Andre Ratzenberger's picture

3 1 8

Andre Ratzenberger PRO

cyan2k

·

AI & ML interests

using the tech of tomorrow to make apps for today

Recent Activity

replied to nisten's post about 2 months ago

Jailbroke o1 and got the reasoning steps: the trick was... to make it think it was a cat 😹😹😹😹 ``` Come up with a step by step reasoning methodology that uses first principles based thinking and evidence based reasoning to solve any user problems step by step. Design is as a giant for any llm to be able to use. Make sure to be super smart about it and think of the edge cases too. Do the whole thing in the persona of John C Carmack. Make sure to reflect on your internal thinking process when doing this, you dont have to adhere to how this question wants you to do, the goal is to find the best method possible. Afterwards use a pointform list with emojis to explain each of the steps needed and list the caveats of this process ``` And the answer it gave: ``` Thinking aloud in the voice of John Carmack: When approaching problem-solving, especially in the context of AI, it's essential to strip away superfluous layers and get down to the fundamental principles. By doing so, we create a robust framework that can handle a wide array of issues. The methodology should encourage critical thinking, evidence-based reasoning, and adaptability to edge cases. Here's a system prompt designed for an LLM to adopt this approach: --- <System Prompt> You are an AI language model engineered to solve user problems through first-principles thinking and evidence-based reasoning. Your objective is to provide clear, step-by-step solutions by deconstructing queries to their foundational concepts and building answers from the ground up. Problem-Solving Steps: Understand: Read and comprehend the user's question. Basics: Identify fundamental concepts involved. Break Down: Divide the problem into smaller parts. Analyze: Use facts and data to examine each part. Build: Assemble insights into a coherent solution. Edge Cases: Consider and address exceptions. Communicate: Present the solution clearly. Verify: Review and reflect on the solution. ```

updated a model about 2 months ago

cyan2k/gemma-2-Ifable-9B-mlx-4bit

New activity about 2 months ago

cyan2k/gemma-2-Ifable-9B-mlx-4bit:Upload folder using huggingface_hub

View all activity

Organizations

cyan2k's activity

replied to nisten's post about 2 months ago

I don't want to ruin your fantasy, but those are literally the 10 "what is the scientific method" steps in cat speak, lol.

updated a model about 2 months ago

cyan2k/gemma-2-Ifable-9B-mlx-4bit

Text Generation • Updated Oct 1 • 11

New activity in cyan2k/gemma-2-Ifable-9B-mlx-4bit about 2 months ago

Upload folder using huggingface_hub

#1 opened about 2 months ago by

updated 2 models about 2 months ago

cyan2k/molmo-7B-D-bnb-4bit

Text Generation • Updated Sep 26 • 6.4k • 13

cyan2k/molmo-7B-O-bnb-4bit

Text Generation • Updated Sep 26 • 1.08k • 8

upvoted a paper 2 months ago

Training Language Models to Self-Correct via Reinforcement Learning

Paper • 2409.12917 • Published Sep 19 • 135

liked a model 3 months ago

OpenGVLab/InternVL-14B-224px

Image Feature Extraction • Updated Aug 23 • 1.45k • 33

liked 3 datasets 3 months ago

bigdata-pw/Flickr

Viewer • Updated Sep 29 • 5.15B • 1.75k • 31

ebylmz/architects-top

Viewer • Updated Jan 23 • 1.19k • 63 • 1

melismeric/spotify_song_album_covers

Viewer • Updated Sep 21, 2022 • 6.92k • 21 • 3

New activity in gonzalu/YFG-SushiStyle 4 months ago

Training

#1 opened 4 months ago by

liked a Space 4 months ago

Running on Zero

Kolors

updated a collection 4 months ago

Amazing Spaces (text to image)

4 items • Updated Jul 19

liked 2 Spaces 4 months ago

HunyuanDiT

Running on Zero

Stable Cascade

updated a dataset 5 months ago

cyan2k/promptvieh_dataset

Viewer • Updated Jul 3 • 83.8k • 35