Urgent.News

What's breaking now, across thousands of outlets.

More in AI

How to build a tiny 1.5B text-to-SQL model that beats a 7B

I wanted to build something with an LLM using my own hands. Not wire an API into a wrapper, but take a base model, train it, measure it, break it, and serve it over HTTP. Why?

  • Author builds tiny 1.5B text-to-SQL model to outperform 7B model
  • Model achieves 44.6% accuracy with held-out evaluation, 49.7% with RL reward
  • 1.5B model still inferior to 7B but answers queries eight times to vote on most common result

I benchmarked 6 free AI text detectors so you don't have to

I got burned by a client who swore my original writeup was "AI-generated." It wasn't. But the accusation cost me a week of back-and-forth, so I did what any annoyed engineer does: I ran the detectors…

  • Six free AI text detectors tested for effectiveness
  • None reliably distinguished human from AI writing
  • Detectors measure surprise, not AI generation

More from Friday 4 September →