Loading…
Latest reads
Every post, summarised
Grounded summaries of engineering blogs, newest first. Each links to the original.
- 4,671 posts
- 20 companies
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
Latest posts
Building Deep Research: How we Achieved State of the Art
Building production AI research agents presents challenges around context window pollution, escalating token costs, and architectural brittleness across model updates. To resolve these issues, Tavily rebuilt its deep research system around simplified orchestration, compact tooling, and active context curation. The agent mimics human research workflows by distilling tool outputs into concise reflections for ongoing reasoning, withholding raw retrieved web data until the final deliverable stage. Compared to traditional ReAct propagation architectures where token consumption scales quadratically, this reflection-based approach achieves linear token growth. As a result, the system reduced token consumption by 66% compared to Open Deep Research while reaching state-of-the-art performance on DeepResearch Bench.
OVHcloud on Hugging Face Inference Providers 🔥
OVHcloud is now integrated as a supported Inference Provider on the Hugging Face Hub, expanding serverless inference options across model pages and client SDKs. The integration enables access to open-weight models, including gpt-oss, Qwen3, DeepSeek R1, and Llama, using European infrastructure with pay-per-token pricing starting at €0.04 per million tokens. Developers can connect via Python and JavaScript SDKs using either direct custom API keys or automatic routing through Hugging Face tokens. The service supports structured outputs, function calling, multimodal workflows, and embedding models while providing sub-200ms first-token response times. Calls routed through Hugging Face pass through standard provider pricing without markups, and PRO tier subscribers receive monthly inference credits.
Unlocking Peak Performance on Qualcomm NPU with LiteRT
Google introduces the LiteRT Qualcomm AI Engine Direct (QNN) Accelerator, developed with Qualcomm to replace the previous TFLite QNN delegate and simplify NPU deployment across supported Qualcomm SoCs. It integrates vendor compilers and runtimes behind a unified workflow, supports ahead-of-time and on-device compilation, and can fall back to GPU or CPU when needed. Across 72 canonical vision, audio, and NLP models, the accelerator supports 90 LiteRT ops, enables full NPU delegation for 64, and reports up to 100x CPU and 10x GPU speedups. On Snapdragon 8 Elite Gen 5, FastVLM-0.5B uses int8 weights, int16 activations, and specialized transformer kernels to reach 0.12 second time-to-first-token, over 11,000 prefill tokens per second, and over 100 decode tokens per second.
Unlock the Secrets of a Custom Sign-In Page with Tailwind and JavaScript
This tutorial shows how to customize an Okta-hosted sign-in page for a fictional to-do application while retaining the Okta Identity Engine and Sign-In Widget (SIW). It starts with a custom domain and brand configuration, then uses the page code editor, SIW design tokens, custom text, Tailwind CSS via CDN, and external JavaScript behavior to create a responsive layout, branded footer, and terms-and-conditions modal. The modal uses Alpine.js transitions and a MutationObserver watching the authentication container so it appears after SIW elements render; Google Fonts also require CSP allowlist entries for googleapis.com and gstatic.com. The post notes that browser manipulation can bypass the modal, recommends accessibility testing after customization, and describes connecting the brand to an Okta React sample through an OIDC custom issuer URL.
SpellVault’s evolution: Beyond LLM apps, towards the agentic future
SpellVault began as Grab’s no-code platform for building LLM apps, using Retrieval-Augmented Generation (RAG) and plugins to connect applications with knowledge sources and external systems. Users could ground responses in Wikis, Google Docs, text, and PDFs, invoke custom HTTP endpoints, and access apps through the web, Slack, or APIs. The platform later added citations, Python execution for mathematical problems, scheduled actions, and drag-and-drop Workflows combining LLM calls, code, and Knowledge Vault lookups, while its executor moved toward graphs with nodes, edges, and states. SpellVault now exposes apps and RAG through MCP, allowing external agents and compatible clients to invoke apps and search, retrieve, or add Knowledge Vault information; TinyMCP adds MCP capabilities to FastAPI as a router.
20x Faster TRL Fine-tuning with RapidFire AI
Hugging Face TRL now officially integrates with RapidFire AI to accelerate LLM fine-tuning and post-training experimentation through concurrent configuration evaluation. Instead of executing training configurations sequentially, the platform shards datasets into discrete chunks and cycles multiple model configurations across GPUs at chunk boundaries. The runtime handles automatic checkpointing via a shared-memory-based adapter and model spilling mechanism to maintain consistent training state. Experimenters can monitor live metrics on an MLflow-based dashboard and use Interactive Control Ops to stop underperforming runs or clone and warm-start promising configurations mid-flight. Benchmark results on NVIDIA A100 GPUs demonstrate experimentation speedups ranging from 15x to 20x over sequential runs when training TinyLlama-1.1B and Llama-3.2-1B models.
Open ASR Leaderboard: Trends and Insights with New Multilingual & Long-Form Tracks
The Open ASR Leaderboard expanded its evaluation framework by introducing dedicated multilingual and long-form transcription tracks across eleven datasets. Benchmarking more than sixty open- and closed-source models from eighteen organizations revealed clear operational trade-offs between accuracy and inference speed. Systems combining Conformer encoders with large language model decoders achieved the lowest word error rates in short-form English speech recognition. In contrast, connectionist temporal classification and token-and-duration transducer decoders yielded tenfold to hundredfold improvements in throughput with only slight accuracy penalties. While closed-source commercial systems maintained performance leads in long-form audio transcription, specialized single-language models consistently outperformed generalized systems supporting hundreds of languages.
How we prepare Shopify for BFCM
Shopify’s BFCM readiness program addresses the challenge of operating critical commerce infrastructure at traffic levels informed by 2024 records, while preparing APIs with no prior holiday-traffic history. Starting in March, teams combined capacity planning on Google Cloud, an infrastructure roadmap, risk assessments, chaos-engineering Game Days, and a Resiliency Matrix covering failure modes, recovery objectives, runbooks, and on-call coverage. Genghis load tests and Toxiproxy network faults ran across three GCP regions, while five April–October scale tests exercised browsing, checkout, analytics, webhooks, regional failover, and cascading failures; testing reached 146 million requests per minute and a p99 target of 200 million. The work exposed and addressed Kafka partition, memory, timeout, routing, queueing, and failover issues, while the operational plan adds monitoring, 24/7 incident coverage, merchant communications, live tuning, and a post-BFCM review.
Introducing AnyLanguageModel: One API for Local and Remote LLMs on Apple Platforms
Apple developers frequently face integration friction when trying to support a mix of local and cloud language models across disparate APIs. To resolve this fragmentation, AnyLanguageModel introduces a unified Swift package that acts as a drop-in replacement for Apple's Foundation Models framework. The package standardizes interactions across local backends such as Core ML, MLX, and llama.cpp alongside cloud providers like Anthropic and OpenAI. To avoid dependency bloat from multi-backend support, the library employs Swift 6.1 package traits so projects only import the specific runtime engines they require. Furthermore, the library extends beyond current Foundation Models limitations by adding prompt image support for vision-language models.
Intercom is now a Shopify Plus Technology Partner
Intercom announces that it is now a certified Shopify Plus Partner on the Technology Track. The program recognizes technology providers whose product quality, service, performance, privacy, and support meet advanced requirements for Shopify Plus merchants. Intercom says its integration is vetted and optimized, and describes recent additions including Data Connector templates for Fin, multi-store support, inbox order actions, EU workspace support, and updated data mapping and custom fields. The announcement also lists planned expanded Fin Tasks, Model Context Protocol support, and smarter product search powered by Shopify data, positioning these capabilities as ways to resolve ecommerce support requests faster and personalize conversations at scale as merchants prepare for peak season and rising customer expectations.
First Block with Jesse Zhang, Co-founder and CEO of Decagon
The episode profiles Jesse Zhang, co-founder and CEO of Decagon, whose AI agents support customer service and reportedly achieve 70–80% deflection rates and 3x improvements in customer satisfaction. In its first 18 months, Decagon prioritized short-term execution and customer deployment, then shifted toward longer-term thinking; the source says this helped it move from stealth to unicorn status in a year. Zhang also describes intentional customer discovery, Agent Operating Procedures (AOPs), enterprise trust, and the need to pair technical excellence with commercial thinking. He credits senior generalists from his network with establishing an early team foundation that supported growth from 12 to 200 people in 18 months, while cautioning against applying generic advice instead of judging personal strengths and timing.
Apriel-H1: The Surprising Key to Distilling Efficient Reasoning Models
Retrofitting efficiency into existing large language models often fails when naive distillation disrupts complex multi-step reasoning mechanisms. The Apriel-H1 project addresses this challenge by converting a 15B full-attention reasoning model into a Mamba hybrid using targeted distillation on high-quality SFT reasoning traces rather than diffuse pretraining data. Built on the open-source Fast-LLM framework, the process applies reverse KL divergence alongside a staged layer replacement strategy combining Leave-One-Out analysis and dynamic loss evaluations. Across fifty total blocks, replacing thirty attention layers with Mamba mixers yielded the flagship Apriel-H1-15b-Thinker-SFT checkpoint. This configuration achieved a 2.1x throughput increase with minimal benchmark degradation after 76.8B training tokens.
2026 customer service planning series: Vol. 01
Part one of a five-part 2026 customer service planning series argues that support organizations must be redesigned around AI rather than adding AI to existing tools, processes, and org charts. It frames AI Agents as end-to-end resolution engines and infrastructure that can serve as the first and last touchpoint, manage workflows, orchestrate handoffs, and take actions. The proposed mindset shift includes planning for changing work distribution, treating support as a product function, measuring resolution, impact, and system reliability, and assigning clear ownership for agent performance and continuous feedback. The post also says teams should give AI increasingly complex workflows while people improve the system, creating compounding returns. It concludes that adaptability will be essential as AI evolves, and previews a future edition on designing the resulting support organization.
Secure Authentication with a Push Notification in Your iOS Device
The tutorial shows how to build a native iOS sign-in flow using Okta DirectAuth and push notification MFA. It starts with an Okta Integrator Free Plan org, configures an OIDC Native Application and enables Okta Verify push notifications, while noting additional authorization policies may be required for a custom authorization server. In Xcode, the app uses Swift, SwiftUI, Swift Package Manager, and the Okta mobile Swift packages OktaDirectAuth and AuthFoundation to handle credentials, tokens, and MFA challenges without browser redirects. An AuthService coordinates authentication state, user and token information, sign-out, access-token refresh, and session restoration from stored credentials. The completed flow is described as phishing-resistant and able to maintain an active session directly within a SwiftUI app.
Customer Experience: The 2026 Marketer's Guide
Customer experience (CX) spans every interaction across the journey, from advertising and purchase through support, product use, and advocacy, rather than referring only to customer service, UX, or customer success. The guide argues that AI has raised expectations for fast, personalized responses, while privacy-first marketing increases the importance of consented zero-party and first-party data, voice-of-customer programs, and social listening. Its framework maps awareness, consideration, purchase, post-purchase, and loyalty or advocacy; combines social, survey, support, and review data; prioritizes fixes with an impact-versus-effort matrix; and establishes workflows, response SLAs, and ongoing measurement. It recommends metrics including NPS, CSAT, CES, sentiment, and churn rate, alongside competitive benchmarking and continuous iteration. Examples describe using Brandwatch's Data Upload API and Social Panels to identify product issues, customer questions, and improvement opportunities before broader launches or operational changes.
Easily Build and Share ROCm Kernels with Hugging Face
Compiling custom deep learning GPU kernels across architectures often leads to complex build flag management, compiler errors, and ABI issues. Hugging Face's kernels library and kernel-builder streamline this workflow by supporting backends such as ROCm, CUDA, Metal, and XPU. Using the RadeonFlow FP8 block-wise GEMM kernel optimized for the AMD Instinct MI300X GPU as an example, developers organize files into specific headers and HIP implementations. The build is configured via a build.toml manifest and flake.nix to ensure reproducible compilation across supported PyTorch and ROCm versions. Artifacts can then be pushed to the Hugging Face Hub, allowing users to load and execute custom operators directly via get_kernel without traditional installation steps.
Join the AMD Open Robotics Hackathon
AMD, Hugging Face, and Data Monsters announced the AMD Open Robotics Hackathon, an in-person competition scheduled for Tokyo and Paris in December 2025. Participating teams of up to four adults will compete over three days across two core missions. The first mission covers an instructor-led session on configuring the LeRobot development environment using AMD AI solutions. During the second mission, teams spend two days developing a freestyle project to address a real-world problem using LeRobot. Participants receive access to SO-101 robotics kits, AMD Ryzen AI laptops, and AMD Instinct MI300X GPUs via AMD Developer Cloud, with prizes awarded to the top seven teams in each city based on creativity, difficulty, ease-of-use, and practicality.
Treating Data as Code at Two Sigma
Scaling research and trading platforms across thousands of data sources created bottlenecks at Two Sigma, where reliance on database snapshots and fragmented infrastructure slowed dataset delivery to data scientists. To address operational costs and architectural complexity, the data engineering team adopted software development principles by treating data as code. The organization migrated to Google BigQuery's serverless architecture, standardized SQL transformations using dbt, and defined declarative pipelines with Terraform under continuous integration workflows. Internal tooling was introduced to track directed acyclic graph dependencies, automate anomaly detection, and streamline data discovery. These shifts eliminated manual data movement routines, reduced operational overhead, and enabled formal data contracts to safeguard downstream consumers and emerging language model integrations.
Past, Present, and Future
Cursor has announced a $2.3 billion Series D financing at a $29.3 billion post-money valuation, nearly two years after describing a vision for an AI-assisted code editor that could make programming more helpful, answer codebase questions instantly, and reduce the visibility of source code. The company says the early stages of that vision are taking shape while substantial work remains to realize Cursor’s potential. It reports a team of more than 300 engineers, researchers, designers, and operators, over $1 billion in annualized revenue, millions of developers and major engineering organizations as customers, and in-house models generating more code than almost any other LLMs in the world. Existing investors Accel, Thrive, and Andreessen Horowitz participated alongside new partners Coatue, NVIDIA, and Google, while the funding will support further research and Cursor’s next magical moments.
Building for an Open Future - our new partnership with Google Cloud
Hugging Face and Google Cloud announced an expanded strategic partnership designed to streamline the deployment and management of open models on Google Cloud infrastructure. Prompted by a tenfold increase in Hugging Face usage on Google Cloud over three years, the collaboration introduces a joint CDN Gateway using Hugging Face Xet technology to cache models and datasets directly on Google Cloud. This caching mechanism aims to shorten download times, strengthen model supply chain resilience, and accelerate time-to-first-token across Vertex AI, Google Kubernetes Engine, Cloud Run, and Compute Engine virtual machines. Hugging Face plans to integrate native library support for Google Cloud TPUs, lower instance prices on Inference Endpoints, and enhance Hub security scanning via VirusTotal, Google Threat Intelligence, and Mandiant.
Top topics
- Architecture834
- Performance816
- LLMs660
- Machine Learning622
- Open Source563
- AI Agents553
- AI470
- Developer Experience448
Weekly digest
The best engineering reads, once a week.