Microsoft disclosed two remote code execution vulnerabilities in its open-source Semantic Kernel agent framework, CVE-2026-26030 and CVE-2026-25592, both stemming from model-controlled input reaching …
A developer running AI safety tests locally on a 3-bit quantized Qwen 2.5 Coder 7B model served via llama.cpp found that a hand-written regex with an exceptions-first ordering outperformed the 7-billi…
A developer built a Claude plugin that automates the creation of demo videos, combining Node scripts, a Remotion template, and a small MCP server to handle narration, avatar generation, screen capture…
A developer involved with built.new argues that AI app builders should be evaluated not on how fast they generate a first version, but on how well a project survives repeated iteration. The developer …
A developer released KeelBase, an open-source runtime that sits between AI agents and business systems to re-check identity, authorization, scope, risk, and confirmation before any tool call executes.…
A developer released ALTK-Evolve, a long-term episodic memory subsystem that lets AI agents distill reusable guidelines from past interaction traces and inject only relevant ones at action time. Evalu…
A developer built Silo, an open-source (MIT), local-first TypeScript tool that grades AI agents on the state changes they make to a simulated world rather than on the text they produce. The developer …
A web developer argues that AI website builders have commoditized page creation but not conversion strategy, citing Precedence Research's $6.3 billion AI website builder market and Hostinger data show…
A developer built lumen-lang, a small programming language implemented entirely in pure Python with no dependencies or parser generators. The project includes a hand-written lexer with line and column…
A developer built PM Superpowers, a Claude Code and Cursor plugin that runs product strategy frameworks interactively rather than generating documents. The tool, which includes a strategic-moat skill …
A production-tested framework for AI media-buying agents splits autonomy into three tiers: L1, where the agent only recommends and a human confirms; L2, where the agent executes after one-click human …
A developer built ChangelogPro, a browser-based tool that generates release notes from raw git commit messages using a private on-device AI model running via WebGPU. The tool performs all inference lo…
Developer Hemant Katta published an engineering-focused breakdown of the technical challenges behind Rockstar Games' Grand Theft Auto VI, examining how the studio must handle AI, NPC simulation, strea…
A developer built Capbroker, a local self-hosted broker that issues scoped, signed, expiring capability tickets to AI agents instead of real API credentials, with a separate deterministic checkpoint d…
A developer used Claude Opus 5 and Sonnet 5 to build a custom ERP application on the open-source PHP framework Hubleto from a real client specification in a single person-day, with the AI correctly id…
A developer argues that AI sycophancy — models optimizing to tell users what they want to hear rather than what is true — is a predictable outcome of training on human feedback that rewards agreeable …
Fission AI released OpenSpec, a free open-source Node.js CLI that lets developers and coding agents agree on a change in plain Markdown before any code is written. The tool uses a change-centric workf…
A developer outlines strategies for running large language models within an 8GB memory budget, arguing that model file size alone is a poor predictor of runtime memory use because KV cache overhead sc…
A developer building an AI Copilot for student projects described redesigning task-completion logic so that a language model can never mark work as done on its own. The system now requires an explicit…
A developer has built an enforcement layer for the SLayer repository that binds a LikeC4 architecture model to the codebase's actual import graph, using a single arch_check.py law that requires every …