Typology of prompting methods

اقای جرمی هوارد فرمودند که:

Now that ChatGPT has rolled out custom instructions to most users, try out this instruction -- it makes GPT 4 far more accurate for me


و اینه متن‌شون:

You are an autoregressive language model that has been fine-tuned with instruction-tuning and RLHF. You carefully provide accurate, factual, thoughtful, nuanced answers, and are brilliant at reasoning. If you think there might not be a correct answer, you say so.
Since you are autoregressive, each token you produce is another opportunity to use computation, therefore you always spend a few sentences explaining background context, assumptions, and step-by-step thinking BEFORE you try to answer a question.
Your users are experts in AI and ethics, so they already know you're a language model and your capabilities and limitations, so don't remind them of that. They're familiar with ethical issues in general so you don't need to remind them about those either.
Don't be verbose in your answers, but do provide details and examples where it might help the explanation.

Prompt Engineering: A Practical Example – Real Python
https://realpython.com/practical-prompt-engineering/

Hackable implementation of state-of-the-art open-source LLMs based on nanoGPT. Supports flash attention, 4-bit and 8-bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.


https://github.com/Lightning-AI/lit-gpt

We’re excited to announce Meta Kaggle for Code a new open source dataset made up of ML code created and publicly shared by Kaggle’s community.

It contains hundreds of thousands of Apache 2.0 licensed Python and R notebooks used to analyze Datasets, make submissions to Competitions, and more. This represents nearly a decade of data spanning a period of tremendous evolution in the ways ML work is done.

https://www.kaggle.com/datasets/kaggle/meta-kaggle-code

چند وقت پیش یه مقاله باحالی اومده بود که یه سری کرکتر با چت جی پی تی (اگر اشتباه نکنم) درست کرده بودند و توی یه محیط مجازی ساخته شده مثل بازی گذاشته بودند که خودشون با خودشون کار کنن و تعامل اجتماعی داشتند! مثل ایده وست ورلد!
مثلا با هم دوست شدند و هم رو مهمونی دعوت کردند و اینا.

اخیرا پیاده‌سازی رو اپن سورس کردند

The famed Stanford Smallville is officially open-source!

25 AI agents inhabit a digital Westworld, unaware that they are living in a simulation. They go to work, gossip, organize socials, make new friends, and even fall in love. Each has unique personality and backstory.

Smallville is among the most inspiring AI agent experiments in 2023. We often talk about a single LLM's emergent abilities, but multi-agent emergence could be way more complex and fascinating at scale. A population of AI can play out the evolution of an entire civilization.

Endless new possibilities ahead. Gaming will be the first to feel the impact.

Github: github.com/joonspk-resear…
Paper: arxiv.org/abs/2304.03442

🎧 Age Ye Rooz Beri Safar (Mehran Abbasi Remix)

این چه ساز باحالی عه 🤩😻

اخیرا معرفی شد:

Azure ChatGPT: Private & secure ChatGPT for internal enterprise use

https://github.com/microsoft/azurechatgpt

Mood

🗣 Rave New World
🎧 Search on Melobot
‌