Full-text search across 68501 articles. Combine with topic and date filters; results sorted by relevance.
A developer built Terminal Is Your Friend, an open-source JavaScript/TypeScript playground that runs code in a dark terminal with a sandboxed runtime and an AI instructor that explains errors and results rather than writ…
A developer describes a three-part approach to testing LLM features that cannot be verified with string equality: a version-controlled golden set of real inputs, deterministic property assertions that run before any LLM-…
A developer published a guide to voice AI security and privacy, cataloging common attack vectors including voice-based phishing (vishing), replay attacks, unencrypted audio storage, and model inversion against TTS system…
SpaceX's reported all-stock acquisition of Anysphere, the maker of Cursor, at $60 billion values a coding product whose real asset is the per-turn policy — what the model sees, which tools it can reach, and what counts a…
A voice agent named Alex negotiates freight rates over the phone using a pipeline of six small models built on LiveKit Agents, an open source framework, rather than a speech-to-speech model, because every price it speaks…
A developer designed OASIS (Opinionated Architecture for Secure Isolated SaaS), a Go and Nuxt 3 framework that enforces multi-tenant data isolation structurally rather than through developer discipline. The system inject…
Chatim, a live chat and AI chatbot widget provider, detailed the engineering constraints behind its embeddable website widget, including a defensive install snippet, a command queue modeled on Google Analytics' dataLayer…
Developer galeone released vim-pi-chat, a Vim 9 plugin that embeds the pi coding agent in a chat window by spawning `pi --mode rpc` as a background job over a strict JSON-lines protocol. The plugin requires Vim 9.0+ comp…
Supabase announced new agent-facing tools at Supabase Select, including a query_logs MCP tool that gives coding agents raw SQL access to project logs, expanded Advisor health checks across Data API, Auth, Storage and Edg…
A benchmark on a 120,000-listing Indian AgriTech mandi dataset compared legacy pre-filtering, legacy post-filtering, and Qdrant's single-stage in-index filtering across four filter-selectivity levels, 60 queries per scen…
Manny Singh released LLMario v0.2.0, a free Apache-2.0 open-source desktop app that runs open models such as Qwen, Gemma, Llama and gpt-oss locally on macOS 13+ (Apple Silicon and Intel) and Windows 10/11 x64 in preview.…
A developer published funcroute, a roughly 4,000-line C router that sits between a client and model vendors and routes each request to a specialist upstream based on its attachments, letting a cheap text-only model handl…
A developer outlines a multi-model invoice extraction architecture that routes OpenAI, Claude, and Gemini through a single normalized OpenAI-compatible chat API, keeping provider selection in configuration rather than ap…
A developer's source-code review of QuantDinger's optional Jev AI trade filter (commit 96cec2d) found the gate fails open: when the LLM's confidence on key questions falls below 0.55 it defers to an uncalibrated fallback…
The Dutch Institute for Vulnerability Disclosure (DIVD) disclosed that attackers exploited two zero-day flaws in its Zammad support platform on September 21 to hijack sessions, run remote code as the local zammad user, a…
Cognition AI Inc. is running always-on training for its Devin coding agent, with head of research Silas Alberti saying the company targets 99.99% reliability because a single failed replica can take down an entire distri…
Leapwork launched Leapwork Play, an AI-native continuous validation platform for building, running and managing Playwright test suites at scale, available today with a free tier and self-service sign-up. Leapwork VP of D…
Andrej Karpathy published an "idea file" gist, llm-wiki.md, describing a pattern in which an AI agent writes and maintains a linked markdown knowledge base from user-supplied sources, compiling synthesis at ingest time r…
John Nunemaker told the YAGNI podcast that after starting a 20x Claude plan on December 14 to try Opus, he rewrote about 80% of Fireside's infrastructure in three days while driving a camper six hours a day, replacing ou…
Fin's 2x Team published a set of context-management practices for Claude Code sessions, arguing that keeping starting context small and pruning stale memory directly lowers token costs and improves output quality. The te…