Hadi Curtay

3x Entrepreneur. Founder @fitnessforceapp Bootstrapping a global vertical SaaS. Interests: AI/ML, scaling businesses and building products.

[Hadi Curtay @hadicurtay]

@calcsam Book

[Hadi Curtay @hadicurtay]

@rsg @trysunflower Some onboarding on this would have been fantastic. I am just upset I didn't tinker with it sooner!

[Hadi Curtay @hadicurtay]

How did I not know about this powerful feature? This is how it should be ! @trysunflower

[Hadi Curtay @hadicurtay]

@trysunflower I've made @trysunflower my primary and removed Gmail from homescreen. Let's see how that goes 😀🤞🏼

[Hadi Curtay @hadicurtay]

@petergyang Put our meeting (internal or client demos) transcripts through clause code to generate new or modify existin help documentation and then step 2 write those doc's.
Have a template that it follows and uses sub-agents.
Site going to go live soon.

[Hadi Curtay @hadicurtay]

@sama need Gmail plugin for ChatGPT. I'm tired of copy pasting.

[Hadi Curtay @hadicurtay]

Two of my favourite things in a single image.

Generated with @bfl_ml

[Hadi Curtay @hadicurtay]

@alexalbert__ My use: "Anthropic Prompt Generator"

I converted Anthropic's prompt guidelines to PDF & uploaded them.

My instructions includes Claude asking me for incomplete information and only after it has everything should it generate the prompt.

I then start a new chat with the prompt.

[Roshan Patel @roshanpateI]

indian engineers are a different breed

[Hadi Curtay @hadicurtay]

https://t.co/lLpyPr3Af6

[Hadi Curtay @hadicurtay]

I'm not afraid to admit I'm a lazy man. So I explore hacks to reduce effort & make my life easier.

[Hadi Curtay @hadicurtay]

If you would like my custom instructions & documentation pdfs in order to upload them on your own platform, let me know in comments and I'll send them over DM to you.

[Hadi Curtay @hadicurtay]

@Vapi_AI

[Hadi Curtay @hadicurtay]

Got to give the devil it's dues. Meta leading the open-source LLM story @AIatMeta

[Vaibhav (VB) Srivastav @reach_vb]

Meta Llama 3.1 405B, 70B & 8B are here - Multilingual & with 128K context & Tool-use + agents! Competitive/ beats GPT4o & Claude Sonnet 3.5 unequivocally the best open LLM out there!🐐

Bonus: It comes with a more permissive license, which allows one to train other LLMs on its high-quality outputs 🔥

Some important facts:

> Multilingual - English, French, German, Hindi, Italian, Portuguese, Spanish, and Thai.
> MMLU - 405B (85.2), 70B (79.3) & 8B (66.7)
> Trained on 15 Trillion tokens + 25M synthetically generated outputs.
> Pre-training cut-off date of December 2023
> Same architecture as Llama 3 with GQA
> Used a massive 39.3 Million GPU hours (16K H100s for 405B)
> 128K context ⚡
> Excels at Code output tasks, too!
> Release Prompt Guard - BERT-based classifier to detect jailbreaks, malicious code, etc
> Llama Guard 8B w/ 128K context for securing prompts across a series of topics

How much GPU VRAM do you need to run these?

405B - 810 GB in fp/bf16, 405 GB in fp8/ int8, 203 GB in int4
70B - 140 GB in fp/bf16, 70 GB in fp8/ int8, 35 GB in int4
8B - 16 GB in fp/bf16, 8 GB in fp8/ int8 & 4 GB in int4

In addition, we provide a series of Quants ready to deploy: AWQ, Bitsandbytes, and GPTQ. These allow you to run 405B in as little as 4 x A100 (80GB) through TGI or VLLM. 🚀

Wait, it improves; we also provide unlimited access to HF Pro users via our deployed Inference Endpoint!

Want to learn more? We wrote a detailed blog post on it 🦙

Kudos to @AIatMeta for believing in open source and science! It has been fun collaborating! 🤗

[AI at Meta @AIatMeta]

Starting today, open source is leading the way. Introducing Llama 3.1: Our most capable models yet.

Today we’re releasing a collection of new Llama 3.1 models including our long awaited 405B. These models deliver improved reasoning capabilities, a larger 128K token context window and improved support for 8 languages among other improvements. Llama 3.1 405B rivals leading closed source models on state-of-the-art capabilities across a range of tasks in general knowledge, steerability, math, tool use and multilingual translation.

The models are available to download now directly from Meta or @huggingface. With today’s release the ecosystem is also ready to go with 25+ partners rolling out our latest models — including @awscloud, @nvidia, @databricks, @groqinc, @dell, @azure and @googlecloud ready on day one.

More details in the full announcement ➡️ https://t.co/hhJoLm5eLV
Download Llama 3.1 models ➡️ https://t.co/rRjvmxqCTC

With these releases we’re setting the stage for unprecedented new opportunities and we can’t wait to see the innovation our newest models will unlock across all levels of the AI community.

[Hadi Curtay @hadicurtay]

Also, never release on Friday.

[Hadi Curtay @hadicurtay]

This whole mess just proves that no matter who you are, you gotta test thoroughly and roll out carefully.

#crowdstrike #bsod #windows

[Hadi Curtay @hadicurtay]

Sorry ChatGPT, I just switched to Claude.

[Jeremy Howard @jeremyphoward]

Today @AnthropicAI launched Claude Sonnet 3.5, the most powerful language model in the world.

And today, we're making it even better, launching Claudette--Claude's BFF!

Claudette makes Claude's awesome features easier & more powerful for Pythonistas.🧵
https://t.co/eAiiZ6qjV8