---
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

### [MongoDB for the Agentic Era: Built for Developers and AI Agents](https://yomu.fyi/post/mongodb-for-the-agentic-era-built-for-developers-and-ai-agents.md)
- Company: [MongoDB](https://yomu.fyi/company/mongodb.md)
- Published: Aug 13, 2026
- Type: Announcement

MongoDB has launched the Atlas Managed MCP Server, a fully hosted service that lets AI coding tools connect to Atlas data without manual infrastructure setup. The server uses OAuth 2.1 to replace shared service accounts with individual user delegation, so agents act with the developer’s own permissions and every action is auditable. Developers can connect via one-click OAuth consent in tools like Claude Code, Codex, Cursor, Grok Build, and Devin AI, with no connection strings or credentials to manage. Admins can enforce read-only mode, configure token lifetimes, and revoke access from the Atlas UI or Admin API. The announcement also includes Atlas App Connections, native connectors for frontier AI tools, and an integration with Vercel v0, aiming to close the gap between prototype and production.


### [Closing the Gap Between Agentic Promise and Impact with Industry Leading Retrieval](https://yomu.fyi/post/closing-the-gap-between-agentic-promise-and-impact-with-industry-leadi.md)
- Company: [MongoDB](https://yomu.fyi/company/mongodb.md)
- Published: Aug 13, 2026
- Type: Announcement

McKinsey projects AI agents will generate $2.9 trillion annually; a WRITER survey finds 97% of executives have deployed agents, yet only 29% see significant ROI due to data accuracy issues. MongoDB announced capabilities embedding benchmark-leading retrieval directly into its operational database, closing the gap between agentic promise and impact. Automated Embedding in MongoDB Atlas powered by Voyage AI, now GA, uses the top-ranked Voyage 4 model family for accurate retrieval without separate pipelines, as demonstrated by MedINT. The Atlas Embedding and Reranking API and voyage-code-4 model, designed for agentic coding retrieval, extend accurate retrieval to any stack and coding agent workloads at low cost. $vectorSearch in Atlas Stream Processing enables agents to retrieve accurate data in motion, and a joint MongoDB-Temporal reference architecture provides a forkable starting point for durable execution on live data.


### [Cloud Agents Start 3x Faster with Builds](https://yomu.fyi/post/cloud-agents-start-3x-faster-with-builds-26.md)
- Company: [Cursor](https://yomu.fyi/company/cursor.md)
- Published: Aug 13, 2026
- Type: Announcement

Cursor’s Cloud Agents now use Builds, ready-to-use copies of a development environment prepared in the background. These environments include cloned repositories, installed dependencies, and completed install commands, allowing agents to start without repeating setup each session. Cursor refreshes environments regularly, keeps warm copies, and activates only successful builds; internally, environments boot 10x faster and time to first token is 3x faster. If a commit or dependency update breaks a build, the last successful build remains active, while users receive a notification and can debug in the background. Builds can be inspected in the Cloud Agents dashboard, where logs, commit SHAs, statuses, and agent run associations are available, with tools for agents to inspect or manage them.


### [HeyGen x Google Cloud: Bringing Avatar IV to TPUs](https://yomu.fyi/post/heygen-x-google-cloud-bringing-avatar-iv-to-tpus.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Published: Aug 13, 2026
- Type: Benchmark

HeyGen and Google Cloud ported Avatar IV, an 18B-plus-parameter diffusion stack for streamed talking-head video, to an eight-chip Trillium (v6e) host. The pipeline uses two diffusion transformers and a VAE decoder, with FSDP weight sharding and Ulysses sequence parallelism across the mesh, and runs through torchax, JAX, XLA, and shape-specific Pallas kernels. Optimization targeted exposed all-to-all collectives, frame-misaligned sparse-attention blocks, serial softmax work, layout copies, scheduler choices, and custom-kernel cost estimates; changes were measured per video chunk against output-quality gates. The resulting pipeline was 1.86× faster than the first working TPU version, comparable in performance to the 8×H100 production setup and up to 25% more cost efficient per generated-video minute, while shipped changes preserved byte-identical output or passed defined similarity review.


### [Introducing Credentio: Open Source C++ Library for C2PA Content Credentials from Google](https://yomu.fyi/post/introducing-credentio-open-source-c-library-for-c2pa-content-credentia.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Sherif Hanna
- Published: Aug 13, 2026
- Type: Announcement

Google introduces Credentio, an open-source C++ library for local validation of C2PA Content Credentials, initially supporting specification versions 2.2 and 2.4. The library is the code used by nearly 40 conformant C2PA-enabled Google products to process tens of billions of generated images, videos, audio files, and documents across many formats. Its API keeps validation inside the developer’s application, avoiding media transmission while providing immediate verdicts, privacy, and zero bandwidth overhead; it is also designed to maintain a small memory footprint for assets ranging from images to multi-gigabyte videos. Credentio parses manifests, assertions, digital signatures, and claims, accepts official or custom trust lists, and reports verification statuses and integrity errors, while planned work includes generating and embedding Content Credentials.


### [What We Learned by Reproducing 2,200 papers from ICML](https://yomu.fyi/post/what-we-learned-by-reproducing-2-200-papers-from-icml.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Abubakar Abid
- Published: Aug 13, 2026
- Type: Benchmark

An ICML 2026 reproduction hackathon examined whether coding agents could audit research at conference scale, amid 23,918 submissions and 6,352 accepted papers. From July 15 to August 2, 1,221 participants published 6,816 Trackio logbooks covering 2,226 papers and 35,908 claims; an open-weights GLM-5.2 judge assigned per-claim verdicts, while participants used cloud jobs and toy reproductions when full experiments were impossible. At least one claim was independently verified in 51% of examined papers, including 266 fully reproduced papers, while 23% had a falsified or contested claim and 242 papers produced opposing verdicts across teams. Adversarial re-checks confirmed issues including a paging-theorem error, a reverse-versus-forward-KL mismatch, and padded evaluation tokens, but also caught false falsifications, leading to the conclusion that agents expand auditing capacity while humans remain necessary to steer experiments and assess cases such as image quality.


### [Databricks Network Configuration delivery to Tens of Millions of Serverless VMs](https://yomu.fyi/post/databricks-network-configuration-delivery-to-tens-of-millions-of-serve.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Manish Bansal, Yankai Zhang, Chen He
- Published: Aug 12, 2026
- Type: Problem & solution

Databricks’ serverless platform launches tens of millions of VMs daily, and each VM needs network configuration before serving customer workloads. The original design synchronously aggregated data from multiple upstream services on the cluster-creation critical path, producing 5,000-ms p99 RPC latency and availability bottlenecks as request volume reached billions per day. The replacement uses change events through a message queue, asynchronous per-workspace recomputation, partition-local snapshots, and periodic reconciliation to recover from missed events. The serving path now performs a single snapshot-store read without upstream calls, while events carry workspace and resource identifiers rather than customer data. After rollout, p99 RPC latency fell to 125 ms, server success rate rose to 99.99%, upstream call volume dropped 86%, and the legacy synchronous framework was deprecated.


### [How Agentforce-Powered AI Security Workflows Accelerate Incident Response](https://yomu.fyi/post/how-agentforce-powered-ai-security-workflows-accelerate-incident-respo.md)
- Company: [Salesforce](https://yomu.fyi/company/salesforce.md)
- Author: Scott Nyberg
- Published: Aug 12, 2026
- Type: Explainer

Salesforce engineers expanded Security Center from a basic conversational interface into an Agentforce-powered stateful investigations platform for incident response. Managing enterprise security incidents required handling long-running lifecycles, disparate telemetry formats, and finite LLM context windows that risk reasoning pocket collapse. To prevent overflowing context limits, the architecture partitions telemetry into contextual segments and uses AI-driven summarization pipelines before feeding data to the agent. Because non-deterministic LLM outputs break traditional deterministic testing, the team implemented AI-driven evaluation pipelines using simulated customer interactions to evaluate response behavior rather than exact wording. Ongoing work focuses on grounding public foundation models with curated, Salesforce-owned security knowledge to improve platform-specific remediation guidance.


### [Serve Qwen3.8-2.4T-A95B, a 2.4T-Parameter Model, with Configurable Reasoning on NVIDIA GB300 NVL72](https://yomu.fyi/post/serve-qwen3-8-2-4t-a95b-a-2-4t-parameter-model-with-configurable-reaso.md)
- Company: [NVIDIA](https://yomu.fyi/company/nvidia-developer-blog.md)
- Author: Michelle Horton
- Published: Aug 12, 2026
- Type: Explainer

Alibaba’s Qwen3.8-2.4T-A95B (Qwen3.8-Max) is an open-weight 2.4T-parameter model with 95B activated per token, designed for reasoning and agentic workloads. Its fine-grained mixture-of-experts architecture combines full and linear attention, supporting context of up to one million tokens and output lengths up to 128K while using bounded recurrent state in linear-attention layers. NVIDIA describes multinode serving on the 72-GPU GB300 NVL72, where a 130 TB/s NVLink domain supports expert communication; in FP8, the model reportedly exceeds 4K tokens per second per GPU and 350 tokens per second per user without additional tuning. Developers can control reasoning depth with low, high, or xhigh modes, choose SGLang, vLLM, NVIDIA Dynamo, or NIM for serving, and use NeMo AutoModel for full SFT or LoRA post-training.


### [Flexible Authentication: Reimagining authentication for millions of users at Airbnb](https://yomu.fyi/post/flexible-authentication-reimagining-authentication-for-millions-of-use.md)
- Company: [Airbnb](https://yomu.fyi/company/airbnb.md)
- Author: Jose Santos
- Published: Aug 12, 2026

Airbnb overhauled its login and registration architecture by transitioning to a server-driven framework called Flexible Authentication. The new system separates user identification from verification, using a backend policy engine to dynamically serve the optimal auth challenge and fallback options based on regional and user context. This shift eliminated dead ends, reduced client bundle sizes, and dramatically sped up experimentation velocity across Web, iOS, and Android.


### [How a major freight railroad scaled pipeline creation with Genie Code](https://yomu.fyi/post/how-a-major-freight-railroad-scaled-pipeline-creation-with-genie-code.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Dinesh Chandrasekaran, Subhadip Chanda, Julia Powell, Gal Oshri
- Published: Aug 12, 2026
- Type: Problem & solution

A major Canadian freight railroad with roughly 20,000 route miles needed to modernize a decades-old analytical estate while handling hundreds of pipelines and rising demand for real-time analytics and AI. Using Databricks Genie Code, Unity Catalog, custom Agent Skills and a Streamlit Databricks App, the team created a metadata-grounded pipeline-generation workflow driven by compact YAML prompts. The workflow discovers schemas, maps source fields, and emits six artifacts—DDL, historical and streaming ingestion, incremental merges, and automated tests—using deterministic patterns for audit columns, deduplication, change-sequence guards and soft-delete reconciliation. Human-reviewed Source-to-Target Mapping preserves business interpretation, while Genie Code handles discovery, orchestration and artifact generation within governed Databricks execution. The reported result was more than 90% automation for new table ingestion, reducing delivery from days per table to minutes and supporting single, multi-table and bulk generation.


### [Introducing OlmoEarth embeddings: Custom embedding exports from OlmoEarth Studio for downstream analysis](https://yomu.fyi/post/introducing-olmoearth-embeddings-custom-embedding-exports-from-olmoear.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Kyle Wiggers
- Published: Aug 12, 2026
- Type: Announcement

OlmoEarth Studio now supports custom computation and export of embedding vectors, compact representations of Earth-observation data generated by open-source OlmoEarth foundation models. Users can select an area, a one-to-twelve-month time span, an encoder variant, spatial resolution, and Sentinel-2 L2A or Sentinel-1 RTC imagery, then receive a Cloud-Optimized GeoTIFF with one int8 band per embedding dimension. The post demonstrates similarity search, few-shot segmentation, change detection, and PCA-based exploration; a logistic regression trained on 60 labeled pixels produced a weighted F1 of 0.84 for three land-cover classes in Ca Mau, Vietnam. Embeddings provide a fast, shareable starting point, while supervised fine-tuning can improve performance for applications needing task-specific results; cloud cover, atmospheric artifacts, and missing observations can affect quality.


### [How to Choose Full-Stack Observability for NVIDIA AI Factories](https://yomu.fyi/post/how-to-choose-full-stack-observability-for-nvidia-ai-factories.md)
- Company: [NVIDIA](https://yomu.fyi/company/nvidia-developer-blog.md)
- Author: Jorge Cardoso
- Published: Aug 12, 2026
- Type: Explainer

AI infrastructure spans compute, networking, storage, orchestration, and applications, so a symptom at one layer may originate elsewhere. The post proposes selecting observability tools by failure domain, mapping components to telemetry sources, and reducing signals to a top-k alert set in a unified Prometheus/Grafana triage dashboard. For a DGX cluster using InfiniBand, BCM, and Slurm, it recommends Redfish/IPMI, DCGM, NVSM, UFM, and BCM, while deferring NetQ, NMX, Run:ai, and NIM until their corresponding capabilities are needed. The framework emphasizes DCGM for GPU metrics, NVSM for DGX system health, UFM for InfiniBand, and BCM for cluster and job aggregation, with specialized tools retaining low-level telemetry. An elevated InfiniBand bit error rate illustrates how retransmissions can slow one rank during NCCL all-reduce, causing synchronized training throughput to follow the slowest rank; alerts should connect concise signals to owners and remediation actions.


### [How iFood built its agentic security platform on ClickHouse Cloud](https://yomu.fyi/post/how-ifood-built-its-agentic-security-platform-on-clickhouse-cloud.md)
- Company: [Clickhouse](https://yomu.fyi/company/clickhouse.md)
- Published: Aug 12, 2026
- Type: Problem & solution

iFood’s security incident response team needed high-volume log ingestion, long-term retention, and rapid access to months of history, but its Databricks-based platform became costly to scale beyond 130 TB and imposed query timeouts. The team ran a production-data proof of concept and rebuilt its tooling around ClickHouse Cloud on AWS: logs land in S3 and flow through ClickPipes into ClickHouse, with Querybook preserving notebook-based investigations and ClickStack planned for operational metrics. With ClickHouse Cloud, iFood reports 9–16x faster queries, expected cost reductions of 40–50%, and data freshness improving from hourly batches to 2–10 minutes; alerts that previously ran hourly can now run about every 10 minutes. That foundation also supports agentic threat hunting: multiple sub-agents query more than 30 TB in parallel, reducing a hunt from about a week to roughly two hours, while Langfuse is used to inspect and tune agent analyses.


### [Running Cost-Efficient Export Workloads at Uber](https://yomu.fyi/post/running-cost-efficient-export-workloads-at-uber.md)
- Company: [Uber](https://yomu.fyi/company/uber.md)
- Published: Aug 12, 2026
- Type: Problem & solution

Uber’s offline export workloads often retrieve a small set of records from large, date-partitioned Apache Hudi tables, but narrow historical predicates can still trigger full-table scans. Repeatedly touching files, metadata, or Parquet footers keeps Google Cloud Storage objects hot, undermining Auto-Class tiering and increasing storage, retrieval, metadata-operation, egress, and latency costs. The approach combines Hudi column stats with sorting on predicate columns: metadata-table statistics prune files without opening them, while clustered records tighten file-level min/max ranges and make pruning more selective. A Hudi secondary index was evaluated but did not reduce file scans enough because records for a subject were spread across most files. The conclusion is that a one-time rewrite and ongoing Hudi table services can turn broad historical scans into lower-touch lookups, while future work targets multi-column layouts and automated ROI-based optimization.


### [How We’re Building Scam Alert on WhatsApp With End-to-End Encryption and Verifiability Guarantees](https://yomu.fyi/post/how-we-re-building-scam-alert-on-whatsapp-with-end-to-end-encryption-a.md)
- Company: [Meta](https://yomu.fyi/company/meta.md)
- Published: Aug 12, 2026
- Type: Announcement

WhatsApp presents an early technical overview of Scam Alert, an optional feature that uses an on-device machine learning model to identify potential scam messages from non-contacts while keeping message content on the device. The warning appears only to the user, who can block, report, continue, or mark a chat trusted; reporting and sharing require explicit user action. To measure performance, the system sends locally aggregated warning and user action counts through confidential federated analytics using Trusted Execution Environments and differential privacy, rather than transmitting raw signals. Model versions are recorded on a public transparency ledger, while published weights, client-side logs, and an expanded Bug Bounty program support independent inspection of delivery and behavior.


### [The Future of Data Analytics: Why AI is rewriting the Analyst’s Job Description](https://yomu.fyi/post/the-future-of-data-analytics-why-ai-is-rewriting-the-analyst-s-job-des.md)
- Company: [Databricks](https://yomu.fyi/company/databricks.md)
- Author: Emma Stowell, Angus Morshead, Ogo Odili
- Published: Aug 12, 2026
- Type: Explainer

The post argues that AI is not eliminating data analysts; it is automating the technical work that has crowded out their business impact. Natural-language tools such as Databricks AI/BI, Genie Code, and Genie One can generate dashboards, answer ad hoc questions, and accelerate tasks such as customer segmentation, which the post says one analyst completed in half a day instead of two months. This shifts the analyst’s focus toward problem framing, context, validation, storytelling, governance, and directing AI agents, while keeping intent, accountability, and decision ownership human. For organisations, the proposed response is to hire and develop curiosity, business acumen, and communication, embed analysts near decision-makers, retain human review, and measure decisions influenced rather than dashboards delivered.


### [Welcoming Fabio Kubo, our new Software Engineer](https://yomu.fyi/post/welcoming-fabio-kubo-our-new-software-engineer.md)
- Company: [Resend](https://yomu.fyi/company/resend.md)
- Published: Aug 12, 2026
- Type: Announcement

Resend announces Fabio Kubo as a new software engineer joining its software engineering team. With more than 10 years of experience, Kubo has helped scale products to millions of customers at iFood and Nu, and he will bring that experience to Resend as the platform grows. He says the product, rapid growth, technical challenges, and fully public handbook attracted him, with the company’s values, culture, working style, and transparency resonating particularly strongly. Kubo also discusses customer feedback as a source of motivation, names Notion and multi-cursor editing as favorite tools, and advises ambitious engineers to learn how they learn and understand underlying concepts when navigating new domains, technologies, and tools.


### [Welcoming Mateus Resende, our new Software Engineer](https://yomu.fyi/post/welcoming-mateus-resende-our-new-software-engineer.md)
- Company: [Resend](https://yomu.fyi/company/resend.md)
- Published: Aug 12, 2026
- Type: Announcement

Resend introduces Mateus Resende as a Software Engineer based in Belo Horizonte, Brazil. He began working in software in 2015, first as a Ruby and Ruby on Rails developer before moving across domains including e-commerce recommendations, vehicle tracking, fintech, and email systems. A snowstorm during his exchange at SUNY Buffalo led him to discover MIT OpenCourseWare, code for hours, and later switch from Electrical Engineering to Computer Science. At Resend, he says its remote and async culture, extensive documentation, and developer-oriented product and company shaped his decision to join. His approach to engineering emphasizes balancing quality with speed and tailoring solutions to users and reviewers, while he recommends fundamentals such as testing, Domain-Driven Design, and Evolutionary Architectures over relying on hyped LLM coding techniques.


### [Introducing Grok 4.6](https://yomu.fyi/post/introducing-grok-4-6.md)
- Company: [Cursor](https://yomu.fyi/company/cursor.md)
- Author: Cursor
- Published: Aug 12, 2026
- Type: Announcement

Grok 4.6, released with SpaceXAI, is presented as a model for long-running agents and ambitious interactive, visual, coding, and knowledge-work tasks. It builds on Grok 4.5 through a longer supplemental training run using curated model-generated reasoning and technical data, an improved optimizer and training recipe, regenerated SFT trajectories, model-based filtering, and agentic reinforcement-learning tasks across several environments. The release says Grok 4.6 matches GPT-5.6 Sol on the Artificial Analysis Intelligence Index and reports stronger first passes, sustained multi-step work, self-testing, and iterative refinement for working projects. It is available in Cursor, Grok Build, the SpaceXAI API, and through OpenRouter, Vercel, and Cloudflare, with pricing from $2 per million input tokens and $6 per million output tokens, while a fast variant costs twice as much.


[Newer posts](https://yomu.fyi/posts/page/77.md) · [Older posts](https://yomu.fyi/posts/page/79.md)