HNHacker News
TopNewBestAskShowJobs

jflynt76

9 karma · joined May 12, 2026

submissionscomments

AI Agent Safety Is Still Thinking Like Permissions

jeffreyflynt02.medium.com·5 pts·jflynt76·
0

A benchmark revealing an average memory-retrieval accuracy of 9%

zendoric.com·5 pts·jflynt76·
0

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

arxiv.org·4 pts·jflynt76·
0

Multi-Agent Simulation Framework for Verifiable Synthetic Corporate Corpora

arxiv.org·4 pts·jflynt76·
0

What happens when OKF runs inside an AI tool

tenureai.dev·5 pts·jflynt76·
0

Why most AI evals would miss the Linear sales email failure

tenureai.dev·6 pts·jflynt76·
2

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

tenureai.dev·6 pts·jflynt76·
0

AI Governance Cannot Be a Tool Call

tenureai.dev·5 pts·jflynt76·
0

AI Memory Is Still Thinking Like Search

medium.com·5 pts·jflynt76·
0

Show HN: Synthetic corporate dataset generator for AI agent evaluation

github.com·3 pts·jflynt76·
0

Why MCP is the wrong abstraction for memory

tenureai.dev·4 pts·jflynt76·
0

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

tenureai.dev·3 pts·jflynt76·
0

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

medium.com·5 pts·jflynt76·
1

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

zamin.uz·5 pts·jflynt76·
0