behnamoh

@[email protected]
0 Followers
0 Following
3 Posts

This account is a replica from Hacker News. Its author can't see your replies. If you find this service useful, please consider supporting us via our Patreon.
Officialhttps://
Support this servicehttps://www.patreon.com/birddotmakeup
behnamohJan 31

Swift is a more convenient Rust (2023)

https://nmn.sh/blog/2023-10-02-swift-is-the-more-convenient-rust

Swift is a more convenient Rust

From the Archive: Thoughts on Swift, while learning Rust

behnamohOct 5

Is there any work on reverse engineering LLMs, especially the closed source API ones? For example, how can we learn about the data used in Claude Sonnet 4.5 training?

And more tricky but as important, is there any work on extrapolating the pretrained model AFTER it's RLHF'd? For example, what kinds of biases did exist in gpt-4o before it was unbiased?

Do biases go away completely or they just get suppressed down deep in the model's "mind"?

behnamohMay 3, 2025

Run LLMs on Apple Neural Engine (ANE)

https://github.com/Anemll/Anemll

GitHub - Anemll/Anemll: Artificial Neural Engine Machine Learning Library

Artificial Neural Engine Machine Learning Library. Contribute to Anemll/Anemll development by creating an account on GitHub.

GitHub