---
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

### [How we AI-updated 1,138 Error-code Docs Pages](https://yomu.fyi/post/how-we-ai-updated-1-138-error-code-docs-pages.md)
- Company: [Twilio](https://yomu.fyi/company/twilio.md)
- Author: Maria Bermudez
- Published: Sep 17, 2026
- Type: Explainer

Twilio used AI to update 1,138 error-code documentation pages over about 12 weeks, with a human reviewing every change. The team first scored roughly 2,692 pages with a deterministic script covering structure, content, and resources, then routed low-scoring pages to an LLM pipeline while sending borderline pages to human review. That pipeline used OpenAI's gpt-5.4 via the Responses API, generated full-file responses, sanitized them, converted them into git apply patches, linted results, and rejected any page whose code snippet fingerprint changed. Small-batch pull requests, tracking files, local-modification checks, and named reviewers limited duplicate work and kept approval in the workflow. Across about 27 pull requests from March to May 2026, the process marked 1,138 error codes complete, while the team acknowledged that human review was the quality bar and that future scaling would benefit from an automated evaluation harness and diff-based generation.


### [Twilio’s 2026 Heightened Awareness Period: Ensuring Reliable Messaging for Peak Season](https://yomu.fyi/post/twilio-s-2026-heightened-awareness-period-ensuring-reliable-messaging.md)
- Company: [Twilio](https://yomu.fyi/company/twilio.md)
- Published: Sep 17, 2026
- Type: Announcement

Twilio has scheduled two 2026 Heightened Awareness Periods (HAPs) to manage messaging throughput during U.S. midterm election traffic and the Black Friday/Cyber Monday and holiday shopping surge. During these windows, high-volume short code and toll-free traffic shifts temporarily to Market Throughput, while 10DLC remains on Account-Based Throughput and RCS uses standard per-sender limits; contracted limits are honored. Most users need no action, but election senders should contact their account team by October 1, 2026, and holiday senders face deadlines for RCS approval, throughput review, A2P 10DLC requests, and supplementary orders. The election HAP runs November 2–4, 2026, while the holiday HAP runs November 19, 2026, through January 4, 2027; capacity is limited and allocated first come, first served.


### [Full Linux VMs for your agents](https://yomu.fyi/post/full-linux-vms-for-your-agents.md)
- Company: [Boxcompute](https://yomu.fyi/company/boxcompute.md)
- Author: boxy
- Published: Sep 17, 2026
- Type: Announcement

BoxCompute VM Sandboxes are now the default runtime for every account, giving agents a full Linux virtual machine rather than a shared-kernel gVisor container. Each disposable VM boots its own kernel and provides root access, outbound internet with public IPv4 and DNS, and a unified approximately 10 GiB filesystem covering / and /workspace, while preserving the existing create, execute, file-transfer, and delete API. The CLI or HTTP API can create a VM, and users can opt out with vmSandbox: false or disable networking with blockNetwork: true. VMs remain billable until explicitly deleted and currently use a fixed profile of 0.5 CPU, 1 GiB memory, and a minimal Ubuntu image. The beta does not include inbound ports, SSH, custom images, or volumes.


### [Why client SDK generation belongs in the open](https://yomu.fyi/post/why-client-sdk-generation-belongs-in-the-open.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Amir Hardon, Philipp Schmid
- Published: Sep 17, 2026
- Type: Announcement

Google describes partnering with Speakeasy to open-source the OpenAPI code-generation suite used for new SDKs for its Interactions, Agents, and Webhooks APIs. The change follows the May 2026 shutdown of a proprietary SDK-generation provider, which exposed platform risk while Google was preparing the Interactions API for general availability; migration prioritized avoiding breaking changes and preserving type definitions, strict error hierarchies, and streaming behavior. The AGPLv3 suite generates statically typed libraries for Python, TypeScript, Go, Java, C#, PHP, and Ruby, plus standalone agent-native CLI binaries and documentation MCP servers built from OpenAPI specifications and Markdown. Google says a deterministic generator paired with Antigravity AI agents now supports its pipeline across six targets, including three released SDKs, with roughly one engineer maintaining it, while generated code can remain under a chosen license such as MIT or Apache 2.0.


### [Preventing Destructive Actions with Step-up Authentication](https://yomu.fyi/post/preventing-destructive-actions-with-step-up-authentication.md)
- Company: [Auth0](https://yomu.fyi/company/auth0.md)
- Author: Jessica Temporal
- Published: Sep 17, 2026
- Type: Tutorial

The Agentic Arcade’s admin panel adds an admin-only “reset all scores” action to prevent a long-lived or stolen admin session from wiping every player’s history. It combines the arcade-admin role with step-up MFA, requiring a recognized MFA signal and auth\_time or iat within five minutes. A shared helper checks amr, acr, or a tenant claim; buildMfaStepUpUrl uses acr\_values and can add max\_age=0, while mfa.challengeWithPopup() opens MFA before the reset request. A beforeSessionSaved hook preserves claims filtered by the Auth0 Next.js SDK, and the API enforces session, role, and freshness gates before clearing scores; cancelled or blocked popups stop the request.


### [REVERSAL-BENCH: A Reversibility Axis and Reset Oracle for Measuring the Reset-Free RL Cliff](https://yomu.fyi/post/reversal-bench-a-reversibility-axis-and-reset-oracle-for-measuring-the.md)
- Company: [Apple](https://yomu.fyi/company/apple.md)
- Published: Sep 17, 2026
- Type: Benchmark

REVERSAL-BENCH addresses the challenge of evaluating reset-free reinforcement learning when environments contain irreversible transitions. It controls reversibility with continuous parameter ρ ∈ \[0, 1\] and supplies a reset oracle, a ground-truth mechanism for verifying state recoverability across eight manipulation settings and five physics engines. Evaluations spanning standard actor-critic, safe reinforcement learning, and specialized reset-free methods find a sharp reversibility cliff: reset-free agents become absorbed into irrecoverable states as ρ increases, while episodic agents maintain steady learning. Geometrically identical reversible counterparts indicate the breakdown is caused by irreversibility rather than obstacle complexity, and the effect persists under learned policies in full physics simulations. The released suite includes a multi-simulator dataset with recoverability labels and a reset oracle; a safety shield predicts recoverability accurately, but active recovery mainly works when agents can steer away from traps.


### [A multi agent approach audience intelligence](https://yomu.fyi/post/a-multi.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Bradley Munday, Tyler Hickey
- Published: Sep 17, 2026
- Type: Explainer

Advertisers often lose strategic intent when campaign briefs become data queries, while planners and data teams also miss insights hidden across large customer datasets. An AI-powered audience generation solution on the Databricks Data + AI Platform addresses this gap by combining Genie, custom tool-calling agents, Agent Bricks, Unity Catalog, and a Databricks App. Planners describe audiences in natural language; Genie produces governed SQL segments, an Affinity Agent calculates statistically validated lift against the full population, and a Supervisor Agent routes or chains these capabilities. The resulting workflow saves audiences in Unity Catalog for auditability and downstream activation, and is described as compressing planning and iteration cycles from days or weeks to minutes while enabling faster response to market shifts and pacing issues.


### [Worker Backpressure (Part 1)](https://yomu.fyi/post/worker-backpressure-part-1.md)
- Company: [Canva](https://yomu.fyi/company/canva.md)
- Author: Mikalai Barysau
- Published: Sep 17, 2026
- Type: Explainer

Canva’s queue workers were designed to consume messages greedily, but that behavior could amplify dependency failures, waste scarce capacity, fill dead-letter queues, and create on-call work. Worker Backpressure adds a local feedback loop to the shared queue library: each processed message reports success or failure, a pluggable controller maintains a 0.0-to-1.0 backoff factor against a configured failure-rate set point, and permits scale concurrency at each poll. The mechanism requires no external coordinator or network calls and adds two arithmetic operations to the runtime path, while trading some throughput for failure containment. In two production incidents, it reduced worker pressure during errors and recovered automatically; one sustained-overload incident recorded a 2.76% average failure rate, 22 DLQ messages over 32.5 hours, and no paging, while rollout to all queue workers remained the immediate goal.


### [How to Use AI Agents to Prepare 3D Scenes for Simulation](https://yomu.fyi/post/how-to-use-ai-agents-to-prepare-3d-scenes-for-simulation.md)
- Company: [NVIDIA](https://yomu.fyi/company/nvidia-developer-blog.md)
- Author: Tanya Lenz
- Published: Sep 16, 2026
- Type: Tutorial

Preparing a Blender scene for robotics simulation requires more than exporting attractive assets: the world needs semantic labels, simulation-aware materials, sensors, collision geometry, physics properties, and validation against a target profile. The described workflow uses Codex or Claude as an orchestration agent, NemoClaw to coordinate specialized Hermes subagents, and NVIDIA Omniverse Libraries to inspect, modify, render, and validate the scene. Blender MCP supplies a structured inventory, while OpenUSD becomes the shared scene contract; ovphysx handles physics authoring and checks, and ovrtx produces visual preflight views. Safe mechanical repairs can be automated, but ambiguous choices such as semantic labels or physical behavior are escalated to a human, with follow-up checks run after approved changes. The intended handoff is a simulation-ready USD world for NVIDIA Isaac Sim or NVIDIA Isaac Lab.


### [TensorRT Edge-LLM Completes the MLPerf Edge Agentic Benchmark 6.4x Faster on Jetson AGX Thor](https://yomu.fyi/post/tensorrt-edge-llm-completes-the-mlperf-edge-agentic-benchmark-6-4x-fas.md)
- Company: [NVIDIA](https://yomu.fyi/company/nvidia-developer-blog.md)
- Author: Elizabeth Goodman
- Published: Sep 16, 2026
- Type: Benchmark

Edge agentic workloads require repeated tool-calling turns, growing conversation histories, and valid function calls on constrained devices rather than single-prompt responses. On one NVIDIA Jetson AGX Thor Developer Kit, TensorRT Edge-LLM ran Qwen3.6-27B in SingleStream mode and completed the benchmark’s 1,007-turn performance workload in 24 minutes and 36 seconds, versus 2 hours and 37 minutes for the llama.cpp reference run. It reported 52.33 tokens per second, 247.12 ms median time to first token, and 87.94% BFCL overall accuracy. The implementation combines NVFP4 weights and activations, FP8 KV cache, reusable prompt prefixes with recurrent-state restoration, and tree-based multi-token prediction; roughly 96% of prompt tokens used hot cache, while tree-based MTP could achieve about 40% more decoding performance than linear MTP with three draft steps.


### [When scanners miss the attack: how Cloudflare Client-Side Security protects storefronts](https://yomu.fyi/post/when-scanners-miss-the-attack-how-cloudflare-client-side-security-prot.md)
- Company: [Cloudflare](https://yomu.fyi/company/cloudflare.md)
- Author: Juan Miguel Cejuela
- Published: Sep 16, 2026
- Type: Explainer

Modern storefronts can appear healthy while malicious JavaScript diverts affiliate credit, hijacks searches or clicks, tampers with analytics, or loads further code. Cloudflare describes four operations spanning eight payloads that Page Shield ML detected in live traffic; humans verified the findings afterward, while seven payloads were absent from VirusTotal and none received a malicious verdict from URLScan. The detection system represents JavaScript as a graph with a graph neural network (GNN), sends fewer than 0.3% of analyzed scripts to a lightweight LLM on Workers AI, and uses a teacher cohort of frontier models for difficult investigations. This combination handles minification, renaming, some obfuscation, and behavior gated by device, time, geography, referrer, browser state, or cooldowns. The post concludes that continuous browser visibility and runtime context are needed because static, one-time scans can miss selectively executed attacks.


### [ClickHouse is now available on the dbt platform](https://yomu.fyi/post/clickhouse-is-now-available-on-the-dbt-platform.md)
- Company: [Clickhouse](https://yomu.fyi/company/clickhouse.md)
- Published: Sep 16, 2026
- Type: Announcement

The ClickHouse adapter for dbt v2, dbt’s Rust rewrite, entered public beta on September 16, 2026, while ClickHouse became a natively supported data warehouse on the dbt platform in private beta. The v2 adapter ships inside the open-source dbt binary, connects through an ADBC driver using Apache Arrow, and supports both open-source ClickHouse and ClickHouse Cloud. Existing models, tests, and profiles carry over, although some features remain incomplete and dbt plans to support the v1 and v2 adapters in parallel. The platform integration provides ClickHouse connections for Studio, environments, scheduled jobs, and Catalog, while the planned path to general availability includes parity items such as ON CLUSTER DDL and distributed materializations, followed by Fusion capabilities.


### [AI Changed How Spotify Builds. What We Learned (and Fixed) About Quality at Higher Velocity](https://yomu.fyi/post/ai-changed-how-spotify-builds-what-we-learned-and-fixed-about-quality.md)
- Company: [Spotify](https://yomu.fyi/company/spotify.md)
- Author: Spotify Engineering
- Published: Sep 16, 2026
- Type: Incident / postmortem

Spotify examines how AI-accelerated development and broader industry compute demand challenged quality across content processing, fleet updates, regional failover, and the mobile app. At its scale—777 million monthly active users, about 100 million concurrent clients, 11–12 million backend requests per second, and nearly 3,000 production services—small control gaps can become visible to listeners and creators. A June 24 processing incident combined competing batch work, higher per-episode compute, and a scheduler bug that cut throughput about 10%, leading to hour-long publication delays; Spotify responded with end-to-end monitoring, scheduler fixes, prioritization, and more capacity. Incident reviews found no material direct contribution from AI-authored code, but change volume outpaced some verification controls, prompting stronger review, testing, rollout, observability, rollback, quality signals, and failover practices. Spotify reports no corresponding rise in rework rate, while continuing to watch increasing PR size and complexity.


### [How Data 360 Builds Trusted Context: The Enduring Layer for Enterprise AI](https://yomu.fyi/post/how-data-360-builds-trusted-context-the-enduring-layer-for-enterprise.md)
- Company: [Salesforce](https://yomu.fyi/company/salesforce.md)
- Author: Scott Nyberg
- Published: Sep 16, 2026
- Type: Explainer

Enterprise AI needs a way to assemble the smallest sufficient set of current, relevant, and authorized evidence for each agent turn instead of sending an entire data estate to a model. Salesforce presents Data 360 as a shared Trusted Context runtime spanning Salesforce, external platforms such as Databricks and Snowflake, operational systems, documents, knowledge bases, and live signals. Its progressive pipeline connects data through ingestion and Zero Copy, then harmonizes, unifies, models, retrieves, reconciles, governs, and compiles evidence into a token-fit Context Pack with citations and action contracts. The Agent Context Engine also returns typed interaction traces, promoting only approved facts into durable memory and validated outcomes into learnings. Q2 FY27 production usage is reported at 104.3 trillion connected records, including 81.5 trillion Zero Copy rows, while proposed benchmarking covers correctness, authorization, provenance, freshness, latency, cost, and memory continuity.


### ["Regex for Rows": Simplifying Pattern Detection in SQL with MATCH\_RECOGNIZE](https://yomu.fyi/post/regex-for-rows-simplifying-pattern-detection-in-sql-with-match-recogni.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Kent Marten, Sergei Fedorov
- Published: Sep 16, 2026
- Type: Explainer

SQL's unordered-set model makes it difficult to detect ordered event sequences such as consecutive login failures followed by a success, especially when timing matters. MATCH\_RECOGNIZE, now available in Databricks compute including Lakehouse Real-Time, expresses row sequences through regex-like states while supporting time anchoring and row-relative checks. The post shows its use for credential-stuffing anomalies, V-shaped stock reversals, checkout abandonment, and equipment-failure signals: FIRST can anchor a failure window, the end-of-partition marker $ can represent inactivity, and PREV/NEXT can compare sensor readings. By replacing chains of common table expressions, gaps-and-islands scaffolding, self-joins, and window-function logic, the clause is presented as easier to validate, maintain, and update for event-sequence analytics.


### [Translating CUDA Tile Operations from Python to Rust Using Agentic AI](https://yomu.fyi/post/translating-cuda-tile-operations-from-python-to-rust-using-agentic-ai.md)
- Company: [NVIDIA](https://yomu.fyi/company/nvidia-developer-blog.md)
- Author: Tanya Lenz
- Published: Sep 16, 2026
- Type: Tutorial

cuTile Rust (cutile-rs) extends Rust’s ownership model to tile-based GPU kernels, and this post describes an agentic workflow for translating cuTile Python and Triton-TileIR implementations. Because all three front ends target CUDA Tile IR and share the tileiras compiler, the workflow compares reference and translated IR while making Python’s implicit specializations explicit through Rust const generics, fixed dtype symbols, and FFI checks. A bounded multi-agent pipeline covers analysis, device kernels, host and FFI code, correctness, and benchmarking, with machine-checkable verdicts controlling progress. It ported all 24 public TileGym operators, roughly 40 kernels, and reported 99.5% average cuTile Python performance across 347 paired configurations on NVIDIA DGX B200. The skill ships with TileGym and uses acceptance checks requiring correctness, backend execution, and a geomean speedup of at least 0.95.


### [Logpoints Walkthrough](https://yomu.fyi/post/logpoints-walkthrough.md)
- Company: [Jetbrains](https://yomu.fyi/company/jetbrains.md)
- Author: Igor Kulakov
- Published: Sep 16, 2026
- Type: Tutorial

Logpoints in IntelliJ IDEA provide a way to inspect a running Java process without suspending it, making them useful when println logging or regular breakpoints would be disruptive. The walkthrough uses a Dockerized gRPC client and server whose incorrect tenant discount is traced by attaching to the server and adding expressions at runtime, without rebuilding or redeploying. Progressive logging shows the tenant value as JetBrains while the expected value is jetbrains, and the correct-discount block is never entered; the supplied fix uses equalsIgnoreCase and returns 2,000 basis points. The article also demonstrates testing changes through logpoint side effects, extending gRPC deadlines selectively, logging in dependencies, and using the ij-debugger AI agent skill. IntelliJ IDEA 2026.2 adds faster placement and instrumentation that removes debugger-introduced overhead, although heavy expressions still execute in the VM.


### [Rider and ReSharper 2026.2.2 Are Out!](https://yomu.fyi/post/rider-and-resharper-2026-2-2-are-out.md)
- Company: [Jetbrains](https://yomu.fyi/company/jetbrains.md)
- Author: Alexander Kurakin
- Published: Sep 16, 2026
- Type: Announcement

Version 2026.2.2 of ReSharper, Rider, and .NET tools is available through the products, Toolbox App, or website. Rider adds an AI Agent Setup widget to the bottom-right status bar, where users can review supported MCP tools, skills, and hooks, see which are enabled, and open the relevant settings. Its hooks now give agents narrower inspection results for newly added code, while the Reformat file hook reports IDE formatting changes as a diff; dotCover also adds TUnit coverage, requiring JetBrains.dotCover.Framework and Microsoft.Testing.Platform 2.3.0 or later. The release fixes a macOS backend-resume freeze, removes dependence on Unity editor executable names for attachment, and enables MCP file operations across attached solution folders; ReSharper also receives TUnit coverage support.


### [Why your Kafka topic ignores retention.ms (and how to fix it)](https://yomu.fyi/post/why-your-kafka-topic-ignores-retention-ms-and-how-to-fix-it.md)
- Company: [Red Hat](https://yomu.fyi/company/red-hat.md)
- Author: Rogerio Santos
- Published: Sep 16, 2026
- Type: Tutorial

A Kafka topic configured with retention.ms=43200000 (12 hours) retained messages for four days because the active log segment never rolled. Kafka retains data by deleting whole closed segments, not individual records, and an active segment remains writable and cannot be deleted. Segment rolling occurs when segment.bytes or segment.ms is reached; in this case, traffic was too modest to fill the 1-GiB segment and only four days had passed, short of the seven-day default. Once a segment closes, retention.ms is evaluated against its newest record, followed by the retention check interval and file.delete.delay.ms before physical deletion. The proposed fix is to set segment.ms to a fraction of the retention window (one hour for the 12-hour example), while tuning segment.bytes as needed; a smaller rolling cadence makes effective retention more predictable.


### [Constraining AI agents with Red Hat AI: Containment, identity, and governance](https://yomu.fyi/post/constraining-ai-agents-with-red-hat-ai-containment-identity-and-govern.md)
- Company: [Red Hat](https://yomu.fyi/company/red-hat.md)
- Author: Grace Ableidinger
- Published: Sep 16, 2026
- Type: Tutorial

AI agents running on laptops or clusters may inherit broad filesystem, network, and credential access, making faulty permissions or prompt injection potential security risks. The guide uses Red Hat OpenShift to build layered controls around an OpenClaw agent: namespace isolation, default-deny network policy, ResourceQuota, and optional Kata Containers contain workloads and limit escape or resource abuse. SPIFFE and SPIRE issue rotating SVIDs based on workload attributes such as namespace and ServiceAccount, allowing services to verify an agent without shared secrets. Governance adds OPA Gatekeeper admission policies, an MCP Gateway with risk-tiered tool authorization, NeMo Guardrails for prompt and completion filtering, and MLflow traces for auditability. The recommended rollout starts with namespace isolation and quotas, then adds sandboxing, identity, and the more involved governance controls.


[Newer posts](https://yomu.fyi/posts/page/42.md) · [Older posts](https://yomu.fyi/posts/page/44.md)