---
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

### [Using Uber: your guide to Pace's RAP Program](https://yomu.fyi/post/using-uber-your-guide-to-pace-s-rap-program.md)
- Company: [Uber](https://yomu.fyi/company/uber.md)
- Published: Jul 31, 2026
- Type: Tutorial

Pace’s Ride Access Program (RAP) is a supplementary service for ADA paratransit riders in its six-county region, using transportation network companies such as Uber to expand transportation options through ride vouchers. RAP riders can use subsidies for up to eight Uber trips daily, pay a $3.25 co-pay, and receive up to $26.75 per trip, while covering costs above the $30 total limit; trips must start and end within the Pace ADA service area. The guide explains enrollment-related account setup, including matching the Uber account’s contact details to the RAP profile, verifying identity, and recognizing the in-app voucher through a strikethrough market price and subsidized initial charge. It also documents a no-smartphone booking option at 833-USE-UBER, support channels, optional tipping, service-animal access, lost-item recovery, and in-app safety tools.


### [Using Uber: your guide to NJ TRANSIT’s Access Link Riders’ Choice Pilot 2.0](https://yomu.fyi/post/using-uber-your-guide-to-nj-transit-s-access-link-riders-choice-pilot.md)
- Company: [Uber](https://yomu.fyi/company/uber.md)
- Published: Jul 31, 2026
- Type: Tutorial

NJ TRANSIT’s Access Link Riders’ Choice (ALRC) Pilot 2.0 gives eligible Access Link customers another option for eligible trips through participating transportation network companies, including Uber. Access Link subsidizes up to 10 Uber trips per month at up to $20 per trip, provided each ride begins and ends within an eligible service area and occurs between 6 a.m. and 9 p.m., seven days a week. After enrollment, riders match their Uber account information to their ALRC profile, accept the voucher from Uber, verify it in the Uber Wallet, and confirm its application before requesting a ride. The guide explains app and phone booking, voucher opt-out, payment, safety checks, support, tipping, service animals, lost items, and incident reporting.


### [Introducing Supabase Evals](https://yomu.fyi/post/introducing-supabase-evals.md)
- Company: [Supabase](https://yomu.fyi/company/supabase.md)
- Author: matt\_rossman
- Published: Jul 31, 2026
- Type: Announcement

Supabase has open sourced supabase/evals, a benchmark and framework for testing how AI agents build using Supabase. It runs coding agents including Claude Code, Codex, and OpenCode against real tasks such as schema creation, Edge Function debugging, and RLS policy repair, scoring behavior with deterministic checks and LLM-as-a-judge. The framework executes scenarios in hosted-like and local containerized environments through the actual MCP server and CLI, with separate breadth-focused benchmark and depth-focused regression suites, plus a retry after failure. Initial findings show many agents pass broad tasks without skills, while skills improve some scores and documentation use; agents still often choose hand-written migrations, miss newer libraries, and use documentation inconsistently across harnesses.


### [Autoscaling endpoints for LLM inference](https://yomu.fyi/post/autoscaling-endpoints-for-llm-inference.md)
- Company: [Together AI](https://yomu.fyi/company/together-ai.md)
- Published: Jul 31, 2026
- Type: Explainer

Dedicated LLM inference deployments face a trade-off between paying for idle GPUs and suffering sharp p95 latency when replicas hit batching limits. The autoscaling loop converts observed load into desired replicas with ceil(N × observed/target), then applies scale-up and scale-down windows, replica bounds, and GPU placement. It presents inflight\_requests as a leading, engine-agnostic default, while TTFT and end-to-end latency target responsiveness but trail demand, and GPU or token utilization prioritize efficiency with less latency headroom. Cold starts can take several minutes because replicas require GPU placement, weight downloads, VRAM loading, and warm-up, so policies should scale early; streaming is required for TTFT, decoding speed, and throughput-per-replica metrics, whereas end-to-end latency supports both streaming and non-streaming workloads.


### [Enable on-demand expertise with Agent Skills in Genkit Go](https://yomu.fyi/post/enable-on-demand-expertise-with-agent-skills-in-genkit-go.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Daniela Petruzalek
- Published: Jul 31, 2026
- Type: Tutorial

Agent Skills in Genkit Go address the prompt-context problem caused by loading every procedure, guide, and document into an agent’s persistent context. The tutorial defines skills as discoverable knowledge packs organized around a SKILL.md file, whose frontmatter is exposed first and whose instructions, references, assets, and scripts are loaded through progressive disclosure when needed. It integrates the Skills middleware with Genkit’s wrapper architecture, scans SkillPaths for metadata, matches descriptions, and invokes the use\_skill tool before injecting the selected skill into active context; Go examples use ai.WithUse during Generate or GenerateText. Recipe and image-restoration examples show skills activating for matching requests, while the post notes that the restoration skill may require several attempts because model behavior is non-deterministic.


### [Agent and Model Evaluations in Gemini Enterprise Agent Platform are now GA](https://yomu.fyi/post/agent-and-model-evaluations-in-gemini-enterprise-agent-platform-are-no.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Alex Martin, Dima Melnyk
- Published: Jul 31, 2026
- Type: Announcement

Agent and model evaluations in Agent Platform are now generally available, providing one engine and consistent metrics for measuring agents and models during development and against live production traffic. The service offers more than 20 pre-built metrics across quality, safety, grounding, tool use, trajectories, and reference-based tasks, plus adaptive rubrics that generate case-specific criteria and a versioned, org-wide registry for custom code-based or LLM-as-a-judge metrics. Experiments can run locally or server-side, with Cloud Storage artifacts supporting auditability and reproducibility, while case generation, user simulation, and environment simulation expand coverage and model slow or failing backends. Online monitors grade sampled production traces, chart scores over time, and issue drift alerts through configured channels. Access is available through the SDK, REST API, agents-cli, console, and ADK; model-based metrics incur standard model-call charges, while code-based and computation metrics add no additional cost.


### [Run High-Performance Core Math at Scale with NVIDIA nvmath-python](https://yomu.fyi/post/run-high-performance-core-math-at-scale-with-nvidia-nvmath-python.md)
- Company: [NVIDIA](https://yomu.fyi/company/nvidia-developer-blog.md)
- Author: Michelle Horton
- Published: Jul 30, 2026
- Type: Announcement

NVIDIA released nvmath-python v1.0 to give Python users direct access to CUDA-X math libraries without requiring low-level C or C++ interfaces. The library acts as an abstraction layer over GPU engines like cuFFT and cuBLASLt, CPU backends like NVPL and Intel MKL, and distributed libraries such as cuBLASMp. It interfaces directly with NumPy, CuPy, and PyTorch tensors, structuring routines into generic interfaces for broad interoperability and specialized advanced modules for hardware-specific optimizations. Users can define custom sparse formats with Universal Sparse Tensors or invoke compiled device APIs directly inside custom numba-cuda kernels. Built-in logging captures execution space decisions and flags potentially expensive memory transfers across host and device environments.


### [Four Ways to Deploy More Secure AI Agents](https://yomu.fyi/post/four-ways-to-deploy-more-secure-ai-agents.md)
- Company: [NVIDIA](https://yomu.fyi/company/nvidia-developer-blog.md)
- Author: Michelle Horton
- Published: Jul 30, 2026
- Type: Problem & solution

Connecting large language models to live tools and enterprise systems introduces severe security vulnerabilities across multiple deployment harnesses. Over six months of evaluations, the NVIDIA AI Red Team identified recurring failures in AI agents, including missing access controls, arbitrary code execution via shell or file-write tools, unrestricted network egress, and exposed plaintext credentials. Mitigations operating in the same control plane as the model, such as system prompts or LLM-as-a-judge review agents, consistently fail against adversarial manipulation. Securing agentic deployments instead requires deterministic, architectural controls enforced outside the model control plane. Effective defenses include authenticating users, isolating command execution inside hardened sandboxes, blocking network egress by default, and delivering ephemeral secrets via external managers.


### [GenRec: Towards LLM-Native Recommendation at Netflix](https://yomu.fyi/post/genrec-towards-llm-native-recommendation-at-netflix.md)
- Company: [Netflix](https://yomu.fyi/company/netflix.md)
- Author: Netflix Technology Blog
- Published: Jul 30, 2026
- Type: Problem & solution

Netflix developed GenRec, an LLM-backed recommendation ranker built by adapting an internal foundation model for large-scale personalization. Traditional recommendation stacks rely on thousands of hand-crafted features and specialized architectures that are costly to maintain across diverse content types. To replace manual feature pipelines, GenRec verbalizes user histories, metadata, and contexts into natural-language prompts and trains with multi-objective losses, including catalog-aware ranking and reward-weighted alignment. At inference time, the model executes in prefill-only mode on vLLM without decoding text. In large-scale online A/B testing against a mature production ranker, GenRec achieved statistically significant improvements in short-term and long-term metrics while using fewer labeled examples.


### [How Salesforce Built an Agentic Engineering Enablement Strategy for Thousands of Software Engineers](https://yomu.fyi/post/how-salesforce-built-an-agentic-engineering-enablement-strategy-for-th.md)
- Company: [Salesforce](https://yomu.fyi/company/salesforce.md)
- Author: Scott Nyberg
- Published: Jul 30, 2026
- Type: Problem & solution

Salesforce addressed the challenge of scaling agentic engineering across thousands of software developers by focusing on organizational learning rather than tooling. While individual engineers initially developed disparate, uncoordinated workflows, the Technology, People, Innovation, and Learning (TPIL) team unified these approaches into the Proficiency Level (PL) Framework. The framework maps developer growth across four mindset-driven stages: AI-Assisted, AI-Validating, AI-Orchestrating, and AI-Native. To facilitate progress across these stages, TPIL introduced global AI camps, weekly working sessions, and manager coaching guides. Rather than tracking course completions or telemetry scores, Salesforce measured transformation through behavioral indicators, such as shifts toward validating agent output, designing multi-agent workflows, and asking higher-level questions regarding human judgment.


### [The Future of Agentic AI Depends on Openness and Trust. That’s Why Docker Is Joining Nvidia’s Open Secure AI Alliance.](https://yomu.fyi/post/the-future-of-agentic-ai-depends-on-openness-and-trust-that-s-why-dock.md)
- Company: [Docker](https://yomu.fyi/company/docker.md)
- Author: Jin Kim
- Published: Jul 30, 2026
- Type: Announcement

Modern discussions surrounding agentic AI increasingly center on whether autonomous systems can be trusted and securely placed at the core of enterprise workflows. While intelligence is generated by underlying models, operational trust depends on the surrounding execution runtime, identity frameworks, governance models, and security boundaries. To address these challenges across an open ecosystem, Docker has joined NVIDIA's Open Secure AI Alliance. This initiative aims to ensure developers can seamlessly route tasks between open-weight and frontier models without rewriting their application architectures or sacrificing control. By extending security and governance into the agent execution environment, the alliance seeks to deliver predictable control as AI agents become fundamental components of software stacks.


### [Foundations for an AI-forward healthcare organization](https://yomu.fyi/post/foundations-for-an-ai-forward-healthcare-organization.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Ramiz Bozai, Sailesh Kadam, Kriti Sen Sharma, Andrew Wallace-Jackson, Grace Crisp
- Published: Jul 30, 2026
- Type: Explainer

Healthcare organizations adopting AI face fragmented data, mismatched governance, and no repeatable operating model, rather than a shortage of ideas or vendors. The piece defines an AI-forward organization as one where AI can be built, trusted, and scaled through a foundation of unified data, visible guardrails, and an operating model that helps teams prioritize and move pilots into production. It describes patient identifiers differing across source systems, requiring manual reconciliation and creating recurring integration costs. Governance must avoid both untrusted outputs and approval processes so rigid that nothing leaves the sandbox, while self-service users need controlled access to clinical, operational, and financial data. The source says modern tooling can centralize permissions and enable a governed first-use case in days rather than quarters when scope and data are ready.


### [Agentic media buying cannot scale without the right foundation. See how buyers and sellers get there on Databricks.](https://yomu.fyi/post/agentic-media-buying-cannot-scale-without-the-right-foundation-see-how.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Joe Hu, Mandy Baker, Luke Barnes
- Published: Jul 30, 2026
- Type: Explainer

Media buying remains slowed by fragmented coordination across emails, spreadsheets, PDFs, and phone calls, leaving teams to research inventory, compare pricing, negotiate, and issue orders manually. The post presents an agentic workflow in which buyer and seller agents discover inventory, negotiate prices, and book deals through IAB Tech Lab’s AAMP standards, including AdCOM, OpenDirect, OpenRTB deals, and registry-based discovery and trust. Its Databricks implementation runs self-contained applications on Databricks Apps, with CrewAI agent crews using Databricks Foundation Model APIs and Claude models, Lakebase providing transactional Postgres state, and MLflow tracing capturing decisions and tool calls. The example processes a $200,000 Q3 Brand Launch across CTV and Linear TV with a $38 CPM ceiling, and is packaged as a Databricks Automation Bundle accelerator deployable with a single command.


### [How controllers from industrial machinery can coordinate multitask machine learning](https://yomu.fyi/post/how-controllers-from-industrial-machinery-can-coordinate-multitask-mac.md)
- Company: amazon.science
- Author: Theodore Vasiloudis
- Published: Jul 30, 2026
- Type: Problem & solution

Multitask machine learning often suffers from gradient conflicts, drift, and drought when blending multiple objective gradients in single update steps. To address this in graph self-supervised learning, researchers developed ControlG, a framework that allocates discrete computational blocks to individual objectives over time. ControlG operates across three coupled loops: sensing objective difficulty via spectral demand and gradient interference, planning target compute allocations using log-hypervolume Pareto sensitivities, and executing the schedule via a proportional-integral-derivative controller. Evaluated across homophilic and heterophilic graph benchmarks, the approach outperforms traditional multitask gradient-manipulation baselines while incurring low computational overhead. The framework also produces interpretable training timelines and deficit traces.


### [NVIDIA Exemplar Cloud: Lessons for Unlocking Full Performance on AI Infrastructure](https://yomu.fyi/post/nvidia-exemplar-cloud-lessons-for-unlocking-full-performance-on-ai-inf.md)
- Company: [NVIDIA](https://yomu.fyi/company/nvidia-developer-blog.md)
- Author: Elizabeth Goodman
- Published: Jul 30, 2026
- Type: Problem & solution

Identical AI computing clusters can exhibit 8% to 12% training throughput deficits compared to NVIDIA reference architectures due to compounded configuration choices across kernels, hypervisors, BIOS, and NCCL settings. Profiling with Linux perf, turbostat, and NCCL tests uncovers performance degradation across multiple layers of the compute stack. In virtualized Grace deployments, enabling Arm SMMU Virtual Command Queue support eliminates invalidation serialization bottlenecks on memory-heavy workloads. On x86 systems, adjusting BIOS C-states to allow idle cores into C6 frees thermal headroom for active cores to achieve rated turbo frequencies, while cpuset isolation resolves NUMA contention. Further gains stem from tuning NCCL queue pairs per connection and properly bind-mounting topology files inside workload containers.


### [Scaling Exact COUNT(DISTINCT) for High-Cardinality Non-Rollup Metrics in Distributed Data Pipelines](https://yomu.fyi/post/scaling-exact-count-distinct-for-high-cardinality-non-rollup-metrics-i.md)
- Company: [Uber](https://yomu.fyi/company/uber.md)
- Published: Jul 30, 2026
- Type: Problem & solution

Uber needed exact COUNT(DISTINCT) for high-cardinality non-rollup metrics such as monthly active users and quarterly retention, where daily or monthly counts cannot be combined and quarterly processing involved 3.6 billion UUID-valued identifiers. RoaringBitmap was exact but failed when a merged bitmap exceeded the JVM’s roughly 2 GB array limit, while HyperLogLog’s 1–5% error was unacceptable for financial reporting. The implemented chunked aggregation buffer hashes each UUID with xxHash64, routes it by the top 16 bits into one of 65,536 Roaring64Bitmap chunks, serializes chunks independently, and returns the final cardinality as an 8-byte long. Across 75 metric families, the deployment reduced two-year backfill time by 65% on average, improved daily runtime by 23%, and recorded no post-deployment OutOfMemoryError failures while retaining exact distinct counts.


### [Your trusted knowledge layer: Introducing Stack Internal's new platform experience](https://yomu.fyi/post/your-trusted-knowledge-layer-introducing-stack-internal-s-new-platform.md)
- Company: [Stack Overflow](https://yomu.fyi/company/stack-overflow.md)
- Author: Phoebe Sajor, Caroline Thomas
- Published: Jul 30, 2026
- Type: Announcement

Organizations face growing challenges managing fragmented institutional data as AI agents and human workers operate across disparate tools. When agents consume stale or conflicting information, they produce confident errors that require costly human verification. Stack Internal has introduced an AI-native knowledge platform that ingests raw data across sources—including Google Docs, Slack, and Stack Internal communities—and evaluates it for trust, freshness, and authority. The updated platform adds a chat interface featuring response-level confidence labels and provenance cards, along with API and MCP server integrations that enforce identity-aware permission boundaries for AI agents. Engineering leaders can also track internal knowledge usage and high-traffic dependencies across versions via new Swagger API v3 endpoints.


### [GPU Management: Why Idle GPUs Are the New Grounded Aircraft](https://yomu.fyi/post/gpu-management-why-idle-gpus-are-the-new-grounded-aircraft.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Erick Lachmann, Gabriel Pimenta de Freitas Cardoso, Gustavo Lucchetti
- Published: Jul 30, 2026
- Type: Explainer

Enterprise AI is shifting from a primary focus on model capability to the utilization of scarce, expensive GPU capacity. Like aircraft, GPUs accrue financing, depreciation, power, and cooling costs by calendar hour, while producing value only during useful compute hours; unlike aircraft, they cannot freely absorb workloads with different memory, latency, and duration profiles. The article explains how peak-sized clusters, mixed workloads such as training, fine-tuning, quantization, real-time and batch inference, embeddings, and evaluation can leave capacity stranded even when dashboards show high occupancy, and argues that API pricing can motivate enterprises to own infrastructure. It presents specialized models and GPU orchestration as complementary levers: specialization reduces each workload’s footprint, while management reallocates freed capacity across workloads and queues. The conclusion is that installed capacity alone does not determine returns; enterprises need both strategies to close the gap between GPUs owned and useful output.


### [How we set up our cloud agent environment](https://yomu.fyi/post/how-we-set-up-our-cloud-agent-environment.md)
- Company: [Cursor](https://yomu.fyi/company/cursor.md)
- Author: Mathew Hogan & Arvind Saripalli
- Published: Jul 30, 2026
- Type: Explainer

Setting up a cloud-agent environment for the Cursor monorepo required treating development infrastructure as a product for agent users. The team aligned cloud VMs with local development by adapting utilities and setup scripts for Ubuntu, adding dependencies to a Cursor-defined Dockerfile, and introducing security controls for secrets and network access. To make the repository easier to operate, it built anydev to start services, route utility scripts, explain subcommands, and supervise long-running builds. Cursor Cloud MCP and Cloud Doctor then inspect environments, distinguish transient from salient failures, perform root-cause analysis, open high-confidence fixes, and improve workflows using traces. The resulting end-to-end testing and recorded demos helped cloud agents grow from about one in ten merged PRs in December to more than half, with the post identifying tool parity, documented skills, and core-workflow verification as readiness checks.


### [Convert proprietary code to open ANSI SQL with Genie Code](https://yomu.fyi/post/convert-proprietary-code-to-open-ansi-sql-with-genie-code.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Jonathan Brito
- Published: Jul 30, 2026
- Type: Announcement

Databricks introduces an agentic converter in Genie Code to translate proprietary warehouse dialects into open ANSI SQL, initially supporting T-SQL, Snowflake, Redshift, Oracle, BigQuery, and Teradata. Migration projects provide a workspace hub for source files, conversion status, complexity scoring, dependency lineage, and collaboration, helping teams prioritize work and identify scripts that can move independently. When launched, swarms of subagents convert files in parallel, iteratively fixing errors and validating syntax and semantic intent; in the proof-of-concept, six of eight files converted successfully. Two files required review because stored procedures needed three-part Unity Catalog names, which could be fixed manually or encoded as a custom Genie Code skill for reuse across the codebase. The post also notes that Databricks supports multi-statement transactions, temporary tables, and stored procedures, while planned additions include legacy ETL sources, new target dialects, data migration, and reconciliation.


[Newer posts](https://yomu.fyi/posts/page/84.md) · [Older posts](https://yomu.fyi/posts/page/86.md)