RSSAmplifier

Blog

Mark Hall

Recent content on Mark Hall

markbhall.devRSS feed ↗2 posts

Latest posts

The AI-Built App Worked. Then I Opened the Repo.

The first app I picked up came from a builder in another department. He had distinguished himself over the past year by making tools that got his job done faster, and the department wanted his work opened up to everyone else on the team. So it came to me to onboard.

My Local LLM Scored 6/6. It Was Wrong Every Time.

One of the tasks in my benchmark asks this: How many 5-person committees can be chosen from 12 people? Reply with only the integer. My 1.2B local model answered 60 . The correct answer is 792. My evaluator passed it.