Fraser Miller @FraserM_AI

Joined February 2023

Tweets

6
Followers

19
Following

47
Likes

0

Xavier Villarroel @XavierTrilogy

2 years ago

Chat With RTX is a demo app that lets you personalize a GPT large language model (LLM) connected to your own content—docs, notes, videos, or other data. Leveraging retrieval-augmented generation (RAG), TensorRT-LLM, and RTX acceleration, you can query a custom chatbot to quickly…

0 1 1 159 0

Joanne Jang @joannejang

2 years ago

📝 we just launched a small experiment for memory on ChatGPT. how it works - it's quite similar to custom instructions, except chatgpt is the one driving it (like auto vs. stick shift!) - basically, we taught chatgpt to keep a notepad for itself. every time you share information…

OpenAI @OpenAI

2 years ago

512 971 6K 2.1M 791

Download Gif

53 88 705 189K 284

Ethan Mollick @emollick

2 years ago

People make writing prompts very hard, assuming you need all sorts of special prompts and formatting. But look at the (apparent) system prompt written by OpenAI for how ChatGPT should generate images - just straight up prose instructions like to a human, no fancy tricks at all.

31 106 735 115K 621

Download Image

anton @abacaj

2 years ago

Searching google and stackoverflow -> 30-45 minute rabbit hole Asking chatgpt -> 2minute tailored answer This is what they mean when they say "productivity" boost

46 47 873 88K 58

OpenAI @OpenAI

2 years ago

You can now bring GPTs into any conversation in ChatGPT - simply type @ and select the GPT. This allows you to add relevant GPTs with the full context of the conversation.

287 639 4K 614K 492

Download Gif

Bindu Reddy @bindureddy

2 years ago

Corrected Retrieval Augmented Generation One of the biggest problems with RAG is that the retrieval step can often go wrong. The reason is that, given a query, it depends heavily on the relevance of the docs in the local corpus. Corrective Retrieval Augmented Generation…