I think it's because too many people have released tools that's clearly not ready for production because they don't know what to actually check. So it's now just easier to pattern match away any good tools that might surface.

jflynt76

Submissions

A Deterministic Replacement for LLM-as-Judge in Stateful Agent Evaluation

Multi-Agent Simulation Framework for Verifiable Synthetic Corporate Corpora

What happens when OKF runs inside an AI tool

Why most AI evals would miss the Linear sales email failure

Two AI judges scored our agent's answer 0.85, but it never opened the file

AI Governance Cannot Be a Tool Call

AI Memory Is Still Thinking Like Search

Show HN: Synthetic corporate dataset generator for AI agent evaluation

Why MCP is the wrong abstraction for memory

Show HN: Tenure – Traceable AI memory with configurable memory modes

You Don't Need a GitHub Copilot Subscription to Use VS Code AI Features

AI Memory Proves Inefficient: Tenure Project Detects 95% Error Rate

[untitled]

[untitled]

[untitled]

comments