» Tag
ai
1019 postsBenchmarking a Markdown Knowledge Graph as AI Agent Memory
IWE tested markdown knowledge graphs as AI agent memory using the LOCOMO benchmark, reaching 96% of a hand-built ceiling with a cheap curator model.
n8n's real bet: closing the AI agent prototype-to-production gap
n8n's strength isn't its visual canvas but how model flexibility, human approvals, observability and self-hosting make AI agents production-ready.
MiniMax M2.7: Open-Source AI That Optimized Its Own Training
MiniMax's open-source M2.7 model actively shaped its own training via memory writes and skill-building, gaining 30% efficiency and matching GPT-5.3-Codex on SWE-bench Pro.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comInstagui turns any CLI tool into a web GUI instantly
Instagui runs via npx and parses a CLI's --help output with AI to auto-generate a local web form, letting you run tools like ffmpeg without memorizing flags.
Claude's Weights Are Closed, So a Live Thought Viewer for Qwen
Inspired by Anthropic's workspace paper, a developer built a live, token-level inner-thought viewer for the open Qwen model since Claude's weights are closed.
When AI Reviewers Disagree: A Multi-Agent Code Review Tribunal
ShiftLeft Society pits two AI reviewers against each other in a cost-based negotiation, using Qwen-Max to cut false positives and raise accuracy from 82.5% to 95%.
Emboss: A Python PDF Engine That Keeps Documents as Structured Data
Emboss is a pure-Python PDF engine delivering deterministic, PDF/UA-accessible output with embedded table data and native MCP/AI integration.
ExploitGym: A Benchmark for AI-Driven Exploit Development
ExploitGym is an open-source AI benchmark with 869 real-world exploit tasks spanning userspace software, V8, and the Linux kernel.
SAGA Framework Pinpoints Which AI Model Generated a Video
SAGA is a new framework that attributes AI-generated videos to their source model across five levels, using minimal labeled data and interpretable signatures.
AI, Rockets, and Why Engineering Judgment Still Costs the Same
AI cheapens code generation, not engineering judgment. A rocket-engineering analogy — Apollo vs. the Soviet N1 — reframes how teams should review AI code.