YTC

Developing AI

[YTC @yutaoc137]

@thsottiaux @NickADobos Hit the button one last time, I promise🥺

[YTC @yutaoc137]

@thsottiaux We all do!!!!!

[YTC @yutaoc137]

@thsottiaux What about paid codex users🥺

[YTC @yutaoc137]

@thsottiaux Rest so I can talk to it too

[YTC @yutaoc137]

@thsottiaux Resettttttttttt

[YTC @yutaoc137]

@thsottiaux Reset and let me finish my loop please

[YTC @yutaoc137]

@thsottiaux Please reset boss

[YTC @yutaoc137]

@gray_yafeng @antigravity @jigyasa_grover Less than 5 mins task

[YTC @yutaoc137]

@gray_yafeng @antigravity @jigyasa_grover Same for me. Reseted yesterday, did 1 task today and reached limit

[YTC @yutaoc137]

Yap early, yap only, yap often.

@KaitoAI is connecting AI, attention and capital with Yaps.

Just claimed my social card and I'm accumulating Yap points in real-time.

Claim yours 👉 https://t.co/zd7XrGhZwO

[Turing Post @TheTuringPost]

CS109A Data Science course materials @Harvard are free and open to everyone!

1. Lecture notes
2. R code, Python notebooks
3. Lab material
4. Advanced sections

Learn here: https://t.co/CriMdwEkCD

[Mayo Oshin @mayowaoshin]

4 simple ways to reduce the cost of using GPT-4 by up to 98% (and improve accuracy at the same time).

1. Combine prompts: Join two or more queries to make a single API call instead of multiple separate calls.
2. Prompt selection: Decrease prompt size by selecting a small optimal subset of examples for the LLM.
3. Caching: Store and reuse the LLM’s response when a similar query is asked.
4. LLM Cascading: First send the API request to a smaller model, then move onto a larger model (i.e. GPT-4) only if results are insufficient.

"Our experiments show that FrugalGPT can save up to 98% of the inference cost of the best individual LLM API while matching its performance on the downstream task. On the other hand, FrugalGPT can improve the performance by up to 4% with the same cost."
- authors: @james_y_zou, @matei_zaharia

paper: https://t.co/EiAetTlRkv

[James Briggs @jamescalam]

I built a ChatGPT @Lex_Fridman plugin that allows to chat with the collective wisdom contained across 499 of Lex's podcasts and videos... Here's how I built it 🧵

#ChatGPT #ArtificialIntelligence #nlproc #OPStack

[Naval @naval]

Beggars build on APIs, sovereigns build on open source.

[Naval @naval]

You lead by being willing to walk alone.

[Naval @naval]

Be wary of anything that starts with the word “social.”

[Naval @naval]

The problem with genius is that you have to tolerate madness.

[Naval @naval]

You can’t buy a real kiss.

[Naval @naval]

Clear thinkers take feedback from reality, not society.

[Naval @naval]

Demystifying NFTs:

(A thread)