolution in atmospheric modeling by combining traditional fluid dynamics with neural networks to solve the long-standing challenge of simulating global precipitation. By training the AI component directly on high-quality NASA satellite observations rather than biased reanalysis data, the model achieves unprecedented accuracy in predicting daily weather cycles and extreme rainfall events. This hybrid approach offers a faster, more precise tool for both medium-range weather forecasting and multi-decadal climate projections. ## The Limitations of Cloud Parameterization * Precipitation is driven by cloud processes occurring at scales as small as 100 meters, which is far below the kilometer-scale resolution of global weather models. * Traditional models rely on "parameterizations," or mathematical approximations, to estimate how these small-scale events affect the larger atmosphere. * Because these approximations are often simplified, traditional models struggle to accurately capture the complexity of water droplet formation and ice crystal growth, leading to errors in long-term forecasts. ## Training on Direct Satellite Observations * Unlike previous AI models trained on "reanalyses"—which are essentially simulations used to fill observational gaps—NeuralGCM is trained on NASA satellite-based precipitation data spanning 2001 to 2018. * The model utilizes a differentiable dynamical core, an architecture that allows the neural network to learn the effects of small-scale events directly from physical observations. * By bypassing the weaknesses inherent in reanalysis data, the model effectively creates a machine-learned parameterization that is more faithful to real-world cloud physics. ## Performance in Weather and Climate Benchmarks * At a resolution of 280 km, NeuralGCM outperforms leading operational models in medium-range forecasts (up to 15 days) and matches the precision of sophisticated multi-decadal climate models. * The model shows a marked improvement in capturing precipitation extremes, particularly for the top 0.1% of rainfall events. * Evaluation through WeatherBench 2 demonstrates that NeuralGCM accurately reproduces the diurnal (daily) weather cycle, a metric where traditional physics-based models frequently fall short. NeuralGCM provides a highly efficient and accessible framework for researchers and city planners who need to simulate long-range climate scenarios, such as 100-year storms or seasonal agricultural cycles. Its ability to maintain physical consistency while leveraging the speed of AI makes it a powerful candidate for the next generation of global atmospheric modeling.

AIMachine LearningNeural NetworksClimate Modeling+5

figma·Jan 7, 2026·2 min readCurated summary

Software Is Culture

Software has evolved from an invisible, mechanical tool into an intimate part of human experience. The next major shift is toward intelligent, adaptive systems that learn and change with users. The post argues that designers will shape this future not merely by automating tasks, but by deciding where technology directs human attention, curiosity, and creativity. ## Software as Human Experience - Software once operated behind screens as an efficient, obedient system. - Touch interfaces—pinching, swiping, and tapping—made software embodied and deeply connected to how people think, feel, and communicate. - As a result, user experience became inseparable from human experience. ## The Shift to Intelligent Software - Future systems will learn, adapt, and respond rather than follow fixed interactions. - Interfaces may change in real time based on users’ needs and behavior. - Static products will become fluid, adaptive, and increasingly “alive.” - Understanding this transition requires examining influential interactions and design decisions from the past two decades. ## AI as Tool and Collaborator - AI can amplify distinctly human qualities rather than simply replace human work. - Interaction is shifting from commands, layers, and parameters toward conversation, goals, gestures, and overall intent. - The central design question is not what to automate, but where people should focus their attention. ## The Designer’s Role - Designers are navigating how intelligent software will affect curiosity, meaning, and craft. - Their choices will influence how future generations experience and understand technology. - Finding a personal perspective as a designer is essential to shaping software’s cultural impact. The practical takeaway is to treat software design as cultural work: build adaptive systems thoughtfully, and focus on how they direct human attention and enable meaningful action.

Read original(opens in new tab)

AIUser ExperienceMachine LearningSoftware Design+3

figma·Jan 6, 2026·2 min readCurated summary

Issue No.14: Software Is Culture | Figma Blog

Software increasingly shapes how people communicate, play, create, eat, and connect. Figma’s January 2026 newsletter argues that as AI evolves from tool to teammate, software will become more responsive to human needs—and its cultural influence will grow. The issue explores this idea through design, language, gaming, food, and physical fabrication. ## Design Is Culture - Familiar interactions such as pinch-to-zoom, infinite scroll, and tap-to-like were once novel inventions. - These interface patterns have had a major influence on how an entire generation thinks and feels. - The newsletter highlights 10 iconic interactions to examine their broader cultural impact. ## Language Is Culture - Social media and recommendation algorithms help new slang spread rapidly, including expressions such as “6-7,” “aura,” and “rizz.” - Linguist Adam Aleksic explains that algorithms influence not only how people speak, but also how they think and relate to one another. - “Algospeak” has become a measure of virality and a distinctive feature of online communication. ## Gaming Is Culture - Video games have grown from simple experiences like Pong into a $184 billion industry built around expansive worlds, characters, game modes, and side quests. - Despite this complexity, players often navigate games through a small set of controller inputs. - Epic Games UX designer Aashrey Sharma examines how these simple controls enable rich interactions and what they suggest about the future of interfaces. ## Food Is Culture - British Columbia’s small farms are under pressure from factory farming and rising costs, with farmers reportedly leaving the industry at an alarming rate. - Entrepreneur Aaron Veale used Figma Make to build a marketplace connecting local growers with restaurants. - By prompting the AI tool, he produced a working minimum viable product in less than three weeks, demonstrating how AI can help individuals address urgent community problems. ## Fabrication Is Culture - Designer Kelsey Fairhurst combines digital design with hands-on manufacturing to create “softline brutalist” stainless-steel flatware. - Her Forks Plus project grew through years of research and work between a Brooklyn studio and a Cleveland fabrication shop. - The story presents software and design tools as companions to physical making rather than replacements for it. The newsletter’s central recommendation is implicit: treat software as a cultural force, not merely a productivity tool. Designers and builders should consider how the interfaces and AI systems they create will shape behavior, language, creativity, and everyday life.

Read original(opens in new tab)

AIFigmaUser Interface DesignVersion Control+4

line·Dec 30, 2025Original article

A Business Trip to Japan After Only One (opens in new tab)

Joining the Developer Relations (DevRel) team at LINE Plus, a new employee was immediately thrust into a high-stakes business trip to Japan just one week after onboarding to support major global tech events. This immersive experience allowed the recruit to rapidly grasp the company’s engineering culture by facilitating cross-border collaboration and managing large-scale technical conferences. Ultimately, the journey highlights how a proactive onboarding strategy and a culture of creative freedom enable DevRel professionals to bridge the gap between complex engineering feats and community engagement. ### Global Collaboration at Tech Week * The trip centered on participating in **Tech-Verse**, a global conference featuring simultaneous interpretation in Korean, English, and Japanese, where the focus was on maintaining operational detail across diverse technical sessions. * Operational support was provided for **Hack Day**, an in-house hackathon that brought together engineers from various countries to collaborate on rapid prototyping and technical problem-solving. * The experience facilitated direct coordination with DevRel teams from Japan, Thailand, Taiwan, and Vietnam, establishing a unified approach to technical branding and regional community support. * Post-event responsibilities included translating live experiences into digital assets, such as "Shorts" video content and technical blog recaps, to maintain engagement after the physical event concluded. ### Modernizing Internal Technical Sharing * The **Tech Talk** series, a long-standing tradition with over 78 sessions, was used as a platform to experiment with "B-grade" humorous marketing—including quirky posters and cup holders—to drive offline participation in a remote-friendly work environment. * To address engineer feedback, the format shifted from passive lectures to **hands-on practical sessions** focusing on AI implementation. * Specific technical workshops demonstrated how to use tools like **Claude Code** and **ChatGPT** to automate workflows, such as generating weekly reports by integrating **Jira tickets with internal Wikis**. * Preparation for these sessions involved creating detailed environment setup guides and troubleshooting protocols to ensure a seamless experience for participating developers. ### Scaling AI Literacy via AI Campus Day * The **AI Campus Day** was a large-scale event designed for over 3,000 participants, aimed at lowering the barrier to entry for AI adoption across all departments. * The "Event & Operation" role involved creating interactive AI photo zones using **Gemini** to familiarize employees with new internal AI tools in a low-pressure setting. * Event production utilized AI-driven assets, including AI-generated voices and icons, to demonstrate the practical utility of these tools within standard business communication and video guides. * The success of the event relied on "participation design," ensuring that even non-technical staff could engage with AI concepts through hands-on play and peer mentoring. For organizations looking to strengthen their technical culture, this experience suggests that integrating new hires into high-impact global projects immediately can be a powerful onboarding tool. Providing DevRel teams the psychological safety to experiment with unconventional marketing and hands-on technical workshops is essential for maintaining developer engagement in a hybrid work era.

AIGenerative AIGeminiClaude Code+5

toss·Dec 23, 2025Original article

Tax Refund Automation: AI (opens in new tab)

At Toss Income, QA Manager Suho Jung successfully automated complex E2E testing for diverse tax refund services by leveraging AI as specialized virtual team members. By shifting from manual coding to a "human-as-orchestrator" model, a single person achieved the productivity of a four-to-five-person automation team within just five months. This approach overcame the inherent brittleness of testing long, React-based flows that are subject to frequent policy changes and external system dependencies. ### Challenges in Tax Service Automation The complexity of tax refund services presented unique hurdles that made traditional manual automation unsustainable: * **Multi-Step Dependencies:** Each refund flow averages 15–20 steps involving internal systems, authentication providers, and HomeTax scraping servers, where a single timing glitch can fail the entire test. * **Frequent UI and Policy Shifts:** Minor UI updates or new tax laws required total scenario reconfigurations, making hard-coded tests obsolete almost immediately. * **Environmental Instability:** Issues such as "Target closed" errors during scraping, differing domain environments, and React-specific hydration delays caused constant test flakiness. ### Building an AI-Driven QA Team Rather than using AI as a simple autocomplete tool, the project assigned specific "personas" to different AI models to handle distinct parts of the lifecycle: * **SDET Agent (Claude Sonnet 4.5):** Acted as the lead developer, responsible for designing the Page Object Model (POM) architecture, writing test logic, and creating utility functions. * **Documentation Specialist:** Automatically generated daily retrospectives and updated technical guides by analyzing daily git commits. * **Git Master:** Managed commit history and PR descriptions to ensure high-quality documentation of the project’s evolution. * **Pair Programmers (Cursor & Codex):** Handled real-time troubleshooting, type errors, and comparative analysis of different test scripts. ### Technical Solutions for React and Policy Logic The team implemented several sophisticated technical strategies to ensure test stability: * **React Interaction Readiness:** To solve "Element is not clickable" errors, they developed a strategy that waits not just for visibility, but for event handlers to bind to the DOM (Hydration). * **Safe Interaction Fallbacks:** A standard `click` utility was created that attempts a Playwright click, then a native keyboard 'Enter' press, and finally a JS dispatch to ensure interactions succeed even during UI transitions. * **Dynamic Consent Flow Utility:** A specialized system was built to automatically detect and handle varying "Terms of Service" agreements across different sub-services (Tax Secretary, Hidden Refund, etc.) through a single unified function. * **Test Isolation:** Automated scripts were used to prevent `userNo` (test ID) collisions, ensuring 35+ complex scenarios could run in parallel without data interference. ### Integrated Feedback and Reporting The automation was integrated directly into internal communication channels to create a tight feedback loop: * **Messenger Notifications:** Every test run sends a report including execution time, test IDs, and environment data to the team's messenger. * **Automated Failure Analysis:** When a test fails, the AI automatically posts the error log, the specific failed step, a tracking EventID, and a screenshot as a thread reply for immediate debugging. * **Human-AI Collaboration:** This structure shifted the QA's role from writing code to discussing failures and policy changes within the messenger threads. The success of this 5-month experiment suggests that for high-complexity environments, the future of QA lies in "AI Orchestration." Instead of focusing on writing selectors, QA engineers should focus on defining problems and managing the AI agents that build the architecture.

AIAI AgentsReactClaude+5