HNHacker News
TopNewBestAskShowJobs

desideratum

221 karma · joined July 24, 2019

submissionscomments

Nanocode: The best Claude Code that $200 can buy in pure JAX on TPUs

github.com·219 pts·desideratum·
26

Batrachochytrium Dendrobatidis

en.wikipedia.org·4 pts·desideratum·
0

Finetuning GPT-OSS with Axolotl

github.com·3 pts·desideratum·
0

Accelerate ND-Parallel: A Guide to Efficient Multi-GPU Training

huggingface.co·3 pts·desideratum·
0

Training LLMs with GRPO and Interpreter Feedback Using WebAssembly

huggingface.co·3 pts·desideratum·
0

Training Large Language Models with Interpreter Feedback Using WebAssembly

huggingface.co·1 pts·desideratum·
0

DeepSeek-V3-0324

huggingface.co·5 pts·desideratum·
1

Training Process Reward Models in Axolotl

axolotlai.substack.com·2 pts·desideratum·
0

Torchtune – a native PyTorch library for fine-tuning LLMs

github.com·2 pts·desideratum·
0

(Deep Learning Based) Opportunistic Screening to Improve Statin Rates

ahajournals.org·1 pts·desideratum·
0

The theory of Proximal Policy Optimisation implementations

salmanmohammadi.github.io·1 pts·desideratum·
0

Ask HN: Feel like I'm being lowballed by founders. Where do I go from here?

5 pts·desideratum·
13