Loading…
Latest reads
Every post, summarised
Grounded summaries of engineering blogs, newest first. Each links to the original.
- 4,671 posts
- 20 companies
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
Latest posts
Introducing Grok 4.5
Cursor and SpaceXAI are releasing Grok 4.5, a mixture-of-experts model designed for long-running computer tasks beyond software engineering, including data science, finance, and legal work. It was trained jointly on trillions of tokens of Cursor data, alongside high-quality STEM tasks, research papers, and other knowledge work, then improved with reinforcement learning in realistic environments where it must investigate, use tools, recover from mistakes, and verify results. A distributed agent system built and refined these training environments at scale, using engineers’ problem definitions and verification methods. Grok 4.5 is available in Cursor’s desktop, web, iOS, CLI, and SDK products, with individual and team plans receiving significant usage and double usage during the first week; base pricing is $2 per million input tokens and $6 per million output tokens. Cursor notes that an accidental training-data inclusion gives the model an advantage on CursorBench.
How Uber Processes Early Chargeback Signals
Uber describes how it uses early chargeback signals, especially TC40 reports, to identify payment-fraud patterns before conventional chargebacks arrive. These notifications come from payment service providers through fraud reports and are ingested from external vendors via SFTP, third-party APIs, or webhooks, then validated, normalized, published to Apache Kafka, and stored in Apache Hive. A streaming pipeline maps signals to internal transactions and users, derives near-real-time features, and sends them to machine-learning models and a rule engine that determines risk actions. Redis TTL caching filters duplicate references, while Kafka propagates signals to downstream systems and Hive retains them for batch processing. Since launch, the project has processed more than 2 million additional signals, and TC40 signals arrive on average 4–5 days earlier than chargeback signals, although the source notes that TC40 data alone does not prevent chargebacks.
How Imperial College London is accelerating dementia research with a modern data platform
Imperial College London’s Care Research and Technology Centre (CR&T) needed to scale Minder, a platform that combines in-home sensors, sleep monitors, and electronic health records to support dementia care and research. Growing data volumes caused competing workloads, tightly coupled storage and compute, and limited access for researchers and clinicians. The re-architected platform validates IoT data through Kubernetes, stores it in Delta Lake on Azure Data Lake Storage using bronze, silver, and anonymized gold layers, and adds Databricks analytics with Unity Catalog governance while retaining FHIR-based EHR interoperability and Kubeflow for model deployment. Research-to-production workflows, reusable pipelines, dashboards, and timestamped data improve collaboration, accessibility, and reproducibility. During migration, uptime remained 100%; new sources integrated in as little as one month, model development fell to about one month, and insights reached 581 people living with dementia in five months.
NVIDIA Vera CPU Boosts AI Factory Throughput to Accelerate Agentic Workloads
Agentic AI workflows and reinforcement learning rely heavily on sequential CPU tasks, such as tool calls, sandboxed code execution, data processing, and environment rollouts between GPU steps. When CPU performance degrades under full socket load, training time inflates, serving latency grows, and GPU KV-caches face eviction. The NVIDIA Vera CPU addresses these bottlenecks by featuring 88 Olympus cores on a monolithic compute die, paired with power-efficient LPDDR5x memory and the Scalable Coherency Fabric. These cores incorporate a neural branch predictor, a 10-wide decode front end, deep out-of-order execution, and NVIDIA Spatial Multithreading. Consequently, Vera achieves 1.8x faster core execution, 40% lower peak loaded latency compared to x86 CPUs, and up to 1.2 TB/s total memory bandwidth, preventing costly KV-cache recomputations.
Contextual Policies in Omnigent: Using session state to better govern AI agents
Omnigent, an open-source meta-harness for AI agents, introduces contextual policies to make agent controls safer and less disruptive than per-action allow, deny, or approval rules. Policies receive session events, maintain private state such as tools used, documents read, accumulated risk, initial intent, and model spend, then allow, deny, transform, or escalate the next action. Omnigent’s server intercepts tool calls from supported agents and applies these policies consistently, while examples include Google Drive restrictions based on documents created or marked confidential, risk thresholds that require approval for later email or file-sharing actions, and budget thresholds that pause or redirect work to a cheaper model. Intent-based authorization limits tools according to the user’s opening request, applying least privilege across supported harnesses and custom agents. The project is described as open source and alpha, with the server providing one interception layer for agents using different harnesses.
AI needs the best-of-breed data stack: Postgres and ClickHouse
AI-native applications generate large volumes of operational data, while agents and users increasingly require real-time answers from that data. This pressure raises both query concurrency and reliability requirements, with a cited sample of companies using Postgres and ClickHouse showing more than 1,000% data growth in six months and over 85 TB added. The proposed stack assigns Postgres low-latency transactional workloads and ClickHouse real-time analytics, connecting them through PeerDB and ClickPipes CDC with single-digit-second replication, pg_clickhouse query pushdown, and pg_stat_ch telemetry streaming. The conclusion is that AI makes the OLTP/OLAP distinction more important, favoring an open best-of-breed stack over a single platform while preserving each database's specialized role.
Develop Humanoid Robot Policies End-to-End with NVIDIA Isaac GR00T
Humanoid robotics development suffers from fragmented tooling, siloed software ecosystems, and incompatible data formats that hinder reproducible workflows. NVIDIA introduced the Isaac GR00T Development Platform, an open-source, modular humanoid development environment that connects simulation setup, demonstration capture, policy training, evaluation, and hardware deployment. Central to this platform is the Isaac GR00T 1.7 vision-language-action model, which features a 3-billion-parameter base checkpoint licensed under Apache 2.0. The architecture adopts a Cosmos-Reason2-2B backbone and supports full pipeline export to ONNX and TensorRT for deployment on Jetson Thor. In a reference pick-and-place manipulation task, developers capture teleoperated demonstrations with Isaac Teleop, convert trajectories into LeRobot format, post-train GR00T 1.7, and evaluate the closed-loop policy inside Isaac Lab-Arena.
Maximize Spectral Efficiency with AI-Native RAN and NVIDIA AI Aerial
Massive MIMO deployments often fail to achieve theoretical spectral efficiency because CPU compute constraints force algorithmic compromises in user tracking, interference mitigation, and pairing. NVIDIA AI Aerial addresses this gap using a GPU-accelerated, AI-native radio access network architecture. This approach enables dense mathematical models across Layer 1 and Layer 2 workloads, including machine-learning beamforming and deep reinforcement learning link adaptation. In 64T64R simulations, AI beamforming achieved up to 1.62x higher throughput at 32 layers compared to regularized Zero Forcing baselines. The platform also unifies physical and MAC layer coordination while allowing dynamic allocation of spare GPU compute to edge AI inference.
Building an Analysis AI Agent for Industrial Alarm Management with NVIDIA Nemotron
Industrial machinery produces high volumes of alarms and sensor readings that exceed manual triage capacity. To address this bottleneck, an end-to-end GPU-accelerated AI agent is designed using NVIDIA NeMo libraries, Nemotron open models, and the NVIDIA OpenShell runtime behind a single HTTP endpoint. When triggered with an alarm payload and sensor frame, the agent gathers historical context using cuDF, cuVS, and NeMo Retriever, queries data warehouses via Text-2-SQL, and executes specialist signal checks with tools like cuFFT and cuML. Nemotron 3 Nano manages orchestration tasks while Nemotron 3 Super synthesizes the gathered evidence. The workflow outputs a structured package containing an observation, root-cause hypothesis, remedy, and recommended action within a seconds-long latency budget.
chDB as the Agent's Local Data Engine
Agents often make 5 to 20 tool calls per turn, and many of those calls retrieve data such as prior memory, recent events, or catalog records. When data is remote, round-trip latency compounds across sequential calls, while packet loss can trigger retries that increase both task time and token usage. The article presents chDB, which embeds a full ClickHouse query engine in the agent process, as a way to make data access local and CPU-bound rather than network-bound. For local memory, it combines structured, time-series, vector, and text-index capabilities with local storage and an embedding model, while append-only MergeTree rows preserve belief revisions, deletion markers, and point-in-time history. It also describes syncing trickle-written local memory to a warehouse on a slower cadence and using a materialized-view mirror for frequently accessed current state.
Notion HQ – Tools & craft – Notion
This Notion HQ page collects product announcements, company updates, and stories about extending Notion’s workspace. It introduces a Developer Platform, Custom Agents that handle entire workflows autonomously, Notion 3.0 with Agents, Notion Calendar, and Notion AI for Work, described as an all-in-one AI toolkit built into the workspace. The updates also cover connectivity and data consolidation, including the acquisition of Automate.io, which built integrations for more than 200 software tools, and the welcome of Sequin, whose tools brought data from across software stacks together. Additional announcements report ZeroEntropy joining Notion, a new board of directors, a security update dated July ’26, and a private tender offer involving GIC, Sequoia Capital, and Index Ventures. The page also includes Custom Agents beta learnings, conference highlights, and a profile of a Notion consultancy.
Introducing Okta Journeys: A Better Way for Developers to Learn Identity
Okta has introduced Journeys, a task-oriented documentation format designed to streamline how developers learn and implement identity management. Rather than requiring engineers to manually assemble information across disparate guides, articles, and API references, each Journey provides an end-to-end curriculum for a specific project. Content is organized into three distinct phases: foundational knowledge in Learn, architectural decision-making in Plan, and curated implementation steps in Build. The initial release includes six Journeys aimed at Okta Customer Identity builders who are implementing authentication, registration, branding, and user management. Future additions will address AI agent governance, integrations for the Okta Integration Network, and migrations from the Classic Engine to the Okta Identity Engine.
Introducing Atlas Gen2 on AWS and GCP for M30+ Dedicated Clusters
MongoDB Atlas introduced Gen2 for M30+ Dedicated Clusters on AWS and GCP, addressing the common inefficiency of overprovisioning storage to meet IOPS requirements. Gen2 runs on newer ARM-based processors, delivering a statistically significant 15-20% reduction in CPU utilization and approximately 45% lower read and write latency in internal pilots. It introduces extended standard IOPS that can be provisioned independently from storage capacity, allowing teams to scale performance without adding unused storage and gain more precise control over infrastructure costs. No application changes or migration are required; teams retain the same Atlas API, connection strings, and operational model while benefiting from newer infrastructure underneath. Gen2 is available in supported AWS and GCP regions across APAC and Europe, with limited U.S. availability on GCP, and existing customers can evaluate upgrade opportunities for eligible M30+ clusters.
Building safeguards for Claude
Claude’s Safeguards team describes a lifecycle approach to reducing misuse while keeping the model useful, combining policy, training, evaluation, real-time enforcement, and monitoring. The team uses a Unified Harm Framework spanning physical, psychological, economic, societal, and individual autonomy harms, and policy vulnerability testing with external experts to shape policies and defenses. Before release, Claude undergoes safety, risk, and bias evaluations, including capability uplift testing in high-risk domains; findings can lead to new detection methods or guardrails. After deployment, prompted or fine-tuned Claude classifiers monitor violations for response steering and account actions, while human review and CSAM hash matching support enforcement. Ongoing analysis uses privacy-preserving topic clusters, hierarchical summarization, and threat intelligence to identify aggregate misuse and novel attacks.
Barracuda makes security logs conversational with Genie
Barracuda Managed XDR needed to make security-log investigations accessible beyond analysts who knew each vendor’s schema and could write SQL. Its AI-Powered Log Search integrates Databricks Genie into the XDR dashboard: Genie translates natural-language questions into SQL, runs them against customer logs, and returns tabular results with the generated query. Security-specific metadata in Unity Catalog helps map requests across network, server, cloud, email, and endpoint sources, while multi-turn context supports iterative filtering. Secure views enforce organization-level filtering before execution; scoped service principals and SQL validation add further controls against cross-tenant access. Barracuda reports reducing routine investigation time from hours to minutes and estimates that self-service could free 83 to 100 SOC analyst hours monthly, or 1,000 to 1,200 annually.
Automatic Upgrades: best practice features for your lakehouse tables
Automatic Upgrades gives Unity Catalog managed tables a hands-off path to adopting best-practice table features without manually auditing thousands of tables or running ALTER TABLE repeatedly. It observes table access over a 100-day window, verifies that every accessing Databricks client supports the feature, skips inactive or externally accessed tables, and applies eligible changes through a lightweight background job. New tables inherit a feature when it becomes a schema default, while explicit table properties take precedence. Supported capabilities include Row Tracking, Automatic Liquid Clustering, Deletion Vectors, Column Mapping, Parquet V2, Catalog Commits, and Checkpoint V2, with benefits spanning query speed, storage and write costs, interoperability, and reliability. Changes are visible in DESCRIBE HISTORY and Catalog Explorer, reversible per table, and not re-enabled after a user disables one.
Enhancing Goodput in Large-Scale LLM Training with Nonuniform Tensor Parallelism
Large-scale LLM training jobs spanning thousands of GPUs frequently encounter transient hardware interruptions that bottleneck tightly coupled tensor parallel groups. Nonuniform Tensor Parallelism addresses this bottleneck by dynamically adapting the tensor parallelism degree within affected scale-up domains rather than dropping entire data replicas. When a GPU drops out, the system reconfigures the remaining functional devices to process larger shards and resumes execution from the latest checkpoint. To prevent the downsized replica from stalling global synchronization, advanced rack designs temporarily power-boost the active GPUs to increase clock frequencies and match baseline throughput. Overlapping the necessary tensor resharding with backward computation and parameter synchronization reduces overhead on healthy replicas to under one percent.
Reimagining Data Modeling on the Lakehouse: Introducing Vibe Data Modeling
Vibe Data Modeling is presented as a way to build a governed Silver-layer data model from a plain-English description of a business, addressing the months or years often required to hand-build one or adapt a generic industry template. The single-notebook implementation uses four widgets and a multi-model LLM agent to organize organizations into divisions, domains, subdomains, products, and attributes, then generate a logical model and deploy it to Unity Catalog. Its pipeline advances through four generate-and-validate stages, applying 251 rules, deterministic structural gates, two architect reviews, and a retry loop that changes strategy when checks fail. The authoritative model.json also produces schemas, Delta tables, informational foreign keys, classification tags, metric views, an RDFS ontology, DBML, and synthetic sample data, while plain-English refinements create auditable, reversible versions.
Government of Alberta uses Claude to find and fix cybersecurity vulnerabilities
The Government of Alberta’s Ministry of Technology and Innovation has used Claude Code with Claude Opus and Sonnet since 2025 to review, secure, and modernize systems spanning 27 provincial ministries. About 50 autonomous agents scanned 466 million lines across 3,400 repositories in roughly 20 hours, using a rules-engine first pass followed by reviews that cite exact files and lines; Alberta estimates a traditional review could take around 6.5 years. Claude Code also generated and tested fixes, wrote missing tests, and rebuilt some obsolete applications, with Ministry engineers approving patches before release. Specialized red-team and blue-team agents now run continuous checks against roughly 95 security controls, while the Alberta AI Academy trains employees and members of the public. The government plans to consolidate 185 legacy applications into 16 reusable modern applications, a future goal rather than a reported result.
Scaling Security Alert Triage With Specialized Agents on Databricks
Databricks describes a security-alert triage system designed to review low-severity alerts that historically received less attention because of their volume and low fidelity. An initial single-agent prompt escalated 50% of alerts, so the team built a fleet of 17 source-specific agents plus a Threat Intelligence agent, using Structured Streaming to ingest alerts, enrich evidence, and route each alert. The pipeline combines deterministic benign-signal filtering, historical and behavioral context, specialized prompt functions, optional tools, structured dispositions, and cost controls before sending escalations to human analysts. Those analysts provide ground truth through MLflow traces and labels, supporting ongoing evaluation across escalate, monitor, and close decisions. After triaging more than 18,000 alerts, the system reached a 3.2% escalation rate, a 10.5-second median triage time, and more than 6,500 analyst hours saved in 30 days; escalated low-severity alerts were roughly 10 times more likely to be true positives than HIGH and MEDIUM alerts.
Top topics
- Architecture834
- Performance816
- LLMs660
- Machine Learning622
- Open Source563
- AI Agents553
- AI470
- Developer Experience448
Weekly digest
The best engineering reads, once a week.