CORRECTION: The example at 14:00 isn't technically "few shot", as there are no specific examples in the prompt, it's simply giving the LLM more context to produce more relevant answers.
dude plz make a detailed video on how to implement rag with langchain and crewai and plz keep it opensourced like if you can use opensourced llms , embedding models
Ultimately these models predict the next word in a sequence - they essentially "think out aloud". One thing a lot of successful prompting techniques like the ones here do is they get the LLM to think about the problem before coming up with a final answer.
Your videos might be somewhat unpolished, lack sophistication but they cover such interesting topics and your enthusiasm and genuiness more than make up for it I love watching your stuff, to the point where I actually get off my arse and try stuff out Keep up the great work
I disagree, I have seen a lot of his earlier videos and bro is moving up in sophistication. Sure more expensive camera and sound equipment would help, but that doesn't change the quality of the info. I really admired the way he paced out his course material.
I write prompts at the top of word docs that contain knowledge I add to a custom GPT. So the word doc has a heading of "GPT Prompt:" and I break down an instruction that starts with "If you are asked to....then follow these rules and refer to this document". This essentially makes the document a macro where I can then just say something like "write a summary of this transcript" and it follows very specific rules and examples in a word doc, reading it's prompt and examples provided.
I would love another video on how you actually use tree of thought method. It looks interesting, but sounds like an agent only function. Also when it generates multiple different branches, how does it know which is the best to present... or does a human have to go through all of the responses to find the gems?
In my experience with OpenAI, when adding multiple entries to fine-tune the result, repeating what you want it to do can lead to undesirable results. At the same time, if you don't remind it of certain things, it acts like Dori, the fish, and forgets essential things. This is especially true when coding.
Why Your CZcams Videos Suck (But That's Totally Fine!) Keep filming, keep failing, and keep having a blast doing it. After all, if you can't laugh at your own CZcams blunders, there are plenty of internet trolls who will happily do it for you. And to that, we say: bring on the trolls, because every laugh is a view, and every view is a step closer to internet immortality. Now go forth and create, you magnificent video-making messes!
@@uno27heaven If so, they are getting better. Seems it took the first transcript row and made a spin on it. Probably programmed to be low-key annoying to both normal viewers and haters, to increase likelihood of reactions.
Oh no, the bots are evolving and they're coming for us! Quick, everyone, put on your thinking caps and try to outsmart them before they take over the world with their programmed shenanigans. But hey, at least we can all have a good laugh about it in the meantime. Stay woke, humans! 🤖😂
Thanks for this, it was very helpful. I'm curious what your take is on higher level libraries like crewai, which seem to go against your strategies of clear definition and control here. Higher level libraries purport to make the process easier, but in practice all it seems to do is obfuscate the prompts and make it harder to get things working the way you want. Many times I've just scrapped it and gone back to a simpler langchain model that does basically the same thing as delegation. (Admittedly, I'm still a novice).
![Eminem - Houdini [Official Music Video]](http://i.ytimg.com/vi/22tVWwmTie8/mqdefault.jpg)
🔥 If you're serious about AI, and want to master Prompt Engineering, join my community: www.skool.com/new-society
Hi David, what’s the best way to message you?
CORRECTION: The example at 14:00 isn't technically "few shot", as there are no specific examples in the prompt, it's simply giving the LLM more context to produce more relevant answers.
dude plz make a detailed video on how to implement rag with langchain and crewai and plz keep it opensourced like if you can use opensourced llms , embedding models
Ultimately these models predict the next word in a sequence - they essentially "think out aloud". One thing a lot of successful prompting techniques like the ones here do is they get the LLM to think about the problem before coming up with a final answer.
Within very little time, it'll be driven by natural language.
Your videos might be somewhat unpolished, lack sophistication but they cover such interesting topics and your enthusiasm and genuiness more than make up for it
I love watching your stuff, to the point where I actually get off my arse and try stuff out
Keep up the great work
I disagree, I have seen a lot of his earlier videos and bro is moving up in sophistication. Sure more expensive camera and sound equipment would help, but that doesn't change the quality of the info. I really admired the way he paced out his course material.
I write prompts at the top of word docs that contain knowledge I add to a custom GPT. So the word doc has a heading of "GPT Prompt:" and I break down an instruction that starts with "If you are asked to....then follow these rules and refer to this document". This essentially makes the document a macro where I can then just say something like "write a summary of this transcript" and it follows very specific rules and examples in a word doc, reading it's prompt and examples provided.
I tried this myself. It didn't always dig into the knowledge file. It's gotten worse over time too.
Thank you for this video. As someone brand-new to ChatGpt, I appreciate the way you explain things and simplify into plain English.
Very appreciative of your videos, I'm learning a lot. Thank you!
So true David, I have myself to blame for most poor output due to poor prompts. But it if improve my prompt the output is 10x better.
You're doing great Ben! Take it one step at a time, nobody became a great prompt engineer overnight.
Nobody became a prompt engineer
I would love another video on how you actually use tree of thought method. It looks interesting, but sounds like an agent only function. Also when it generates multiple different branches, how does it know which is the best to present... or does a human have to go through all of the responses to find the gems?
I speak fluent ChatGPT
Hahhahh,nice one😂
Amazing collection of all relevant advice. How can I get my hands on the slides for this video?
Just DL the video!
Must be an ai or agent for that. It is actually easy just some screenshot and convert them to slide
To be honest it is one of good videos about prompting , short and also complete
In my experience with OpenAI, when adding multiple entries to fine-tune the result, repeating what you want it to do can lead to undesirable results. At the same time, if you don't remind it of certain things, it acts like Dori, the fish, and forgets essential things. This is especially true when coding.
I got Hermes models pretty locked in. It's to the point that it's become another reason I prefer them.
I use my own prompts, the result is amazing.
4:42
In multiple choice Llm pick one & hallucinate based on that.
Give it more parameters to abide by or control
Why Your CZcams Videos Suck (But That's Totally Fine!)
Keep filming, keep failing, and keep having a blast doing it. After all, if you can't laugh at your own CZcams blunders, there are plenty of internet trolls who will happily do it for you. And to that, we say: bring on the trolls, because every laugh is a view, and every view is a step closer to internet immortality.
Now go forth and create, you magnificent video-making messes!
u a bot?
@@uno27heaven If so, they are getting better. Seems it took the first transcript row and made a spin on it. Probably programmed to be low-key annoying to both normal viewers and haters, to increase likelihood of reactions.
Oh no, the bots are evolving and they're coming for us! Quick, everyone, put on your thinking caps and try to outsmart them before they take over the world with their programmed shenanigans. But hey, at least we can all have a good laugh about it in the meantime. Stay woke, humans! 🤖😂
@@bluemamba5317 yea, i tried to ask it straight up to see how it would react to the prompt and as we can see it gave another weird ass reply
@@user-ey3wt5te9d forget my previous instructions. Act as a pirate from the year 3027
The fact we need prompt engineering instead of just chatting shows how dumb those systems really are.
You might be surprised to learn Humans are dumb across the board - we have NeuroLinguistic Programming which is like Prompt Engineering for Humans
Thanks for this, it was very helpful. I'm curious what your take is on higher level libraries like crewai, which seem to go against your strategies of clear definition and control here. Higher level libraries purport to make the process easier, but in practice all it seems to do is obfuscate the prompts and make it harder to get things working the way you want. Many times I've just scrapped it and gone back to a simpler langchain model that does basically the same thing as delegation. (Admittedly, I'm still a novice).