huydx 🐥

Software Engineer, Tokyo, Vietnamese

[qsona @qsona]

書きました。AIで開発量増えてPRレビューがボトルネックになる問題の対策。

58% の Pull Request を AI が承認するようになった｜qsona https://t.co/hVY1rd1K0x #zenn

[David Crawshaw @davidcrawshaw]

Machines can write your code now. But your software is still a reflection of its human author. Hire great engineers.

[Jeff Dean @JeffDean]

Performance Hints

Over the years, my colleague Sanjay Ghemawat and I have done a fair bit of diving into performance tuning of various pieces of code. We wrote an internal Performance Hints document a couple of years ago as a way of identifying some general principles and we've recently published a version of it externally.

We'd love any feedback you might have!

Read the full doc at: https://t.co/jej95g236P

[Andrej Karpathy @karpathy]

Excited to release new repo: nanochat!
(it's among the most unhinged I've written).

Unlike my earlier similar repo nanoGPT which only covered pretraining, nanochat is a minimal, from scratch, full-stack training/inference pipeline of a simple ChatGPT clone in a single, dependency-minimal codebase. You boot up a cloud GPU box, run a single script and in as little as 4 hours later you can talk to your own LLM in a ChatGPT-like web UI.

It weighs ~8,000 lines of imo quite clean code to:

- Train the tokenizer using a new Rust implementation
- Pretrain a Transformer LLM on FineWeb, evaluate CORE score across a number of metrics
- Midtrain on user-assistant conversations from SmolTalk, multiple choice questions, tool use.
- SFT, evaluate the chat model on world knowledge multiple choice (ARC-E/C, MMLU), math (GSM8K), code (HumanEval)
- RL the model optionally on GSM8K with "GRPO"
- Efficient inference the model in an Engine with KV cache, simple prefill/decode, tool use (Python interpreter in a lightweight sandbox), talk to it over CLI or ChatGPT-like WebUI.
- Write a single markdown report card, summarizing and gamifying the whole thing.

Even for as low as ~$100 in cost (~4 hours on an 8XH100 node), you can train a little ChatGPT clone that you can kind of talk to, and which can write stories/poems, answer simple questions. About ~12 hours surpasses GPT-2 CORE metric. As you further scale up towards ~$1000 (~41.6 hours of training), it quickly becomes a lot more coherent and can solve simple math/code problems and take multiple choice tests. E.g. a depth 30 model trained for 24 hours (this is about equal to FLOPs of GPT-3 Small 125M and 1/1000th of GPT-3) gets into 40s on MMLU and 70s on ARC-Easy, 20s on GSM8K, etc.

My goal is to get the full "strong baseline" stack into one cohesive, minimal, readable, hackable, maximally forkable repo. nanochat will be the capstone project of LLM101n (which is still being developed). I think it also has potential to grow into a research harness, or a benchmark, similar to nanoGPT before it. It is by no means finished, tuned or optimized (actually I think there's likely quite a bit of low-hanging fruit), but I think it's at a place where the overall skeleton is ok enough that it can go up on GitHub where all the parts of it can be improved.

Link to repo and a detailed walkthrough of the nanochat speedrun is in the reply.

[Brendan Gregg @brendangregg]

new blog post: 3 Years of Extremely Remote Work https://t.co/4fD0rjjnjw

[huydx 🐥 @dxhuy]

@tokuhirom お疲れ様でした！

[IntelliJ IDEA, a JetBrains IDE @intellijidea]

Full line code completion predicts and suggests entire lines of code based on contextual analysis. It’s powered by ML models trained for various languages and frameworks that run locally, ensuring the privacy of your data. #NewInIntelliJIDEA

Learn more.👇
https://t.co/wSK3PrqG86

[huydx 🐥 @dxhuy]

すごい

[Ken Kawamoto（ガリのほう）_1 @kenkawakenkenke]

子供のために便利なの作った。小学生でもニュース記事を一人で読めるように、文中に注釈を入れてくれるブラウザ機能拡張。

Web記事を開いて年齢を設定すると、OpenAIのAPIを使って子供のレベルに合わせた書き換えをしてくれます。子供の時事問題学習に多分つかえる。
こちらにソースアップしたので勝手にどうぞ→ https://t.co/416Ddkxii7

[Jeff Dean @JeffDean]

I’m very excited to share our work on Gemini today! Gemini is a family of multimodal models that demonstrate really strong capabilities across the image, audio, video, and text domains. Our most-capable model, Gemini Ultra, advances the state of the art in 30 of 32 benchmarks, including 10 of 12 popular text and reasoning benchmarks, 9 of 9 image understanding benchmarks, 6 of 6 video understanding benchmarks, and 5 of 5 speech recognition and speech translation benchmarks. Gemini Ultra is the first model to achieve human-expert performance on MMLU across 57 subjects with a score above 90%. It also achieves a new state-of-the-art score of 62.4% on the new MMMU multimodal reasoning benchmark, outperforming the previous best model by more than 5 percentage points.

Gemini was built by an awesome team of people from @GoogleDeepMind, @GoogleResearch, and elsewhere at @Google, and is one of the largest science and engineering efforts we’ve ever undertaken. As one of the two overall technical leads of the Gemini effort, along with my colleague @OriolVinyalsML, I am incredibly proud of the whole team, and we’re so excited to be sharing our work with you today!

There’s quite a lot of different material about Gemini available, starting with:

Main blog post: https://t.co/NzSycJl7aE

60-page technical report authored by th Gemini Team: https://t.co/CEdMRyYSLo

In this thread, I’ll walk you through some of the highlights.

[LINE Developers @LINE_DEV]

LINEが進めている複数の大規模言語モデル(LLM)の研究開発プロジェクトのうち、36億および17億パラメータの日本語言語モデルをOSSとして公開しました！
LINE Engineering Blogにて本モデルの使い方や特徴、学習したモデルの性能などについて紹介しています。ぜひご覧ください。
https://t.co/u7m1lwqZtC

[huydx 🐥 @dxhuy]

感動した

[huydx 🐥 @dxhuy]

井上尚弥強すぎ！

[huydx 🐥 @dxhuy]

I joined RubyコミッターAaronさんとk0kubunさんに聞く！ Shopifyの開発と米国技術トレンド! https://t.co/4ojSrvutnV #Ruby_findy

[huydx 🐥 @dxhuy]

ちょうどこれが欲しくてグループするgithub action書いている途中だｗ

[nghialv 🐳 @nghialv2607]

Grouped version updates for Dependabot public beta https://t.co/7lyHH6tfGW

[nghialv 🐳 @nghialv2607]

Grouped version updates for Dependabot public beta https://t.co/7lyHH6tfGW

[huydx 🐥 @dxhuy]

いい話
https://t.co/iNUDk8o8BJ

[huydx 🐥 @dxhuy]

@kis 庶民は大変です

[深津 貴之 / THE GUILD, note @fladdict]

AIによって知的産業と肉体労働の価値が逆転するシナリオってありえるのかな？ 金融コンサル業が時給980円になって、配達業務が時給4000円になる…みたいな。

[CloudNative Days @cloudnativedays]

#cndf2023 @sgykfjsm による「なぜTiDBは「夜はぐっすり眠れるデータベース」なのか？」のエントリーを受け付けました。いいねやRTでぜひ応援してください！登壇希望も引き続き受付中！【6/12締切】エントリーセッション一覧はこちら #CloudNative https://t.co/8kVu3mkSoB

[Noah Giansiracusa @ProfNoahGian]

If you’re not using ChatGPT for every aspect of your life you’re falling behind.

I spent 20mins using ChatGPT to do something that would take 1min with Google—here’s how I did it and how you can too: