Search posts, papers, and topics
Claude Code 2026‑09‑18 release adds AGENTS.md fallback when CLAUDE.md is missing and makes the auto‑mode classifier server‑side by default. It also introduces several new env vars, header maps, and dozens of bug‑fixes that improve stability and startup speed.
Android 17 QPR1 is the first Android release since 3.x to introduce new APIs without an AOSP update. The APIs are currently limited to Pixel devices and not yet exposed to other OEMs.
Pirate Face offers a decentralized, torrent‑based layer that mirrors open LLM models from Hugging Face, providing checksum‑verified downloads and a drop‑in API so pipelines stay functional even if the original host disappears.
A joke npm package that pads strings by calling a TypeSafe LLM model, essentially replicating `padStart()` with unnecessary API calls. Not production‑ready and offers no real engineering insight.
Uber developed a context-aware mechanism to prevent retry storms in deep microservice dependency chains. It introduces "error ownership" where services claim errors they originate and unclaim errors they propagate, allowing upstream callers to make informed retry decisions and avoid amplifying load on already struggling services.
This article argues that uptime percentages are a poor public interface for communicating service reliability because their non-linear nature is not intuitive to non-infrastructure people. It proposes showing absolute downtime (e.g., hours affected) alongside percentages for better clarity for a general audience.
Vercel reports that the Jev decision model was adopted by 13% of paid teams within its first day, outpacing prior model launches. Jev claims to be up to 194× faster and 445× cheaper than general‑purpose LLMs while returning structured, probabilistic decisions.
Vercel AI Gateway now offers Jev, a probabilistic decision model that returns typed choices, scores, and booleans instead of raw text. TypeSafe AI reports it runs up to 193× faster and 445× cheaper than standard LLMs, exposed via the experimental evaluate API in AI SDK 7.
Jev is a "System One" AI model focused on classification, providing calibrated probabilities for predefined answers rather than generating text. This article demonstrates its use with the Laravel AI SDK to replace complex rule-based systems for detecting spam and auto-replies in a helpdesk application.
CodeName One prepared for Android 17 (API 37) by addressing platform changes proactively, including fixing version number parsing and implementing the new system-rendered location button. They also added robust PEM key parsing and explicit task removal to simplify common security operations for app developers.
Cloudflare adds four granular roles (Metadata Read‑Only, Content Read‑Only, Editor, Admin) that can be scoped to a single Worker (or other Developer Platform resources). The roles let you enforce least‑privilege for teammates, CI/CD agents, or third‑party services, and can be granted via the dashboard or scoped API tokens.
Meta open‑sourced Rebalancer, a library that lets engineers describe assignment problems (objects → bins) via a high‑level spec API, then solves them with either a MIP backend or a highly parallel local‑search engine. It handles millions of objects, solves ~40 M problems daily, and includes a debugging UI.
Simon Willison shows a minimal JavaScript UI that talks to Google’s Gemini 3.8 Live speech‑to‑speech models via a WebSocket API, using the Web Audio API for capture/playback and no external libraries.
Vercel AI Gateway now offers OpenAI’s GPT‑Live 1, a full‑duplex voice model that can listen and speak simultaneously. The SDK lets you start a voice session and optionally delegate work to any text model, with code examples for both patterns.
The GitHub Copilot SDK enables developers to embed Copilot's agent runtime into custom applications, demonstrated by an interview coach app. This allows applications to define agents with specific instructions and custom tools, leveraging Copilot for model interaction and tool execution.
AWS announced a new “project” onboarding flow that lets new users start building with default configurations, free credits, and simplified IAM handling. Sign‑in via Google/GitHub/Apple creates an isolated AWS account, auto‑provisions a CLI/agent toolkit, and lets you invite collaborators by email. Spend limits can be set per project, and advanced features (multi‑region, org policies) can be enabl…
This tutorial demonstrates building an event-driven lead scoring pipeline using Node.js and PostgreSQL. It focuses on robust design patterns like idempotency, secure webhook processing, and transactional consistency with a transactional outbox.
Dropbox’s Riviera platform has been expanded from a preview service into a universal, composable content‑processing system that now handles hundreds of thousands of transformations per second across 300+ file types. The architecture separates orchestration from execution, adds a plugin model, and offers async public APIs so internal and external AI workloads can reuse cached transformations.
Zapier’s Ben Lyso reviews six conversational‑AI platforms (Fin, Voiceflow, Google Conversational Agents, Decagon, Kore.ai, Cognigy) on criteria like custom agent building, conversation quality, channel coverage, and integration depth, noting pros/cons, pricing, and deployment nuances.
A vendor‑agnostic JSON Schema manifest for AI agent tools, with a TypeScript adapter layer that compiles the manifest into OpenAI function‑calling and Anthropic Claude formats, plus runtime validation, permission scoping, and execution constraints.
CodeName One introduces a new com.codename1.security.vault API to simplify secure, cross-device data encryption and access for mobile and web applications. It manages key derivation, wrapping, and synchronization without exposing the data key to the sync server.
Codename One introduces a backend runtime allowing a single Java model to define entities and validation rules for both client applications and the server. This approach aims to reduce duplication and ensure consistent data rules from the app to PostgreSQL.
This article distinguishes between serialization (preventing concurrent access) and arbitration (permitting access and rejecting losers) in distributed concurrency control. It argues that arbitration should be responsible for correctness, as serialization guarantees are conditional and can fail silently in multi-process environments, leading to data corruption.
A step‑by‑step guide for turning support tickets into well‑structured GitHub issues. It defines escalation criteria, outlines a decision table for support, specifies required fields, and provides a minimal Node.js 24 adapter that validates input, builds a markdown issue body, and calls the GitHub Issues API with proper error handling and security considerations.
AndroidX Security State (v1.1.0) and Security State Provider (v1.0.0) expose per‑component security patch levels (DSPL, PSPL, ASPL) for system, system modules, and kernel, letting apps and MDMs make context‑aware decisions and letting OEMs publish update availability via a standardized IPC.
Codename One replaced its Javadoc‑generated site with a Hugo‑based pipeline: a custom doclet emits one Hugo content file per Java type, preserving Markdown comments, generating a lightweight search index, and keeping the traditional offline Javadoc archive. The approach reduces index size (1.9 MB → 341 KB gzipped), retains existing anchors, and can be reused for other Java projects.
Vercel AI Gateway now offers the GLM‑5.3‑FlashX model, a fast (~200 tps) multimodal coding LLM. The post includes a TypeScript streaming example, notes the model’s fit for coding agents and interactive tools, and lists AI Gateway features (unified API, usage tracking, retries/failover, custom reporting, key budgets, routing rules) with no platform fee.
Step‑by‑step tutorial showing how to build a stateless composite Model Context Protocol (MCP) gateway in TypeScript using Hono, Zod, and the MCP SDK. It covers config‑driven upstream registration, namespaced tool discovery, JSON‑RPC routing, per‑tool auth middleware, and a token‑bucket rate limiter, with concrete code snippets and design trade‑offs.
Datasette 1.0a40 adds a background‑task API (datasette.add_background_task()), switches the internal HTTP client to httpx2, and ships a batch of bug fixes aimed at stabilising the upcoming 1.0 release. The security fix mirrors that of 0.65.5.
Laravel MCP 1.0 ships with the 2026-07-28 protocol, adding searchable tool catalogs, cache hints, stateless request handling, and PKCE‑required OAuth with client‑metadata support. The release includes migration guidance and new headers for versioned RPC calls.
