DeepSeek: X2 Speed for WASM with SIMD

1. llama.cpp

   1 1,066 123,686 10.0 C++

   LLM inference in C/C++

   

   > I hope we can put to rest the argument that LLMs are only marginally useful in coding - which are often among the top comments on many threads. I suppose these arguments arise from (a) having used only GH copilot which is the worst tool, or (b) not having spent enough time with the tool/llm, or (c) apprehension. I've given up responding to these.

   Look at the code that was changed[0]. It's a single file. From what I can tell, it's almost purely functional with clearly specified inputs and outputs. There's no need to implement half the code, realize the requirements weren't specified properly, and go back and have a conversation with the PM about it. Which is, you know, what developers actually do.

   This is the kind of stuff LLMs are great at, but it's not representative of a typical change request by Java Developer #1753 at Fortune 500 Enterprise Company #271.

   [0] https://github.com/ggerganov/llama.cpp/pull/11453/files

2. SaaSHub

   www.saashub.com featured

   SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives

   

3. hn-search

   2 2,423 614 2.9 TypeScript

   Discontinued Hacker News Search

   

   You can't post like this here, no matter how wrong someone else is or you feel they are. We ban accounts that do, so if you'd please review https://news.ycombinator.com/newsguidelines.html and stick to the rules, we'd appreciate it.

   "Please don't post insinuations about astroturfing, shilling, bots, brigading, foreign agents and the like. It degrades discussion and is usually mistaken. If you're worried about abuse, email hn@ycombinator.com and we'll look at the data."

   https://news.ycombinator.com/newsguidelines.html

   https://hn.algolia.com/?sort=byDate&dateRange=all&type=comme...

4. clap-config-file

   3 1 12 5.5 Rust

   A proc macro for adding config file support to clap

   

   I am subscribed to o1 Pro and am working on a little Rust crate.

   I asked both o1 Pro and Deepseek R1 to write e2e tests given all of the code in the repo (using yek[1]).

   o1 Pro code: https://github.com/bodo-run/clap-config-file/pull/3

   Deepseek R1: https://github.com/bodo-run/clap-config-file/pull/4

   My judgement is that Deepseek wrote better tests. This repo is small enough for making a judgement by reviewing the code.

   Neither pass tests.

   [1] https://github.com/bodo-run/yek

5. yek

   4 11 2,470 8.1 Rust

   A fast Rust based tool to serialize text-based files in a repository or directory for LLM consumption

   

   Yes! I've done something like this here[1] This was nice while lasted (Deepseek is practically useless through the API since yesterday)

   https://github.com/bodo-run/yek/blob/main/.github/workflows/...

6. DeepSeek-R1

   5 31 91,987 7.0

   

   DeepSeek published a bunch of benchmarks when they released the models: https://github.com/deepseek-ai/DeepSeek-R1?tab=readme-ov-fil...

   I'd like to see detailed benchmarks run by other unaffiliated organizations.

7. duopoly

   6 1 6 4.4 Python

   An experiment in AI collaboration

   

   When GPT-4 came out, I worked on a project called Duopoly [1], which was a coding bot that aimed to develop itself as much as possible.

   The first commit was half a page of code that read itself in, asked the user what change they'd like to make, sent that to GPT-4, and overwrote itself with the result. The second commit was GPT-4 adding docstrings and type hints.

   Over 80% of the code was written by AI in this manner, and at some point, I pulled the plug and decided to develop it entirely without human written code, and the last couple hundred commits were entirely written by AI.

   It was a huge pain to develop with how slow and expensive and flaky the GPT-4 API was at the time. There was a lot of dancing around the tiny 8k context window. After spending thousands in GPT-4 credits, I decided to mark it as proof of concept complete and move on developing other tech with LLMs.

   Today, with Sonnet and R1, I don't even think it would be difficult or expensive to bootstrap the thing entirely with AI, never writing a line of code. Aider, a fantastic similar tool written by HN user anotherpaulg, wasn't writing large amounts of its own code in the GPT-4 days. But today it's above 80% in some releases [2].

   Even if the models froze to what we have today, I don't think we've scratched the surface on what sophisticated tooling could get out of them.

   [1]: https://github.com/reitzensteinm/duopoly

8. bevy

   7 606 47,508 10.0 Rust

   A refreshingly simple data-driven game engine built in Rust

   

   Here, give it a shot - I'm at work so I can't try again right now, but last I did was use claude+context, chatGPT 4o with just chatting, Copilot in Neovim, and Aider w/ claude + uploading all the files as context.

   I even went so far as to grab relevant examples from https://github.com/bevyengine/bevy/tree/latest/examples#exam... , adding relevant ones as I saw fit.

   It took a long time to get anything that would compile, way longer than just reading + doing, and it was eventually wrong anyway. This is a recurring issue with Rust, and I'd love a workaround since I spend 60+h/week writing it. Probably a skill issue.

   https://gist.github.com/jodavaho/8fb042fab33c1aaa95cd67144da...

9. duckduckgo-locales

   8 2,399 113 9.9 Perl

   Translation files for <a href="https://duckduckgo.com"> </a>

   

   Possibly because Claude knows these are not in short supply by any means and its capabilities can be put to better use.

   https://duckduckgo.com/?t=ftsa&q=hitler&iax=images&ia=images

10. aider

    9 165 48,063 9.4 Python

    aider is AI pair programming in your terminal

    

Suggest a related project