Viewing profile — sciences44

Nice work. Regarding your first insight, that's a sneaky one ^^. I experiment a similar issue with fine-tuning a small model with MLX. It was very hard to find out.

[dead]

I wanted to test the new Qwen 3.5 Small models (released March 2) for a structured output task. I fine-tuned the 0.8B, 2B and 4B on text-to-SQL using LoRA on a Mac (64 GB, MLX), an…

Interesting subject, thank you! I have a cluster of 2 Orange Pis (16 GB RAM each) plus a Raspberry Pi. I think it's high time to get them back on my desk. I never had time to get v…

Hey HN! Creator here. What is meshii? An orchestration layer for 3D mesh generation models (Trellis 1/2, PartPack). Built it because I'm working with a small game studio (Peakeey -…

Love the originality here - makes you curious to explore more. Solid technical execution too. Well done!

Interesting, thanks for the explanation! Good luck with the project.

Really interesting workflow, Addy! Two questions about your approach: 1. *Spec → Implementation process:* How do you ensure Claude actually completes everything in the spec and fin…

This is fascinating! I'm working on a problem using AI to accelerate game development workflows but never used it for playing. Curious how Claude handles the game logic constraints…