---
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

### [Session Replay for Unreal Engine: see the crash before the crash](https://yomu.fyi/post/session-replay-for-unreal-engine-see-the-crash-before-the-crash.md)
- Company: [Sentry](https://yomu.fyi/company/sentry.md)
- Author: Ivan Tustanivskyi
- Published: Jul 24, 2026
- Type: Announcement

Crash reports in non-deterministic game environments often lack player context, making callstack-only debugging difficult. Sentry's SDK version 1.16.0 for Unreal Engine introduces Session Replay to continuously record gameplay and attach the final video clip directly to crash reports. The cross-platform recording pipeline hooks into Slate's backbuffer presentation on the render thread, uses engine pixel shaders for format conversion, and feeds frames to hardware H.264 encoders via Unreal's AVCodecs plugins. Encoded fragments are organized in a rolling ring buffer and periodically written to temporary MP4 files that are uploaded alongside crash data. Benchmark results in a 4K demo game showed an overhead of approximately 0.20 ms per frame.


### [Agent platform (Part 1): How we help Grab build and run AI agents at scale](https://yomu.fyi/post/agent-platform-part-1-how-we-help-grab-build-and-run-ai-agents-at-scal.md)
- Company: [Grab](https://yomu.fyi/company/grab.md)
- Author: Kendrick Tan
- Published: Jul 24, 2026
- Type: Explainer

Grab’s AI support bot grew from an internal GPT-powered Level-0 service into the foundation for LLM-Kit, an internal framework now used by more than 500 services, alongside over 50 registered remote MCP servers and a company-wide LLM gateway handling billions of tokens monthly. The bot used a single-agent reasoning loop and a tool plane spanning Glean, Kibana, GitLab, Slack, and HTTP plugins, but scaling exposed missing evaluations, fragmented observability, provider-switching friction, and costly production plumbing. LLM-Kit addresses those problems with generated FastAPI services, LangGraph agent templates, OpenTelemetry tracing, configuration and secret-management integrations, evaluation routes, remote MCP tool discovery, and gRPC contracts, clients, health checks, and channel selection. The post concludes that framework concerns became platform concerns at 500 agents, leading to a gateway, remote MCP framework, and evals platform described as the series continues.


### [Kimi K3 vs Claude Fable 5 on DeepSWE: Cost and Coding](https://yomu.fyi/post/kimi-k3-vs-claude-fable-5-on-deepswe-cost-and-coding.md)
- Company: [Together AI](https://yomu.fyi/company/together-ai.md)
- Published: Jul 24, 2026
- Type: Benchmark

On DeepSWE, Kimi K3 trails Claude Fable 5 by 1.4 points at pass@1 (68.5% vs 69.9%) but leads at pass@2 (82.0 vs 80.2) and pass@4 (89.4% vs 88.5%) across 452 rollouts. Kimi K3 costs $4.65 per rollout versus $13.41 for Fable, delivering 2.8x more solved tasks per dollar. It covers 89.4% of the benchmark, solving 101 of 113 tasks, while Fable solves 100, though Fable is more reliable with 58 tasks solved four-for-four versus Kimi’s 45. The models share the highest cross-vendor similarity (0.72) and fail on the same tasks, with Kimi leading in Go and Fable leading in Python, JavaScript, TypeScript, and Rust. As an open-weight model, Kimi K3 offers a cost-effective alternative for retry-tolerant workloads.


### [Run Ray on TPU, Part 2: Ray AI libraries](https://yomu.fyi/post/run-ray-on-tpu-part-2-ray-ai-libraries.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Ivan Nardini, Spencer Peterson
- Published: Jul 24, 2026
- Type: Tutorial

Running Ray on TPUs requires multi-host workloads to remain on one intact TPU slice whose hosts share a high-speed ICI link. This guide presents Ray's AI libraries on top of GKE and Ray Core: Ray Serve for serving, Ray Data's iter\_jax\_batches() for input pipelines and batch inference, and Ray Train's JaxTrainer for distributed JAX training. Serve uses accelerator\_config.topology to defer slice placement to the replica, while iter\_jax\_batches() returns device-sharded JAX arrays and handles ragged final batches through drop, pad, or raise choices. JaxTrainer takes a training function and slice topology, launches one worker per host, and provides checkpointing, fault-tolerant restarts, and multi-slice scale-out; official TPU images and dashboard metrics round out the workflow.


### [Turn And Face The Strange](https://yomu.fyi/post/turn-and-face-the-strange.md)
- Company: [Fly.io](https://yomu.fyi/company/fly-io.md)
- Published: Jul 24, 2026
- Type: Announcement

Fly.io announces a strategic shift toward Sprites, its “computers for agents,” after concluding that AI-driven software development changes the needs its public-cloud platform should serve. The company says coding agents increasingly run in cloud-hosted workstations because laptops stop when closed, while conventional cloud resources impose too much commitment for semi-disposable agent workloads. Sprites are designed to be created rapidly in large numbers, retain 100GB durable disks, use metered utility billing that pauses during inactivity, and host Internet-accessible applications. The post says a new iteration adds scaling and orchestration work plus the Sprite Block Device, while Fly Machines and platform-as-a-service features will continue. Fly.io also announces new funding and Scott Johnston as CEO, with the founder moving to an advisor role.


### [How AI Rebuilt Salesforce’s Decades-Old Localization Pipeline](https://yomu.fyi/post/how-ai-rebuilt-salesforce-s-decades-old-localization-pipeline.md)
- Company: [Salesforce](https://yomu.fyi/company/salesforce.md)
- Author: Scott Nyberg
- Published: Jul 23, 2026
- Type: Problem & solution

Salesforce needed to deliver major releases across 34 languages as product localization volume surged by more than 35% under fixed budgets and unchanged delivery windows. To address these scaling constraints, the engineering team replaced their legacy translation workflows with an LLM-powered orchestration pipeline integrating prompt engineering, context engineering, and multi-stage validation. The architecture transforms existing style guides, glossaries, and terminology databases into structured context, routing interface strings through specialized prompt stages—up to 85 stages for some languages—to enforce product context, grammar, and branding rules. Combined with an automated validation loop spanning AI editing, AI validation, and human review, this system reduced localization costs by 50 to 90% while accelerating turnaround times across enterprise releases.


### [How the FDA Built an AI Platform That 85% of Its Staff Now Use Daily](https://yomu.fyi/post/how-the-fda-built-an-ai-platform-that-85-of-its-staff-now-use-daily.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Molly Just-Behr
- Published: Jul 23, 2026
- Type: Explainer

The FDA built ELSA, a generative AI platform for its 16,000 staff, on Halo, a governed Databricks data foundation created to address fragmented systems across eight centers. Those centers had separate chatbots and data stores; consolidating 50 to 60 sources enabled faster sharing, real-time streaming, and centralized access controls through Unity Catalog. Within roughly two months, ELSA adoption rose from less than 1% to 85%, while staff began building hundreds of agents weekly from standard operating procedures, regulatory guidance, and center-specific documents. MCP servers layered over Unity Catalog make governed data and tooling accessible beyond data scientists, and Databricks ML and NLP capabilities through MLflow extracted starting materials and product-supplier-manufacturer relationships from millions of submission pages. A reviewer can now request grounded starting-material information for a drug application in about three minutes instead of days, while the FDA adapts center-specific MCP tools and extends the model across its organization.


### [Permission isn't purpose: Intent-based authorization in Omnigent](https://yomu.fyi/post/permission-isn-t-purpose-intent-based-authorization-in-omnigent.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Nishith Sinha, Matei Zaharia
- Published: Jul 23, 2026
- Type: Explainer

Omnigent’s intent-based authorization addresses a gap in identity-based access control: an agent with valid credentials may follow indirect prompt injections embedded in data and perform authorized actions unrelated to the user’s task. It binds each session to a human-declared purpose and evaluates that intent before every tool call, producing permitted, consent-required, or denied verdicts. In a data-quality example, reading a customers table is allowed, dashboard publication requires approval, and an injected request to grant external access is denied despite the agent’s identity permitting that tool. The intent is fixed at design time for autonomous agents or approved by a human at session start for interactive agents, and cannot be broadened by the agent. Omnigent combines this policy with session-risk scoring and other contextual policies in a single engine where any denial wins.


### [Provisioning for the Agentic Era: How Databricks Built a Self-Serve Infrastructure Vending Machine](https://yomu.fyi/post/provisioning-for-the-agentic-era-how-databricks-built-a-self-serve-inf.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Evan Pandya, Greg Wood, Joel Thomas
- Published: Jul 23, 2026
- Type: Problem & solution

Databricks built the Field Engineering Vending Machine (FEVM) to replace shared environments with isolated, centrally governed infrastructure for its growing field organization. Users or agents describe a use case and configuration details, receiving an environment assembled through a React frontend, Python backend, Databricks Apps, Terraform, Git Runner, and Lakebase across AWS, Azure, and GCP. FEVM supports templates and add-ons such as Lakebase, notebooks, and pre-packaged assets from UC Volumes, applies configurable time-to-live policies, and sends Slack notifications for provisioning, expiration, and deletion. It also manages shared resources independently, including catalogs that persist across workspace lifecycles, and provides administrative controls for limits and audits. At the time described, it managed more than 2,600 active deployments across three clouds and over 5,000 active users, after handling nearly 1,200 requests during one internal event.


### [Debugging Ray Tracing Applications Using NVIDIA OptiX Toolkit](https://yomu.fyi/post/debugging-ray-tracing-applications-using-nvidia-optix-toolkit.md)
- Company: [NVIDIA](https://yomu.fyi/company/nvidia-developer-blog.md)
- Author: Tanya Lenz
- Published: Jul 23, 2026
- Type: Problem & solution

NVIDIA OptiX ray tracing applications often present difficult debugging challenges, including invalid API arguments, black frames, and concurrency issues across thousands of GPU threads. The open-source NVIDIA OptiX Toolkit addresses these diagnostic hurdles by offering unified error checking and targeted device-side debug logging. Host-side macros like OTK\_ERROR\_CHECK wrap OptiX, CUDA runtime, and CUDA driver API calls to enforce uniform error validation while capturing file and line diagnostics. For device-side troubleshooting, the toolkit introduces a DebugLocation utility to isolate logging to specific launch indices instead of flooding the output stream with concurrent thread data. This device mechanism also supports interactive one-shot debug dumps and screen highlights around the inspected pixel.


### [Start Customizing NVIDIA Nemotron 3 Nano with Prime Intellect Lab in Minutes](https://yomu.fyi/post/start-customizing-nvidia-nemotron-3-nano-with-prime-intellect-lab-in-m.md)
- Company: [NVIDIA](https://yomu.fyi/company/nvidia-developer-blog.md)
- Author: Chris Alexiuk
- Published: Jul 23, 2026
- Type: Tutorial

Adapting open models to specialized tasks often requires significant infrastructure, technical expertise, and GPU resources. This tutorial demonstrates how developers can customize NVIDIA Nemotron 3 Nano using Prime Intellect Lab for hosted reinforcement learning with verifiable rewards. The workflow establishes a baseline evaluation on a Python Math task, trains a LoRA adapter using a TOML configuration, and reevaluates performance. Across 32 held-out problems capped at five assistant turns, the model improves its accuracy from 21.9% to 90.6% for less than five dollars in compute spend. The same hosted training approach applies to larger models in the family, including Nemotron 3 Super and Nemotron 3 Ultra.


### [Why A Frontier Data Agent Outperforms General Coding Agents in Quality and Cost](https://yomu.fyi/post/why-a-frontier-data-agent-outperforms-general-coding-agents-in-quality.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: The Databricks AI Research Team
- Published: Jul 23, 2026
- Type: Benchmark

An evaluation compared Genie Code with three widely used coding agents from major AI labs on 401 real internal data tasks, using a shared 20-minute wall-clock budget and independent grading. Genie Code achieved 76.6% accuracy at an estimated $0.55 per task, outperforming rivals at 55.9–72.1% accuracy and $0.91–$1.16 per task. Its advantage is attributed to semantic search across catalog and workspace assets, persistent memory of tables and business logic, and enterprise-context understanding, which reduce exploratory tool use. On discovery-heavy tasks, general-purpose agents often wandered through large workspaces or timed out on inefficient scans, while Genie Code averaged 8.3 tool calls per task. The benchmark found no accuracy-cost trade-off, although the authors note that Genie Ontology was disabled and expect it to strengthen the advantage.


### [Connect Amazon S3 data to Databricks with Delegated IAM Permissions](https://yomu.fyi/post/connect-amazon-s3-data-to-databricks-with-delegated-iam-permissions.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Gordon Wang
- Published: Jul 23, 2026
- Type: Announcement

Databricks introduces a simpler flow for connecting Amazon S3 to Unity Catalog through an external location, addressing the manual work previously required to establish governed read and write access. Instead of writing 140-line IAM trust policies, configuring bucket permissions, deploying CloudFormation templates, and switching between consoles, users specify a bucket and access level, then verify permissions in AWS. AWS IAM temporary delegation lets Databricks provision a least-privilege IAM role, configure its cross-account trust policy, register the external location, and enable Auto Loader and File Events. The delegated authorization is time-bounded and expires after setup; provisioning actions are logged in AWS CloudTrail, and users without sufficient permissions can request access from an AWS administrator in the flow. The result is a single-session setup intended to reduce configuration errors while supporting governed S3 access for ingestion, pipelines, analytics, and LTAP workloads.


### [How we built the new Table of Contents feature](https://yomu.fyi/post/how-we-built-the-new-table-of-contents-feature.md)
- Company: [Medium](https://yomu.fyi/company/medium.md)
- Author: Scott Batson
- Published: Jul 23, 2026
- Type: Explainer

Medium built a new Table of Contents feature after an existing Chrome extension demonstrated demand, while its approach of inserting a static list into post content created revision, maintenance, navigation, and reading-experience problems. The shipped implementation derives a nested list from the rendered post body at runtime: H2 and H3 become top-level entries, H4 headings nest beneath the latest top-level heading, and lead title, subtitle, and kicker are excluded. It appears as a right-margin indicator that scrolls with the reader, highlights the current heading, supports smooth scrolling, and uses a sliding window for posts with many headings. Full-width images receive a translucent background, one-heading posts hide the feature, and mobile needs a separate solution because desktop indicators overlap content; the feature took a couple of days, mostly for UX testing and design iteration.


### [Introducing AI spend controls with Unity AI Gateway](https://yomu.fyi/post/introducing-ai-spend-controls-with-unity-ai-gateway.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Kevin Stumpf
- Published: Jul 23, 2026
- Type: Announcement

Unity AI Gateway now offers AI Spend Controls, extending existing cost visibility with proactive budget alerts across models and workloads. The feature supports budgets at user, use-case, workspace, and account levels, plus shared and per-user thresholds that can trigger email alerts or enforce hard caps by stopping requests after a limit is exceeded. Configuration starts in account settings under Usage and Budgets, where administrators select Unity AI Gateway, optionally scope workspaces and resource tags, and define monthly limits and recipients. Budget status and trends are available in the Cost section, while customizable Cost Analytics dashboards use Unity Catalog system tables to attribute DBU and model-provider costs by identity, workspace, endpoint, tags, model, provider, and request tags. The release positions Databricks budgets, Unity AI Gateway, and Unity Catalog as a combined governance layer for controlling AI access, usage, and spend.


### [From 57 bugs to 1, thanks to Seer](https://yomu.fyi/post/from-57-bugs-to-1-thanks-to-seer.md)
- Company: [Sentry](https://yomu.fyi/company/sentry.md)
- Author: Dan Mindru
- Published: Jul 23, 2026
- Type: Problem & solution

Software teams frequently defer low-priority bugs to the backlog because manual triage, investigation, and code fixes consume valuable engineering time. To resolve 56 out of 57 backlog bugs, Dan Mindru utilized Sentry telemetry combined with Seer and the hosted Sentry Model Context Protocol server. Sentry captures context including traces, logs, and session replays, allowing Seer to assess fixability scores and generate pull requests with unit tests for isolated issues. For more intricate problems, developers query production breadcrumbs and telemetry directly in their agentic editors while supplying missing historical business logic. Consequently, automated tool calling and agent workflows drastically lowered the economic cost of addressing routine production bugs.


### [Observability for every Supabase project with Grafana Cloud](https://yomu.fyi/post/observability-for-every-supabase-project-with-grafana-cloud.md)
- Company: [Supabase](https://yomu.fyi/company/supabase.md)
- Author: alex\_hall, matt\_linkous, raminder\_singh
- Published: Jul 23, 2026
- Type: Announcement

Supabase now offers a one-click Grafana Cloud integration from its Dashboard, with the setup available on every plan, including the free plan. The setup provisions authentication, metric scraping, and a pre-built observability dashboard that tracks more than 200 metrics through Supabase’s Metrics API. Those metrics cover CPU and memory pressure, disk I/O, network traffic, connections and pooler behavior, replication lag, checkpoints, database size, and query statistics, while the same open-source dashboard definitions support self-hosted Grafana, the existing Grafana Cloud integration, and the new setup. The release is focused on metrics and is designed to accommodate logs without architectural changes; support for log drains to Grafana Cloud is already in progress. Users can start with Grafana Cloud’s free tier without a credit card on either side.


### [Introducing Claude Opus 4.7](https://yomu.fyi/post/introducing-claude-opus-4-7.md)
- Company: [Anthropic](https://yomu.fyi/company/anthropic.md)
- Published: Jul 23, 2026
- Type: Announcement

Claude Opus 4.7 is generally available as an upgrade to Opus 4.6, with stated gains in advanced software engineering, difficult long-running tasks, instruction following, self-verification, and higher-resolution vision. The announcement reports benchmark and tester results including a 13% resolution increase on a 93-task coding benchmark, a 0.715 tie for top score across six research-agent modules, and 90.9% on BigLaw Bench at high effort. It also describes safeguards that detect and block prohibited or high-risk cybersecurity requests, while legitimate security professionals can apply to the Cyber Verification Program. The model is offered across Claude products, its API, Amazon Bedrock, Vertex AI, and Microsoft Foundry at $5 per million input tokens and $25 per million output tokens. New controls include xhigh effort, task budgets, Claude Code’s /ultrareview, and auto mode, while migration may increase token counts because of tokenizer and reasoning changes.


### [Introducing Claude Opus 4.5](https://yomu.fyi/post/introducing-claude-opus-4-5.md)
- Company: [Anthropic](https://yomu.fyi/company/anthropic.md)
- Published: Jul 23, 2026
- Type: Announcement

Claude Opus 4.5 is available today across Claude apps, the API, and all three major cloud platforms, with the model identifier claude-opus-4-5-20251101 and pricing of $5/$25 per million tokens. The announcement positions it as a state-of-the-art model for coding, agents, computer use, deep research, spreadsheets, and slides, while reporting stronger vision, reasoning, and mathematics than predecessors. On the Claude API, an effort parameter lets developers trade off speed and spend against capability; at medium effort, Opus 4.5 matched Sonnet 4.5’s best SWE-bench Verified score using 76% fewer output tokens, while highest effort exceeded it by 4.3 percentage points using 48% fewer tokens. Additional platform changes include context compaction, advanced tool use, memory, and improved multi-agent coordination. Product updates add Claude Code’s editable Plan Mode and desktop sessions, automatic conversation summarization, and expanded Claude for Chrome and Excel access.


### [The production platform for open-weight AI inference](https://yomu.fyi/post/the-production-platform-for-open-weight-ai-inference.md)
- Company: [Together AI](https://yomu.fyi/company/together-ai.md)
- Published: Jul 23, 2026
- Type: Announcement

The update presents a production inference platform for open-weight, licensed closed-weight, and fine-tuned models, aimed at giving teams control over performance, cost, quality, and functionality without building an inference stack from scratch. It supports uploading weights or adapters from Hugging Face, S3, or local machines, uses tested deployment profiles for hardware, quantization, tensor parallelism, speculative decoding, and serving engine choices, and lets operators tune placement and autoscaling signals. Endpoints can keep a stable interface while multiple deployments receive traffic through canary, blue-green, rolling, A/B, or shadow testing, with threshold-based automatic rollback. The rebuilt caching and distribution layer proactively warms shared weights; internal testing reports roughly 4× faster warm starts across several frontier models, while a closed beta adds full-weight and LoRA reinforcement learning and supervised fine-tuning with deployable checkpoints.


[Newer posts](https://yomu.fyi/posts/page/88.md) · [Older posts](https://yomu.fyi/posts/page/90.md)