---
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

### [Introducing RTEB: A New Standard for Retrieval Evaluation](https://yomu.fyi/post/introducing-rteb-a-new-standard-for-retrieval-evaluation.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Frank Liu, Kenneth Enevoldsen, Solomatin Roman, Isaac Chung, Tom Aarsen, Fődi, Zoltán
- Published: Oct 1, 2025
- Type: Announcement

Public embedding benchmarks often fail to measure true generalization because training sets overlap with public evaluation data, rewarding memorization over general search quality. The Retrieval Embedding Benchmark (RTEB) beta introduces a standardized evaluation framework designed for real-world enterprise retrieval applications. To prevent overfitting while preserving transparency, RTEB combines fully public datasets with private evaluation sets managed exclusively by MTEB maintainers. The suite spans 20 languages across domains like healthcare, law, finance, and code, measuring ranked retrieval quality using NDCG@10 on datasets of at least 1,000 documents. While currently limited to text-only retrieval and containing repurposed question-answering datasets, the benchmark provides clear signals when models degrade on unseen data.


### [Top Considerations When Choosing a Hybrid Search Solution](https://yomu.fyi/post/top-considerations-when-choosing-a-hybrid-search-solution.md)
- Company: [MongoDB](https://yomu.fyi/company/mongodb.md)
- Author: Jose Parra
- Published: Sep 30, 2025
- Type: Explainer

Natural language queries and generative AI workflows like retrieval-augmented generation have exposed the limitations of standalone vector search, particularly for tokens outside an embedding model's training corpus. Hybrid search addresses these gaps by merging traditional lexical precision with dense vector context. Platforms combine these modalities using techniques such as reciprocal rank fusion and relative score fusion, often complemented by downstream cross-encoders or learning-to-rank models. Architecture choices center on the trade-offs between lexical-first systems using inverted indexes and vector-first platforms employing sparse vectors. MongoDB has integrated vector search indexes alongside its existing lexical indexes, releasing native hybrid search functions across Atlas, Community Edition, and Enterprise Server to unify operational data and search retrieval.


### [Charting a New Course for SaaS Security: Why MongoDB Helped Build the SSCF](https://yomu.fyi/post/charting-a-new-course-for-saas-security-why-mongodb-helped-build-the-s.md)
- Company: [MongoDB](https://yomu.fyi/company/mongodb.md)
- Author: Boris Sieklik
- Published: Sep 30, 2025
- Type: Problem & solution

Widespread enterprise SaaS adoption has introduced notable security blind spots due to inconsistent controls, visibility, and configurations across disparate vendor applications. While traditional compliance frameworks such as SOC 2 and ISO 27001 evaluate provider organizational security, they typically fail to address customer-facing application capabilities. To resolve this discrepancy, MongoDB collaborated with the Cloud Security Alliance and GuidePoint Security to develop the SaaS Security Capability Framework. This framework establishes actionable technical controls across six critical operational domains, including identity and access management, machine-readable logging, configuration management, and incident notifications. By standardizing customer-side capabilities within the shared responsibility model, the framework simplifies vendor risk assessments and provides engineering teams with structured implementation benchmarks.


### [Accelerating Qwen3-8B Agent on Intel® Core™ Ultra with Depth-Pruned Draft Models](https://yomu.fyi/post/accelerating-qwen3-8b-agent-on-intel-coretm-ultra-with-depth-pruned-dr.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Igor Margulis, Ofir Zafrir, Shira Guskin, Guy Boudoukh, Pedro Cuenca
- Published: Sep 29, 2025
- Type: Problem & solution

Local agentic AI workflows generate multi-step reasoning traces that increase token counts and strain real-time inference on personal computers. To accelerate execution, researchers implemented speculative decoding using OpenVINO.GenAI on an Intel Lunar Lake integrated GPU, pairing a 4-bit Qwen3-8B target model with a smaller Qwen3-0.6B draft model. By measuring angular distance across layers, the team pruned six of the draft model's twenty-eight layers to minimize draft latency and fine-tuned it on synthetic data generated from 500,000 prompts. This depth-pruned draft elevated speculative decoding throughput from a 1.3x speedup to a 1.4x speedup over the standalone baseline. Finally, deploying the optimized model alongside the Hugging Face smolagents framework allowed local agents to perform tool invocation and code generation tasks efficiently.


### [VibeGame: Exploring Vibe Coding Games](https://yomu.fyi/post/vibegame-exploring-vibe-coding-games.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Dylan Ebert
- Published: Sep 29, 2025
- Type: Problem & solution

Vibe coding games often fails as projects grow because large context sizes degrade model performance. After evaluating Roblox MCP, Unity MCP, and open web libraries with Claude Code, the author found web tooling offered the strongest model proficiency but lacked high-level game abstractions. To bridge this gap, the author created VibeGame, an open-source declarative game engine built on three.js, rapier, and bitecs. VibeGame uses an Entity-Component-System architecture, XML-like markup, and bundled documentation in an llms.txt file to keep project context lean. While effective for basic physics and rendering mechanics, the engine requires further development for complex features like inventories, multiplayer, and interactions.


### [User foundation models for Grab](https://yomu.fyi/post/user-foundation-models-for-grab.md)
- Company: [Grab](https://yomu.fyi/company/grab.md)
- Author: Abhinav Rai
- Published: Sep 26, 2025
- Type: Explainer

Grab describes a foundation model that learns from both tabular data and sequential clickstream interactions to represent users, merchants, and drivers across its superapp. Traditional recommender systems depended on manually engineered, task-specific features, which required substantial effort and did not capture evolving behavior holistically. The custom architecture addresses heterogeneous modalities including text, numerical values, IDs, images, and location data, combining long-term profiles with immediate intent. Grab pre-trains the model on a diverse corpus, then either extracts embeddings for downstream recommendation and prediction tasks or fine-tunes it to predict directly. The resulting reusable representations are reported to support applications such as ad optimisation, dual app prediction, fraud detection, and churn probability, while future work targets unified data, improved architecture, and greater training and inference efficiency.


### [Swift Transformers Reaches 1.0 – and Looks to the Future](https://yomu.fyi/post/swift-transformers-reaches-1-0-and-looks-to-the-future.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Pedro Cuenca, Christopher Fleetwood, Mattt, Vaibhav Srivastav
- Published: Sep 26, 2025
- Type: Announcement

swift-transformers has released version 1.0 to provide a stable foundation for running local models on Apple Silicon platforms. The library supplies components missing from Core ML and MLX, focusing heavily on tokenization, chat templates, and Hugging Face Hub integration. In this major release, Tokenizers and Hub become standalone top-level modules, enabling developers to import only the components they require. The update also integrates an updated swift-jinja library for faster template processing, adopts Modern Core ML stateful models and MLTensor APIs, removes unnecessary CLI dependencies, and adds full Swift 6 support. Future development will prioritize deeper integration with MLX frameworks and agentic workflows like MCP.


### [Carrying Complexity, Delivering Agility](https://yomu.fyi/post/carrying-complexity-delivering-agility.md)
- Company: [MongoDB](https://yomu.fyi/company/mongodb.md)
- Author: Akshat Vig, Ashish Kumar
- Published: Sep 25, 2025
- Type: Explainer

MongoDB centers its engineering architecture around resilience, intelligence, and simplicity to minimize developer cognitive and operational burdens when building distributed applications. Security is enforced through dedicated clusters in isolated virtual private networks alongside Queryable Encryption, which allows equality and range queries on ciphertext without decryption keys ever leaving the client. High availability is built on replica sets across independent availability zones and multi-cloud topologies, utilizing consensus mechanisms that commit writes only after majority acknowledgment in the active term. Operational friction in artificial intelligence workloads is addressed by integrating vector search directly into the core query engine, eliminating brittle extract-transform-load pipelines and separate vector databases.


### [From Niche NoSQL to Enterprise Powerhouse: The Story of MongoDB's Evolution](https://yomu.fyi/post/from-niche-nosql-to-enterprise-powerhouse-the-story-of-mongodb-s-evolu.md)
- Company: [MongoDB](https://yomu.fyi/company/mongodb.md)
- Author: Ashish Kumar
- Published: Sep 25, 2025
- Type: Explainer

Early perceptions categorized MongoDB alongside eventually consistent NoSQL databases, creating doubts regarding its suitability for mission-critical enterprise workloads. Over fifteen years of development, the platform addressed enterprise requirements by introducing replica sets with Raft-style consensus, native horizontal sharding, tunable read and write concerns, and multi-document ACID transactions across sharded clusters. Security capabilities were expanded through Role-Based Access Control, Field-Level Encryption, and Queryable Encryption supporting prefix, suffix, and substring searches. Current initiatives focus on decoupling compute and storage scaling, developing AI-driven tooling within the Application Modernization Platform to translate legacy relational applications to microservices, and optimizing query execution for non-denormalized data models. MongoDB Atlas now incorporates Atlas Search, Atlas Vector Search, native Stream Processing, and embedding generation powered by Voyage AI models.


### [Endian Communication Systems and Information Exchange in Bytes](https://yomu.fyi/post/endian-communication-systems-and-information-exchange-in-bytes.md)
- Company: [MongoDB](https://yomu.fyi/company/mongodb.md)
- Author: Nitish Joshi
- Published: Sep 25, 2025
- Type: Explainer

Endianness dictates the order in which multi-byte numbers are stored and transmitted across systems. While big-endian formats store the most significant byte first at the lowest address, little-endian systems place the least significant byte first. Communication across diverse architectures relies on consistent byte ordering to prevent critical interpretation errors in fields such as telecommunications, IoT, automotive, finance, and aerospace. To safely process disparate payloads, modern ingestion pipelines deploy an endian converter to normalize raw binary data into a unified format. These normalized data streams flow through Apache Kafka, undergo real-time processing and enrichment via Atlas Stream Processing, and persist in MongoDB Atlas for downstream analytics and visualization.


### [MongoDB SQL Interface: Now Available for Enterprise Advanced](https://yomu.fyi/post/mongodb-sql-interface-now-available-for-enterprise-advanced.md)
- Company: [MongoDB](https://yomu.fyi/company/mongodb.md)
- Author: Jourdain Patrick, Alexi Antonino
- Published: Sep 25, 2025
- Type: Announcement

MongoDB has released the general availability of the MongoDB SQL Interface for MongoDB Enterprise Advanced on self-managed deployments running MongoDB 6.0 or higher. Previously, teams relying on SQL-based business intelligence tools faced maintenance bottlenecks when learning MongoDB Query Language or creating custom extract, transform, and load pipelines. The new interface translates standard SQL queries into native MongoDB operations in real time using MongoSQL, a SQL-92 compatible dialect. Users utilize a Schema Builder CLI to generate JSON schemas that map nested document structures and store them alongside data for query validation. This native query translation replaces the MongoDB BI Connector, which will remain supported until September 2026, while offering improved performance and direct connectivity via JDBC and ODBC drivers.


### [MongoDB is a Glassdoor Best-Led Company of 2025](https://yomu.fyi/post/mongodb-is-a-glassdoor-best-led-company-of-2025.md)
- Company: [MongoDB](https://yomu.fyi/company/mongodb.md)
- Author: Jackie Denner
- Published: Sep 24, 2025
- Type: Announcement

MongoDB has been named one of Glassdoor's Best-Led Companies of 2025, an honor ranking the top 50 organizations with over 1,000 employees based entirely on employee reviews. This recognition coincides with recent company milestones, including the release of MongoDB 8.2, integration with Voyage AI embedding models and rerankers, and the introduction of the MongoDB Application Modernization Platform. MongoDB now serves nearly 60,000 organizations, encompassing more than 70 percent of the Fortune 500 alongside artificial intelligence startups. Company employees attribute the workplace recognition to leadership transparency, regular quarterly goal alignment, and a supportive hybrid work model that grants staff autonomy over their work locations outside the New York City headquarters.


### [From support to sales: Turn ecommerce conversations into customers with Fin](https://yomu.fyi/post/from-support-to-sales-turn-ecommerce-conversations-into-customers-with.md)
- Company: [Intercom](https://yomu.fyi/company/intercom.md)
- Author: Kelly Farrell
- Published: Sep 24, 2025
- Type: Explainer

Online retailers often struggle to answer delivery, returns, discount, and product questions quickly, especially during peak shopping periods, when delays can frustrate shoppers and contribute to abandoned carts. Intercom’s Fin is presented as an LLM-powered AI agent that uses existing knowledge content and real-time data to resolve queries, personalize support, and assist with sales activities such as upselling, cart recovery, and targeted promotions. It can handle order tracking, refunds, exchanges, product availability, and support in more than 45 languages, while integrating with Shopify and Stripe for actions including order changes and refunds. Reported examples include GoodBuy Gear’s 50% resolution rate and engagement in over 20% of interactions, plus Nuuly’s 11% reduction in subscriber support contact rates after implementation. Fin is positioned as a way to scale 24/7 multichannel support and connect service interactions with conversion and loyalty goals.


### [Build AI Agents Worth Keeping: The Canvas Framework](https://yomu.fyi/post/build-ai-agents-worth-keeping-the-canvas-framework.md)
- Company: [MongoDB](https://yomu.fyi/company/mongodb.md)
- Author: Mikiko Bazeley
- Published: Sep 23, 2025
- Type: Explainer

Enterprise AI agent initiatives frequently stall after pilot phases due to technology-first thinking, governance gaps, infrastructure complexity, and poor alignment with business needs. To bridge this divide, development teams are shifting away from data-first pipelines toward a product-first methodology structured as product, agent, data, and model. The Canvas framework provides a phased workflow moving from quick proof-of-concept validation to model orchestration and operational hardening. In Phase 4, developers focus on API management, external provider orchestration, cost optimization, and evaluation pipelines. Phase 5 adds necessary governance, compliance, user experience, and security layers required to transform working agent prototypes into sustainable production deployments.


### [Powering Partner Gateway metrics with Apache Pinot](https://yomu.fyi/post/powering-partner-gateway-metrics-with-apache-pinot.md)
- Company: [Grab](https://yomu.fyi/company/grab.md)
- Author: Alvis Chew
- Published: Sep 23, 2025
- Type: Problem & solution

Partner Gateway needed low-latency analytics for API traffic and response-time metrics across intervals from one hour to 30-day retrospectives, with a particular dataset potentially reaching approximately 6.8 billion rows in a 30-day period. Apache Pinot was selected as a distributed real-time OLAP datastore, using high-throughput ingestion and columnar, indexed, partitioned data for millisecond analytical queries. Initial aggregation queries on datasets over 150GB timed out for 20- to 30-day periods, exceeding 10 seconds and threatening a 300-millisecond SLA. The implementation routes metrics through Kafka and Apache Flink, then ingests Schema Registry-compatible messages into Pinot, while partitioning by metric name and adding aggregation-focused optimizations. For one metric, query latency fell from 5,072 to 35 milliseconds; Star-tree indexing improved speed but raised 30-day storage from 192GB to 373GB, with the additional AWS EBS cost described as minor.


### [Smol2Operator: Post-Training GUI Agents for Computer Use](https://yomu.fyi/post/smol2operator-post-training-gui-agents-for-computer-use.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Amir Mahla, merve, Sergio Paniego, Vaibhav Srivastav, Lewis Tunstall
- Published: Sep 23, 2025
- Type: Problem & solution

Lightweight vision-language models often lack the precise visual grounding and action execution capabilities required for graphical user interface automation. To resolve this deficiency, the authors constructed a post-training pipeline that evolves base models into agentic GUI coders through supervised fine-tuning. The process standardizes disparate mobile and desktop dataset action spaces into a unified functional format utilizing normalized coordinates relative to image size. Training is structured into two sequential phases that first establish basic visual perception and subsequently introduce explicit reasoning steps with masked assistant loss. On the ScreenSpot-v2 perception benchmark, fine-tuning SmolVLM2-2.2B-Instruct increased element localization accuracy to 61.71 percent, while a compact 460-million-parameter model achieved approximately 58 percent accuracy.


### [Simplify AI-Driven Data Connectivity With MongoDB and MCP Toolbox](https://yomu.fyi/post/simplify-ai-driven-data-connectivity-with-mongodb-and-mcp-toolbox.md)
- Company: [MongoDB](https://yomu.fyi/company/mongodb.md)
- Author: Venkatesh Shanbhag, Yang Li, Kurtis Van Gent
- Published: Sep 22, 2025
- Type: Announcement

Organizations building generative AI applications require simplified, standardized connections to an expanding ecosystem of enterprise databases. MCP Toolbox for Databases, an open-source Model Context Protocol server based on Anthropic's standardized protocol, now supports MongoDB Atlas to streamline connections to generative AI systems. This new integration allows gen AI agents to execute standard CRUD operations alongside advanced transformations and computations using the MongoDB aggregation framework. Through flexible configuration files, developers can configure MongoDB Atlas as both a data source and a sink by defining parameters like connection URIs, target datasets, filters, projections, and toolsets. By linking flexible document data with cross-database query capabilities, enterprises can unify results and automate multi-source AI workflows.


### [SyGra: The One-Stop Framework for Building Data for LLMs and SLMs](https://yomu.fyi/post/sygra-the-one-stop-framework-for-building-data-for-llms-and-slms.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Bidyapati Pradhan, Vipul Mittal, Amit Kumar Saha, Surajit Dasgupta
- Published: Sep 22, 2025
- Type: Problem & solution

Training and aligning large language models and small language models requires datasets tailored for complex reasoning, preference tuning, multi-turn questioning, and format conversion. To eliminate the need for bespoke data preparation scripts, SyGra provides a low-code and no-code Python framework for automated dataset creation, transformation, and alignment. The library integrates with diverse inference backends, including vLLM, Hugging Face TGI, Triton, and Ollama, allowing teams to focus on prompt engineering rather than pipeline infrastructure. It supports data workflows ranging from converting PDFs and knowledge bases into question-answering pairs to filtering low-quality samples and generating Direct Preference Optimization datasets. These plug-and-play workflows reduce manual curation effort while accelerating model fine-tuning and retrieval-augmented generation pipelines.


### [Introducing the Okta Open Source MCP Server](https://yomu.fyi/post/introducing-the-okta-open-source-mcp-server.md)
- Company: [Okta](https://yomu.fyi/company/okta.md)
- Author: Swetha Selvanayagam
- Published: Sep 22, 2025
- Type: Announcement

The Okta Open Source MCP Server connects large language model agents to Okta’s Admin Management APIs for identity and access management workflows. It translates natural-language requests into structured API calls, supporting user and group management, group membership and application operations, system-log retrieval, and additional application and policy actions. The server uses Okta’s official SDK and supports interactive Device Authorization Grant authentication or browserless Private Key JWT, with scoped API access and credentials supplied through environment variables. The guide explains setup with Python 3.9 or later and uv, Okta application configuration, and VS Code’s MCP client settings, then shows examples including user administration and audit-report generation. Its stated purpose is to automate organization-management tasks while respecting Okta’s security model.


### [Gaia2 and ARE: Empowering the community to study agents](https://yomu.fyi/post/gaia2-and-are-empowering-the-community-to-study-agents.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Clémentine Fourrier, Grégoire Mialon, Maxime Lecanu, Pierre Andrews, Adrien Carreira, frere thibaud, Avijit Ghosh, Romain Froger, Dheeraj Mekala, Caroline Pascal, Ulyana Piterbarg
- Published: Sep 22, 2025
- Type: Benchmark

Existing AI agent evaluation environments are often tightly coupled to specific tasks and fail to model real-world challenges such as API failures, spontaneous events, and asynchronous conditions. To address this limitation, the Gaia2 benchmark and the Meta Agents Research Environments (ARE) framework introduce interactive read-and-write evaluation. Gaia2 incorporates 1,000 human-created scenarios spanning multi-step execution, cross-source search, ambiguity handling, adaptability, temporal reasoning, agent collaboration, and noise tolerance. Using a simulated smartphone interface equipped with 101 tools, evaluations showed that GPT-5 with high reasoning scored highest overall, while Kimi K2 was the leading open-source model. The results demonstrated that instruction following and search do not reliably predict performance on closer-to-real-world tasks.


[Newer posts](https://yomu.fyi/posts/page/169.md) · [Older posts](https://yomu.fyi/posts/page/171.md)