SmartGPT: Make ChatGPT Smarter

  Рет қаралды 10,234

Prompt Engineering

Prompt Engineering

Күн бұрын

Пікірлер: 29
@engineerprompt
@engineerprompt Жыл бұрын
Want to connect? 💼Consulting: calendly.com/engineerprompt/consulting-call 🦾 Discord: discord.com/invite/t4eYQRUcXB ☕ Buy me a Coffee: ko-fi.com/promptengineering |🔴 Join Patreon: Patreon.com/PromptEngineering
@twentiesguide8517
@twentiesguide8517 Жыл бұрын
Pls do a video on few shot learning using LLAMA 2 for text classification. Nobody have done this and it’ll be very useful for us.
@satyamgupta2182
@satyamgupta2182 Жыл бұрын
Yes. Great idea
@pavanpraneeth4659
@pavanpraneeth4659 Жыл бұрын
Yes we need this
@MichealAngeloArts
@MichealAngeloArts Жыл бұрын
There is probably no point for the ideation phase to have n>1 as all the resulted ideas have produced the same output (e.g. 6 hours as in your first experiment). Setting the temperature to a high value comes on the risk of increasing hallucinations. As a result you may end up having all your responses unfactual. A better implementation of ideation is to be guided sequentially rather than parallel (same as when you have "guided" the model in the UI approach that there is a logical flaw to its first idea)
@minercraftmen
@minercraftmen 3 ай бұрын
Exactly. I was thinking the same thing. It's only good if you have to give the answers separately for some reason. I tried it with a plain local model to solve the problem. Could not solve it. Then I wrote a 3 step prompt about like the one in the video and it solved it with one output. What I noticed is that it responded very well to the "common sense" prompt. The prompt: (sorry for bad eglish) ## Ideas: Make 3 different ideas for the same input. Use common sense. ## Critiuqe: Look at your 3 responses and search for flaws in them. ## Final: Conclude from the critics what would be the right answer. Dont overthink and look for additional information. Answer: (OpenChant 3.5) Idea 1: The number of shirts doesn't affect the drying time, so 30 shirts will also take 6 hours to dry. Idea 2: The drying time is directly proportional to the number of shirts, so 30 shirts will take 3 times longer, or 18 hours, to dry. Idea 3: The drying time is indirectly proportional to the number of shirts, so 30 shirts will take 1/5th the time, or 1.2 hours, to dry. Critique: Idea 1 is incorrect because the number of shirts does affect the drying time. Idea 2 is incorrect because the drying time is not directly proportional to the number of shirts. Idea 3 is incorrect because the drying time is not indirectly proportional to the number of shirts. Final: Based on the critiques, the correct answer is that 30 shirts will take 6 hours to dry.
@AdrienSales
@AdrienSales Жыл бұрын
Thanks a lot for having made me discover this approach. I've just tested it and I have started prototype and tune prompts on it. I wonder if you tried to pipe chain after that with common expression language ?
@marilynlucas5128
@marilynlucas5128 Жыл бұрын
All these advancements are useless if developers keep ignoring open source and developing AI apps that require Open AI Api keys. Smh
@JustAThought01
@JustAThought01 Жыл бұрын
Consider a two track process: cloud processing for major social/business services and at home products for individual/small business implementations. Cloud implementations will have much greater funding for researching possible implementations and then open source implementations once the best path forward is identified.
@Lorv0
@Lorv0 Жыл бұрын
True but there are tools like openllm which can act as an OpenAI server. So basically you could use this tool or any other tool using OpenAI keys with your own local LLM
@marilynlucas5128
@marilynlucas5128 Жыл бұрын
@@Lorv0 I understand what you're saying. I am aware of Openllm and even vLLM and its paged attention feature that enables fast inference. I just didn't get the part where you said I can use OpenAI API keys with openllm?
@MattGoldenberg
@MattGoldenberg Жыл бұрын
These methods can all be used without access to the model.
@YT-Gmailer
@YT-Gmailer Жыл бұрын
langChain is capable of using other models. You don't necessarily have to use gpt3.5-turbo
@paulstevenconyngham7880
@paulstevenconyngham7880 Жыл бұрын
Got a link to the colab notebook you used in your example by any chance?
@engineerprompt
@engineerprompt Жыл бұрын
There is a link to the LangChain documentation in the description which has the code, if not I will share the colab link.
@paulstevenconyngham7880
@paulstevenconyngham7880 Жыл бұрын
@@engineerprompt doh! thanks man, love your content - keep up the excellent work
@coder-r
@coder-r Жыл бұрын
@@engineerprompt share your collab link if you can please
@manabchetia8382
@manabchetia8382 Жыл бұрын
Can we use SmartChain with Lllama 2 ?
@WeylandLabs
@WeylandLabs Жыл бұрын
Bingo ! Finally intelligence has been detected...
@dmerriman
@dmerriman 9 ай бұрын
Yes, you can use Ollama, switch out the OpenAI module for from langchain.llms import Ollama and for the llm use the following: llm = Ollama(model=llama2", verbose=True)
@WeylandLabs
@WeylandLabs Жыл бұрын
Yay ! We are evolving finally ... 🤣
@JustAThought01
@JustAThought01 Жыл бұрын
Very interesting concept. Good for comparing different solutions for problem solving. Current event problem: how best to control economic inflation.
@coder-r
@coder-r Жыл бұрын
Is there a link the notebook?
@engineerprompt
@engineerprompt Жыл бұрын
Yes, there is a link to the actual documentation from langchain which was used during the video
@Codescord
@Codescord Жыл бұрын
MAKE A VIDEO ON "HOW TO TRAIN LLAMA 2 FROM TXT FILES"
@gunngunn6763
@gunngunn6763 Жыл бұрын
How to get free ChatGpt 4?
@engineerprompt
@engineerprompt Жыл бұрын
Use bing chat
@franchocou
@franchocou Жыл бұрын
First
Run your own AI (but private)
22:13
NetworkChuck
Рет қаралды 1,4 МЛН
when you have plan B 😂
00:11
Andrey Grechka
Рет қаралды 62 МЛН
отомстил?
00:56
История одного вокалиста
Рет қаралды 6 МЛН
NEW Friendly Samantha that can Code
12:30
Prompt Engineering
Рет қаралды 10 М.
GPT-4 Makes Old ChatGPT Look Like a JOKE!
12:56
Nick Chapsas
Рет қаралды 427 М.
Automate Dataset Creation for Llama-2 with GPT-4!
10:13
Prompt Engineering
Рет қаралды 12 М.
SMALL BUT MIGHTY - 13B Model Beats Llama-65B NEW BEST LLM!!!
12:17
Prompt Engineering
Рет қаралды 22 М.
ChatGPT Prompt Engineering: The Secret to 10x Smarter Responses!
18:02
Don't Use ChatGPT Until You Watch This Video
13:40
Leila Gharani
Рет қаралды 1,6 МЛН
Is GPT Engineer Actually Useful? 🤨
17:33
ArjanCodes
Рет қаралды 32 М.
CODE-LLAMA For Talking to Code Base and Documentation
14:49
Prompt Engineering
Рет қаралды 22 М.
LocalGPT Updates - Tips & Tricks
19:38
Prompt Engineering
Рет қаралды 23 М.
AutoGen Tutorial 🚀 Create Custom AI Agents EASILY (Incredible)
20:10
when you have plan B 😂
00:11
Andrey Grechka
Рет қаралды 62 МЛН