---
title: "Latest reads"
description: "The engineering internet, summarised so you can actually read it."
---

# Latest reads
> The engineering internet, summarised so you can actually read it.

## Articles

### [Why we built ADK 2.0](https://yomu.fyi/post/why-we-built-adk-2-0.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Swapnil Agarwal, Alan Blount, Frank Guan
- Published: Jul 1, 2026
- Type: Explainer

ADK 2.0 addresses the structural challenge of moving AI agents from prototypes into production, where infinite loops, hallucinated bypasses, and failures without clean exceptions make model-led orchestration unreliable. Because language models are slow, costly, and variable for routing, scheduling, and error handling, the release separates execution routing from language processing and reserves LLMs for ambiguous or cognitive steps. Building on ADK v1’s support for Python, Java, Go, TypeScript, and Kotlin, it adds a structured workflow runtime and task-collaboration model, with Workflows available in Python since March and newly launched for Go. Deterministic graphs combine tool calls, Human-in-the-Loop steps, and specialized agents with explicit branching and error handling. Dynamic workflows extend this model with native Python and asyncio control flows for retries, branching, and reusable sub-workflows.


### [From monolith to Lakebase to LTAP: rethinking the database from storage up](https://yomu.fyi/post/from-monolith-to-lakebase-to-ltap-rethinking-the-database-from-storage.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Reynold Xin
- Published: Jun 30, 2026
- Type: Explainer

The post examines why monolithic OLTP databases become fragile and difficult to scale when compute, the write-ahead log (WAL), and data files share one machine. Using Postgres as its primary example, it contrasts local WAL durability and physical cloning with Lakebase, whose stateless Postgres compute externalizes those components into SafeKeeper and PageServer services. SafeKeeper replicates log records across a quorum through Paxos-based network replication, while PageServer applies the WAL and materializes data in cloud object storage. The resulting separation is presented as a way to improve durability, independently scale reads and writes, isolate workloads, and support high availability and branching without physical database clones. LTAP extends the design by making transactional tables directly queryable for analytics from a single governed copy, avoiding CDC or mirroring and allowing transactional and analytical engines to scale independently.


### [Designing GPU-Accelerated Query Engines with NVIDIA GQE](https://yomu.fyi/post/designing-gpu-accelerated-query-engines-with-nvidia-gqe.md)
- Company: [NVIDIA](https://yomu.fyi/company/nvidia-developer-blog.md)
- Author: Michelle Horton
- Published: Jun 30, 2026
- Type: Explainer

GPU-accelerated query engines encounter performance constraints stemming from memory and I/O bandwidth limitations. NVIDIA introduces GQE, a reference architecture using NVIDIA cuDF, nvCOMP, and other CUDA-X libraries to accelerate SQL query execution across modern hardware like the NVIDIA GB200 NVL4. The architecture coordinates three distinct layers: a query layer consuming Substrait plans, a data layer managing in-memory table transfers, and an execution layer executing relational operator task graphs. GQE employs pipeline parallelism, partition pruning, hybrid compression, and batched asynchronous transfers to overlap data movement with GPU compute. On a non-standard 1 TB TPC-H benchmark, GQE on a single B200 GPU achieved a 7.5x total execution time speedup over dual-socket CPU configurations running DuckDB.


### [10 Years of Meta’s Commitment to Python](https://yomu.fyi/post/10-years-of-meta-s-commitment-to-python.md)
- Company: [Meta](https://yomu.fyi/company/meta.md)
- Published: Jun 30, 2026

Meta has marked ten consecutive years as a sponsor of the Python Software Foundation (PSF) to ensure the language remains robust and sustainable. Python represents the most widely used programming language across Meta's infrastructure, powering applications like Instagram and Threads as well as internal AI research. Beyond financial backing, Meta engineers actively contribute core language features, author Python Enhancement Proposals (PEPs), and build open-source tools such as the Pyrefly type checker. Company sponsorship directly funds the PSF's Developer-in-Residence program, core infrastructure, and security enhancements for the Python Package Index (PyPI). Continued support of the PSF functions as a strategic investment in maintaining the stability of the broader open-source ecosystem.


### [Optimizing a Neural Reconstruction Pipeline Using NVIDIA Nsight Developer Tools](https://yomu.fyi/post/optimizing-a-neural-reconstruction-pipeline-using-nvidia-nsight-develo.md)
- Company: [NVIDIA](https://yomu.fyi/company/nvidia-developer-blog.md)
- Author: Tanya Lenz
- Published: Jun 30, 2026
- Type: Problem & solution

NVIDIA Omniverse NuRec reconstructs dynamic 3D environments from camera and lidar sensor data for autonomous vehicle simulation workflows, but high computational demands historically caused long reconstruction times. Engineers used NVIDIA Nsight Systems and Nsight Compute to systematically profile the PyTorch-based training pipeline and optimize its underlying CUDA kernels. Nsight Systems revealed GPU underutilization caused by numerous small kernels and blocking synchronization calls, leading to a fused interpolate kernel that accelerated execution from 4.184 milliseconds to 83.81 microseconds. Profiling with Nsight Compute uncovered resource mismatch in the renderBackward kernel, prompting the team to split it into dedicated camera and lidar implementations with tuned register and shared memory allocations. These adjustments raised kernel occupancy from approximately 15% to between 30% and 50% while decreasing the longest lidar kernel runtime from 31 milliseconds to 18 milliseconds.


### [A Quadrillion Rows across three Clouds: scaling LogHouse](https://yomu.fyi/post/a-quadrillion-rows-across-three-clouds-scaling-loghouse.md)
- Company: [Clickhouse](https://yomu.fyi/company/clickhouse.md)
- Published: Jun 30, 2026
- Type: Problem & solution

LogHouse now stores 431 PiB of uncompressed data across 1.59 quadrillion rows, spans more than 30 regions across three cloud providers, and serves typical queries in a few hundred milliseconds. The platform grew 23x from 19 PiB in two years, while peak ingestion reached 80 GiB/s and 190 million rows per second. Its write architecture uses local geosharding, multiple cells in busy regions, and ClickHouse Async Inserts to combine small incoming writes into larger parts without overwhelming merges. On the read side, a single Distributed table hides the cell topology, while unavailable shards remain visible by default rather than producing silently incomplete results. Current work includes reducing index and metadata memory, improving async-insert durability, collecting system data from object storage, and expanding OpenTelemetry traces and metrics.


### [Agentic Risk Operations](https://yomu.fyi/post/agentic-risk-operations.md)
- Company: [Ramp](https://yomu.fyi/company/ramp.md)
- Author: Blake Williams, Mueed Rehman, Vishal Sundaram, Brad Hoeweler
- Published: Jun 30, 2026
- Type: Problem & solution

Ramp describes an architecture for scaling risk operations as payment volume, payment rails, partners, and country coverage expand, rather than letting headcount grow with the business. Agents handle universal intake, gather business context, classify requests, and route work, while machine-learning models trained on millions of historical data points and approved policies make autonomous risk decisions. Operators can modify agent skills and tool configurations without engineering involvement, deploy changes in shadow mode, and rely on asynchronous execution, provider failover, and centralized observability. In payment-risk workflows, structured operator feedback produced a benchmark of more than 1,000 operations covering tool-call trajectories, operator alignment, and downstream outcomes, enabling separate evaluation of agents and policies. Ramp rolls agents out beside operators, then scales operation types and dollar volume using performance thresholds and capped exposure budgets.


### [Why intent prediction needs more than an LLM](https://yomu.fyi/post/why-intent-prediction-needs-more-than-an-llm.md)
- Company: [Stack Overflow](https://yomu.fyi/company/stack-overflow.md)
- Author: Phoebe Sajor
- Published: Jun 30, 2026
- Type: Explainer

Traditional large language models rely on next-token prediction trained over broad text sequences, excelling at conversational synthesis and code generation while struggling with forecasting future user behavior. Predicting intent inherently requires modeling decision-making under conditions of uncertainty, a capability not directly produced by general text pretraining. Dedicated behavioral foundation models address this limitation by training representations directly on proprietary, sensitive behavioral data, such as anonymous browsing sessions and product identifiers. By learning base representations of behavior, these models generalize to unseen predictive tasks, such as optimizing ad campaigns for products absent from the original training dataset. Implementing these behavioral models also necessitates privacy-centric machine learning techniques, ranging from differential privacy concepts to homomorphic machine learning.


### [Agentic Coding on Supabase with OpenCode](https://yomu.fyi/post/agentic-coding-on-supabase-with-opencode.md)
- Company: [Supabase](https://yomu.fyi/company/supabase.md)
- Author: ekhar
- Published: Jun 30, 2026
- Type: Announcement

Supabase has made its OpenCode integration available, connecting an AI coding agent to Supabase account and project management APIs and bundled Supabase skills. Users invoke /supabase, authenticate, and, for database, Edge Functions, logs, and other project-scoped capabilities, are guided through connecting Supabase MCP; the integration requires OpenCode 1.3.4 or later. It can list organizations and projects, create projects, open the MCP setup flow, monitor agent activity in real time, and let agents query data, check logs, and deploy functions, while the plugin is open source. The post demonstrates the workflow in Minecraft, where OpenCode connected through MCP, created and populated a table, and deployed an Edge Function on a real Supabase project.


### [Anthropic integration with Modal brings scalable compute to Claude Science](https://yomu.fyi/post/anthropic-integration-with-modal-brings-scalable-compute-to-claude-sci.md)
- Company: [Modal](https://yomu.fyi/company/modal.md)
- Published: Jun 30, 2026
- Type: Announcement

Anthropic launched Claude Science, an AI workbench where life sciences researchers run computational workloads from conversation with Claude. The workbench addresses the fragmented toolchain of local machines, HPC clusters, and cloud VMs by centralizing execution in one place. Modal integrates with Claude Science as the compute backend, routing GPU and CPU-heavy workloads to Modal sandboxes automatically and fanning out parallel tasks like virtual screening across hundreds of containers to reduce hours to minutes. Researchers can prompt for tasks such as predicting GFP structure, and Claude writes the folding code, runs it on a Modal GPU, and returns the structure with confidence scores inside the conversation, with Modal handling scheduling, shared storage, and reproducible environments. Modal is committing up to $100,000 in compute for the Claude Science Cohort, with 500– 2,000 allocations per project.


### [Together AI at ICML 2026: frontier research across the full stack](https://yomu.fyi/post/together-ai-at-icml-2026-frontier-research-across-the-full-stack.md)
- Company: [Together AI](https://yomu.fyi/company/together-ai.md)
- Published: Jun 30, 2026
- Type: Announcement

Together AI says nine papers from its researchers and peers were accepted to ICML 2026 in Seoul, spanning frontier agents, model shaping, algorithmic and systems optimization, and kernels. The collection is presented as a full-stack view of AI research, with work ranging from DSGym’s unified evaluation and training API for more than 1,000 data-science tasks to ThunderAgent’s program-aware scheduling, TTT-Discover’s test-time reinforcement learning, and RARO’s verifier-free adversarial training. Reported results include up to 3.6× agent throughput, state-of-the-art discoveries from an open 120B model, a 25% expert-response win rate without a verifier, and 5M-token context on one node for Untied Ulysses. Aurora illustrates the research-to-production loop: its adaptive speculative-decoding work ships as the ATLAS speculator on the Together platform.


### [Build reliable multi-agent applications with ADK Go 2.0. Discover our new graph-based workflow engine, built-in human-in-the-loop, and dynamic orchestration](https://yomu.fyi/post/build-reliable-multi-agent-applications-with-adk-go-2-0-discover-our-n.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Toni Klopfenstein, Sampath Kumar Maddula
- Published: Jun 30, 2026
- Type: Announcement

ADK for Go 2.0 introduces a graph-based workflow engine for composing multi-agent applications whose execution can classify, branch, fan out, gather results, pause for human input, retry, and loop. Graphs consist of typed nodes and routed edges, with constructors for functions, emitting functions, agents, tools, joins, parallel workers, state-bound nodes, dynamic orchestration, and nested workflows; a scheduler handles concurrency, persistence, backpressure, cancellation, and resumption. Its built-in human-in-the-loop primitive validates responses, supports handoff or re-entry, and can resume durably after process restarts, while agent modes and a unified node runtime align single agents with full graphs. The release is highly additive for ADK 1.0 users, though context and event APIs require mechanical migrations, and it provides workflow examples for basic, routing, dynamic, HITL, and complex graphs.


### [Driving the Agent Quality Flywheel from Your Coding Agent](https://yomu.fyi/post/driving-the-agent-quality-flywheel-from-your-coding-agent.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Dima Melnyk, Jason Dai
- Published: Jun 30, 2026
- Type: Tutorial

The quality-flywheel skill addresses the gap between prompt tweaks that improve a few examples and evidence that an agent improved without regressions. A coding agent orchestrates dataset preparation, inference, trace grading, failure analysis, and optimization, using Google's adaptive AutoRaters or custom metrics while keeping the optimizer and evaluator independent. In a travel-concierge example, the revision\_honored rubric found that 21% of cases ignored mid-conversation trip changes, exceeding the stated action threshold. A separate software-bug-assistant cycle raised tool-disclosure responses from 0% to 96% across 15 cases, while production traces and online monitors extend the same loop beyond synthetic scenarios. Human approval remains required, and adaptive scores are treated as directional signals rather than absolute grades.


### [The Builder Revolution: Why We're Shifting to Builder Advocacy](https://yomu.fyi/post/the-builder-revolution-why-we-re-shifting-to-builder-advocacy.md)
- Company: [Okta](https://yomu.fyi/company/okta.md)
- Author: Michael Palermo
- Published: Jun 30, 2026
- Type: Announcement

The team formerly known as Developer Advocacy, within Developer Success, has been renamed Builder Advocacy within Builder Experience (BX). The change responds to an expanded definition of who builds with technology: alongside traditional developers, AI builders and no-code or low-code automators are creating production-level experiences and mission-critical infrastructure. The organization says its advocacy will serve developers, prompt engineers, LLM integrators, AI-agent creators, ML practitioners, and automation-focused builders, while continuing support for traditional coders, engineers, and architects. The announcement cites GitHub’s 180 million developers, 36 million new developers in 2025, and Stack Overflow’s finding that 84% use or plan to use AI tools. The rename is effective immediately and begins broader investments in resources, content, and community programs for this wider builder community.


### [Clever ingests 200x more logs at the same cost with ClickHouse Cloud](https://yomu.fyi/post/clever-ingests-200x-more-logs-at-the-same-cost-with-clickhouse-cloud.md)
- Company: [Clickhouse](https://yomu.fyi/company/clickhouse.md)
- Published: Jun 30, 2026
- Type: Problem & solution

Clever, an identity platform for K-12 education, faced a fragmented logging setup as its 400 services and 200 AWS Lambdas generated about 150 TB of uncompressed logs monthly. Datadog indexed only about 10% and retained it for three days, while the remainder was in Athena and required SQL. Clever migrated to ClickHouse Cloud on AWS, indexing all logs with 60-day retention and reporting 200× more searchable log volume at no additional cost, with 10× compression. Its design extracts frequently queried JSON fields into columns, stores remaining attributes in a map alongside raw JSON, uses skipping indexes, date partitions, a 60-day TTL, and reverse Unix timestamp ordering; this ordering produced an 8–10× query speedup. A custom query layer translates LogQL to SQL, while separate development and production services and multi-region deployment address isolation and availability.


### [How Jua delivers the world’s most accurate physics simulations 3x faster with ClickHouse Cloud](https://yomu.fyi/post/how-jua-delivers-the-world-s-most-accurate-physics-simulations-3x-fast.md)
- Company: [Clickhouse](https://yomu.fyi/company/clickhouse.md)
- Published: Jun 30, 2026
- Type: Problem & solution

Jua uses ClickHouse Cloud to deliver data from EPT-2, its physics foundation model, to energy traders and grid operators faster than its previous file-based pipeline. Jua’s forecasts combine outputs from multiple models and add roughly four terabytes of new data daily, producing about one petabyte compressed and over 10–12 petabytes uncompressed. Replacing Zarr and other file-based storage plus manual pre-fetching with ClickHouse Cloud reduced flagship forecast delivery from one hour to 20 minutes, with about 20 seconds of upload overhead. The platform also cut compute costs by roughly a third, reduced two-year single-location historical queries from hours to seconds, and supports both point lookups and regional aggregations; Jua selected the managed service for operational simplicity, separated storage and compute, and cost efficiency.


### [Teen rides return to Los Angeles](https://yomu.fyi/post/teen-rides-return-to-los-angeles.md)
- Company: [Uber](https://yomu.fyi/company/uber.md)
- Published: Jun 29, 2026
- Type: Announcement

Uber for teens is now available in Los Angeles, allowing teens to request their own rides while guardians can book rides on their behalf. The service lets guardians track trips live, sends realtime notifications, pairs teens with highly rated drivers, and keeps PIN verification and RideCheck enabled for every ride. Guardians and teens can also message the driver in a shared group chat, while on-demand pickups and dropoffs must remain within the designated service area; Reserve trips remain available outside it. To book, a guardian selects “Where to?”, changes the rider from “For me” to the relevant teen, and chooses “Uber for teens.” Trips to or from airports cannot currently be requested.


### [Washington: Background Check Criteria Disclosure](https://yomu.fyi/post/washington-background-check-criteria-disclosure.md)
- Company: [Uber](https://yomu.fyi/company/uber.md)
- Published: Jun 29, 2026
- Type: Explainer

Uber’s Washington State driver-screening disclosure sets time-based limits on driving violations, criminal charges, and convictions for people seeking to provide rides on the platform. Drivers may have no more than three minor driving violations in three years, while major driving violations and pending criminal matters such as driving while unlicensed or uninsured are disqualifying during that period. A broader seven-year bar covers felonies and specified offenses including violence, theft, fraud, DUI-related violations, hit and run, reckless driving, and speeding over 100 MPH; the disclosure also bars serious offenses including sexual crimes, murder, kidnapping, and active warrants. Seattle and King County add a seven-year licensing-related rule, while Vancouver adds tighter recent-violation limits and separate felony and drug-offense lookbacks.


### [How to Govern Autonomous Agents in Enterprise AI Factories](https://yomu.fyi/post/how-to-govern-autonomous-agents-in-enterprise-ai-factories.md)
- Company: [NVIDIA](https://yomu.fyi/company/nvidia-developer-blog.md)
- Author: Michelle Horton
- Published: Jun 29, 2026
- Type: Problem & solution

Autonomous AI agents require governed environments to safely inspect code, execute tests, query enterprise systems, and handle sensitive business data. The NVIDIA Secure Agent Workspace Reference Design shifts agent execution away from user laptops to dedicated, single-user virtual machines managed on Red Hat OpenShift Virtualization or Microsoft Azure. Perimeter defenses enforce enterprise single sign-on access broker connections, default-deny network egress rules, and human approval gates for critical state-changing actions. Inside the workspace virtual machine, active sandboxing through NVIDIA OpenShell evaluates signed security policies before each tool invocation while credential proxies prevent direct access to raw secrets. GitOps workflows continuously reconcile infrastructure profiles and network configurations while all operational and security telemetry streams to centralized SIEM platforms in OCSF format.


### [Washington State Driver Information](https://yomu.fyi/post/washington-state-driver-information.md)
- Company: [Uber](https://yomu.fyi/company/uber.md)
- Published: Jun 29, 2026
- Type: Explainer

This page outlines benefits, protections, rights, and eligibility information for drivers operating on the Uber platform in Washington state. Starting July 1, 2026, drivers may request a downloadable CSV report containing two years of Washington mobility trip receipt data through drivers.uber.com; an email with an access link will arrive within three business days, and the link expires after seven days. It directs drivers to multilingual notices about driver rights and Paid Sick Time, states that drivers may be entitled to Paid Sick Time and Unemployment Benefits, and provides contact information for appealing deactivation through Drivers Union. The page also describes background check criteria for operating on the platform, noting that different criteria may apply in Seattle and King County.


[Newer posts](https://yomu.fyi/posts/page/102.md) · [Older posts](https://yomu.fyi/posts/page/104.md)