dobby_lee · HN

Open-Source for AI tool status checker

schafberg · HN

Is AI Dumber Today? An index of AI model experience from user's opinion

@andreasacca · X

Inspired by @robj3d3’s that went viral last week. Over the past year working with ecommerce brands I kept hearing: “I only use 10% of this SaaS and I’m paying hundreds for it.” So I built the Ecommerce focused version: 200+ tools analysed. Honest verdicts on what you can realistically vibecode. Vibecoded entirely with @Lovable + some fixes, starting from the prompt taken from First detailed analyses coming soon. Reply with the tool you pay for every month. Thanks @robj3d3 for the inspiration! Loving X

@Akinzoooo · X

@BobbySBX · X

We just dropped Assay v0.2.6, the open source evaluation engine powering Most registries judge an AI tool by its README. We built Assay to actually run skills, MCP servers, and plugins inside isolated sandboxes with live models to observe what they do before you install them. What is new in v0.2.6: - NVIDIA API Catalog provider: Native support is here, allowing you to use NVIDIA driver and judge models to run behavioral benchmarks and multi-tier audits. - Zero runtime dependencies: Still a self-contained ~240 KB tarball that speaks directly to @nvidia , @AnthropicAI , @OpenAI , @OpenRouter , and local HTTP endpoints without SDK bloat. - Adversarial and static checks: Out of the box verification against prompt injection, tool scope creep, destructive shell commands, and supply chain drift. Every tool on is tested through Assay. That means 4,200+ skills, MCP servers, and plugins are commit-pinned, graded on actual runtime behavior, and rea

ai world generator — 用文本和照片生成自然风光视频的 AI 工具网站

@orsik_sergey · X

@SpendLensAI · X

@supezen · X

😂我做了一个截然相反的产品，把「过程」留给 AI，把「结果」留给自己

davidtsong · HN

Benchmarklist: track AI benchmarks (2.4k+), models, and capabilities

@KalantariAria · X

A Discord/Slack alternative with a native AI Agent built in, it's called Waffle (@trywaffle_app).

@gabebenchimol · X