Story Published at: June 12, 2023 at 08:10PM
Earth’s rotation, with the camera locked to the sky instead of the ground
MeZO: Fine-Tuning Language Models with Just Forward Passes
Story Published at: June 6, 2023 at 06:49PM
Ask HN: Do Americans write better software than the rest of the world?
I’ve seen a few example of software written by two independent groups—one in the US and one in Europe—which ended up giving drastically different user experience. For instance, Microsoft Guidance (written by two people) is a framework for working with large language models and upon my first try, it worked really well. I was able to generate controlled sequences of […]
OpenAI Employee: GPT-4 hasn’t gotten worse since March
Story Published at: June 1, 2023 at 07:27PM
Ask HN: Is it just me or GPT-4’s quality has significantly deteriorated lately?
It is much faster than before but the quality of its responses is more like a GPT-3.5++. It generates more buggy code, the answers have less depth and analysis to them, and overall it feels much worse than before. For a while, the GPT-4 on phind.com gave even better results than GPT-4-powered ChatGPT. I could notice the difference in speed […]
Having a 20GB file that lets you ask an offline computer any question is amazing
Story Published at: May 22, 2023 at 05:39AM
Counterintuitive Properties of High Dimensional Space
Story Published at: May 20, 2023 at 06:51AM
On the foolishness of “natural language programming”
Story Published at: May 16, 2023 at 10:42PM
LMQL: A query language for programming (large) language models
Story Published at: May 16, 2023 at 01:46AM
The Unreasonable Effectiveness of Character-Level Language Models
Story Published at: May 14, 2023 at 08:11PM