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
Differential Transformer V2
Differential Transformer V2 introduces an architectural refinement to differential attention that pairs and subtracts query heads within the same grouped-query attention group. The architecture doubles query heads while preserving key-value head counts, which avoids increasing key-value cache demands and removes the need for custom kernels. DIFF V2 replaces the per-head RMSNorm of its predecessor with a per-token, per-head projected lambda passed through a sigmoid function. This formulation expands the context root-mean-square range to between zero and root two, preventing massive gradient magnifications, mitigating attention sinks, and stabilizing large learning rate pretraining. Ablations confirm that sharing keys and values across subtracted heads and constraining lambda scaling are necessary to prevent training instability and elevated loss.
Introducing xaa.dev: A Playground for Cross App Access
xaa.dev is a free, beta playground for exploring Cross App Access (XAA) end to end without local setup, infrastructure provisioning, or signup. It addresses the difficulty of testing XAA, which otherwise requires configuring an Identity Provider, resource authorization server, resource API, and requesting application before a token exchange can be observed. The site pre-configures these roles and guides users through authentication, token exchange, access token request, and resource access while exposing requests, responses, and cryptographic claims. Developers can also connect their own apps, including MCP clients, and test both OIDC and SAML identity assertions; it is currently in beta and requires no account.
Introducing Waypoint-1: Real-time interactive video diffusion from Overworld
Overworld introduced Waypoint-1, a real-time interactive video diffusion model controllable through text prompts, mouse movements, and keyboard inputs. The architecture uses a frame-causal rectified flow transformer trained on compressed latent representations across 10,000 hours of video game footage paired with control signals. Pre-training uses diffusion forcing with causal attention, while post-training incorporates self forcing via DMD to mitigate autoregressive rollout error accumulation, enable one-pass classifier-free guidance, and support few-step denoising. To achieve low latency on consumer hardware, Overworld developed WorldEngine, a pure Python streaming inference library. Utilizing AdaLN feature caching, static rolling key-value caching with Flex Attention, fused matrix multiplications, and PyTorch compilation, the 2.3B parameter Waypoint-1-Small model reaches up to 60 frames per second on an RTX 5090 GPU.
Okta Developer Connect Recap
Okta Developer Connect Bengaluru was Okta’s first flagship Developer Connect event in India, bringing developers, architects, engineering managers, IAM practitioners, and technology leaders together to discuss identity as systems scale and AI agents work alongside humans. Sessions framed identity as foundational infrastructure spanning users, applications, APIs, services, and AI agents, while connecting core standards and practices to platform use cases including the Okta MCP Server, Cross App Access, Okta Integration Network, Okta Workflows, lifecycle management, and Verifiable Digital Credentials. Interactive discussions, audience Q&A, quizzes, surveys, and a research panel complemented talks and enabled exchanges with Okta engineers, product leaders, and advocates. The Bengaluru event begins an ongoing series intended to support practical identity education and open technical dialogue about enterprise-ready systems, identity standards, and AI-driven access and security assumptions.
How Etsy Uses LLMs to Improve Search Relevance
Etsy’s Search Relevance team addresses a limitation of engagement-based search signals: popular listings can attract clicks even when they are not the best match for a query. It introduces semantic relevance, measured through a framework combining human-curated golden labels, an LLM annotator, cascaded models, and production integrations, with categories for relevant, partially relevant, and irrelevant query-listing pairs. The data pipeline uses sampled search-log pairs, dual human annotation, an evolving guideline, few-shot chain-of-thought prompting with o3 in LangGraph, and self-consistency sampling; a Qwen 3 VL 4B teacher then labels data at scale before distilling into a BERT-based two-tower student. The student supports real-time use with less than 10ms additional latency, while the framework evaluates and enhances search relevance alongside engagement signals.
AI Trends to Watch In 2026
eBay’s leaders identify five AI-related trends they expect to shape commerce and engineering in 2026, building on the company’s 2025 work in search, recommendations, seller tools, and eBay Live. They predict AI will absorb complexity across translation, compliance, payments, logistics, and risk while enabling continuous verification and agentic commerce that can negotiate, verify provenance, and execute cross-border transactions. Other forecasts include using AI to surface pre-loved goods, identify recyclable materials, deliver company-specific context to models for developer productivity, and make shopping more emotionally engaging. The final theme is uncertainty: because generative models introduce unpredictable behavior, product teams will need guardrails and faster learning from observable failures rather than relying on fully predictable flows.
From deployment slop to production reality: How BriX bridges the gap with enterprise-grade AI infrastructure
BriX addresses “deployment slop,” the gap between quickly built AI prototypes and enterprise production, where inconsistent versions, reliability failures, and security risks can block adoption. The platform centralizes production infrastructure so semi-technical domain experts can configure deployments rather than become DevOps specialists, covering scaling, monitoring, audit trails, access controls, data connections, and consistent behavior. BriX supports switching among models such as Claude, GPT, and Gemini; its Model Context Protocols (MCPs) provide standardized, pre-built connectors to approved enterprise data sources with built-in access controls and query logging. Centralized system prompts and context files enforce shared guardrails, while custom frontends and persistent, shareable reports extend use beyond chat interfaces. The stated result is a platform intended to turn deployment into a configuration task, helping teams move from prototypes to enterprise-grade tools in days rather than months.
MongoDB.local San Francisco 2026: Ship Production AI, Faster
MongoDB announced several features aimed at streamlining AI application development across its database and search ecosystem. The Voyage 4 embedding model family is now generally available, introducing cross-model compatibility within a shared embedding space alongside the video-capable voyage-multimodal-3.5 model. For in-database operations, MongoDB Community Edition introduced Automated Embedding in public preview to eliminate external synchronization pipelines for vector generation. Vector Search gained Lexical Prefilters, replacing the knnBeta operator with a dedicated vectorSearch operator and vector data type inside $search aggregations. Additionally, MongoDB made its intelligent assistant generally available in Compass and released the source code for its mongot search engine under the SSPL.
Building a better Bugbot
Bugbot is a code review agent built to identify logic bugs, performance issues, and security vulnerabilities in pull requests before production, as increasingly capable coding agents increased review workload. Its development moved from qualitative assessments to systematic experimentation, using an AI-driven resolution-rate metric, the BugBench benchmark, and online evaluations of real pull requests. An early production flow ran eight parallel passes with randomized diff ordering, majority voting, category filters, validation, and deduplication, while later versions adopted a fully agentic design with tools and dynamic context. Across 40 major experiments, resolution rate rose from 52% to over 70%, bugs flagged per run from 0.4 to 0.7, and resolved bugs per pull request from roughly 0.2 to about 0.5. Newer versions caught more bugs without a comparable rise in false positives, and planned capabilities include Autofix, self-verification, deep research, and continuous scanning.
Open Responses: What you need to know
Open Responses is a new open inference standard initiated by OpenAI, developed by the open source AI community, and backed by Hugging Face. While agentic workloads require multi-step planning and tool execution, the ecosystem has remained constrained by the legacy Chat Completion format and proprietary Responses implementations. Open Responses addresses this mismatch by standardizing semantic event streaming, provider-specific configuration options, and distinct roles for model providers and intermediary routers. The specification formalizes reasoning visibility across raw traces, protected encrypted content, and sanitized summaries while supporting provider-managed sub-agent execution loops. Developers can now orchestrate multi-step tool calls and stream reasoning deltas across heterogeneous providers through a single consistent API schema.
Scaling long-running autonomous coding
The post reports experiments running coding agents autonomously for weeks, with hundreds concurrently contributing to projects that typically take human teams months. It describes initial dynamic coordination through shared files, locks, and optimistic concurrency control, then explains why flat peer structures caused bottlenecks, fragility, risk aversion, and stalled progress. The successful design separates recursive planners from task-focused workers, uses a judge between cycles, and lets workers push changes to a shared branch with minimal conflicts. In tests, agents built a browser with more than 1 million lines across 1,000 files, migrated Solid to React over three weeks with +266K/-193K edits, and delivered a 25x faster Rust video renderer; other projects remain underway. The authors say GPT-5.2 models perform better on extended autonomous work, role-specific models and carefully tuned prompts matter, and moderate structure outperforms both flat peer coordination and elaborate controls, though drift and scheduling remain unsolved.
The Design & Implementation of Sprites
Sprites are Linux virtual machines designed as fast, disposable computers with root access, persistent 100GB durable filesystems, automatic sleeping, and low inactive cost. To make creation feel instantaneous, the platform removes user-facing OCI container images and keeps pools of preloaded standard Fly Machines, so a new Sprite mainly performs startup work rather than pulling and unpacking an image. Its storage stack follows a hacked-up JuiceFS model, splitting immutable data chunks from metadata, keeping metadata durable with Litestream, and using a sparse NVMe volume as a dm-cache-like read-through cache for object storage; checkpoints and restores primarily shuffle metadata. This design supports migration and recovery without depending on local storage, while low-cost sleeping and object-backed disks suit interactive work more than warm, containerized production workloads, and billing applies only to storage blocks actually written.
AI in Investment Management: 2026 Outlook (Part I)
Senior leaders and researchers at Two Sigma analyze the expanding role of artificial intelligence across quantitative investment management for 2026. Rapid model improvements are inverting traditional quantitative research workflows by vastly expanding hypothesis generation and shifting operational bottlenecks toward rapid evaluation. Rather than relying on large language models to execute trades independently, firms are integrating agentic workflows as an underlying operating system across data pipelines and portfolio rooms. However, autonomous agents present alignment challenges because they optimize proxy objective functions relentlessly without intrinsic contextual awareness. Sustained success relies heavily on human supervision, rigorous safety monitoring, and disciplined research execution rather than mere compute scale or model complexity.
Vision RAG: Enabling Search on Any Documents
Traditional retrieval-augmented generation relies on text parsing and optical character recognition to extract data from complex visual documents. These legacy techniques introduce high engineering effort, inconsistent accuracy, and heavy scaling costs. Vision RAG resolves these challenges by embedding entire visual documents directly through multimodal models like Voyage AI's voyage-multimodal-3.5, removing the need for text extraction pipelines. In this pipeline, dense vector embeddings map both text queries and visual assets into a unified representation space. At query time, the system retrieves relevant document images and supplies them alongside the text prompt to Anthropic's Claude 3.5 Sonnet to generate visually grounded responses.
Why We Built Our Own Background Agent
Ramp built Inspect, a hosted background coding agent that writes code and verifies its work using the context and tools available to engineers. For backend tasks it can run tests, inspect telemetry, and query feature flags, while frontend work can be checked visually with screenshots and live previews. Each session runs in a sandboxed Modal VM initialized from repository-specific images and snapshots, with integrations including GitHub, Slack, Sentry, Datadog, LaunchDarkly, Braintrust, and Buildkite. Inspect supports frontier models, MCPs, custom tools, and skills, and provides Slack, web, Chrome extension, pull request, and browser-based VS Code workflows whose changes remain synchronized. Ramp reports that about 30% of merged pull requests in its frontend and backend repositories are written by Inspect.
Building the Universal Commerce Protocol
Universal Commerce Protocol (UCP) is an open standard co-developed by Shopify and Google to let AI agents discover merchant capabilities, negotiate what both sides support, and transact with merchants. It addresses commerce complexity arising from cart-, buyer-, and market-dependent payment rules, discount combinations, and fulfillment variations. UCP uses layered extensibility: a shopping service supplies transaction primitives, capabilities such as Checkout and Orders are independently versioned, and extensions add domain-specific schemas without changing the core. Profiles and reverse-domain namespaces support decentralized capability discovery, while checkout states and continue_url enable structured handoff when human input or unsupported capabilities are required. Payment handlers are negotiated dynamically per transaction, and the public protocol is presented as ready for merchants, agents, and providers to build against.
Best practices for coding with agents
Cursor's guide presents practices for using coding agents that can run for hours, complete multi-file refactors, and iterate until tests pass. Planning first is emphasized: Plan Mode researches the codebase, asks clarifying questions, creates a reviewable implementation plan, and waits for approval. The guidance recommends letting the agent discover context, starting new conversations when focus declines, and using Rules for persistent project instructions while Skills provide dynamic workflows. It also describes hooks for long-running loops, worktrees for isolated changes, parallel model runs, cloud agents, and Debug Mode's hypothesis-and-instrumentation process. Careful diff review, specific prompts, and verifiable goals remain necessary because generated code can be subtly wrong.
Welcome to Notion, Sequin team!
Notion welcomes the Sequin team—Eric Goldman, Anthony Accomazzo, and Carter Pedersen—following discussions about the companies’ shared view of fragmented knowledge work. Sequin built a data-syncing product that brought information from systems including Salesforce, ServiceNow, and Stripe into Postgres, giving developers flexible building blocks instead of requiring them to recreate integrations. The founders say they were drawn to Notion’s enterprise search, work on AI and agents, ambitious direction, and strong user community, while Notion describes Sequin’s experience as aligned with its plans. The announcement frames the broader problem as information scattered across documents, conversations, and tools, and points to AI and agents as a way to help teams find information, automate repetitive work, and prepare for AI-native work.
Code And Let Live
Code And Let Live argues that read-only, ephemeral sandboxes are the wrong abstraction for coding agents, which need durable computers rather than fresh containers for every task. It introduces Sprites, disposable cloud computers that provide root Linux shells, 100GB of initial capacity, HTTPS through an Anycast network, automatic idle shutdown and metering stops, and persistence until explicitly removed. Sprites can be checkpointed and restored in about a second, allowing interactive recovery after changes while retaining installed software and development state across days or months. The argument extends beyond developer workflows: durable agents can keep realistic application context, observe logs, and support personal software whose development and production environments are the same, although the post says Sprites are unsuitable for applications serving millions of users.
Why team size no longer matters
Lean teams competing with larger companies cannot match their rivals’ hiring capacity or budgets, prompting a reassessment of success based on individual impact rather than headcount. Adding tools, integrations, and AI can create a “multi-tool trap,” scattering information and accelerating mistakes when infrastructure and direction are weak. The recommended response is to consolidate work and knowledge into connected systems, invest in documentation such as roadmaps, specifications, requirements, and strategic memos, and choose infrastructure improvements over reflexive hiring. These foundations give AI usable context, preserve decisions through organizational change, and help individuals operate as effective generalists; the conclusion is that scalable infrastructure can let one person do work that once required three, while making each future hire more impactful.
Top topics
- Architecture834
- Performance816
- LLMs660
- Machine Learning622
- Open Source563
- AI Agents553
- AI470
- Developer Experience448
Weekly digest
The best engineering reads, once a week.