Відео

Where did OpenAI say they didn't use tree search? I think they do use tree search, specifically MCTS for generating the synthetic data for o1, then at inference time they don't use tree search. The magic is in creating the synthetic data - they take a variety of paths including some wrong paths of the tree search and chain those with keywords like "but wait, the above is getting me stuck. Let's try this instead" then jump to another branch (the branch frequently does lead to the correct answer) of the tree. The key is MCTS + "let's verify step by step" in my opinion, so they linearize the MCTS thoughts chains and train on that. Somewhere in there they're using RL also as another key ingredient. Looking forward to hear your thoughts

I tried o1 with moderately complex questions regarding solar astronomy and o1 completely fell apart. It was useless. I would point the contradictions in the answers and it kept apologizing.

Prompt that makes 4o behave like o1: ``` [Problem] Do it out by the following format, taking care to reflect, verify, clarify all assumptions: ###Thoughts### <Subtask 1 Name> <Subtask 1 Result> <Subtask 2 Name> <Subtask 2 Result> ... ###Final Answer### <Final Result> ```

Great content, thanks so much for sharing all of your videos!

What is the purpose of generating synthetic data from the model which would be used to improve itself? Wouldn't the synthetic data it produced contain the exact same biases as the model? How do you remove the inherent bias? More importantly, if it can produce expert data, why would it be used to fine-tune itself over it again considering the model was already able to produce the very same data? Does this feel like CoT or ReAct with extra steps?

AgentJo GitHub repo here: github.com/tanchongmin/agentjo

Great work and very practical too, kudos 👍 How much more time for going from agentjo to agentjohn? LOL

Check out AgentJo GitHub here! github.com/tanchongmin/agentjo

I like this more. But how does the tech differ from hypothes.is ?

Thank you John for this explanation! Will try it out!

i am quite interested to know, the distribution of XOR/XNOR distribution here. They are very good with non linearity classification. after the training is complete, does the distribution of xor/xnor seem higher than other gates?

Can't wait to see how this will revolutionize math

may you provide code pls?

Since the connections are randomly initialized and then fixed, so it's impossible to guarantee a 100% acc even the data is guaranteed no noise?

i hear the size being of concern, but i feel the comparison is a bit off: while the number of neurons in the logic gate net scale n^2 with the input size, where as in classic neural net scale linear. the number of weights in a classic FC-NN also scale quadratically with the number of neurons. so the learnable parameter count scales quadratically in both. the logic gate net when drawn on paper may look larger, but it wont require more memory i think. in the paper they mention that they just save the random connections in form of a seed number, so that does not require any space

There’s no choice, but it feels like too many interfaces have changed. 😭

It will not work well...

No, if you have a pulse signal, it will have an infinite representation in the latent (frequency) space. No advantage! Also, this JEPA is nothing new. In the past it was called PLS (Partial Least Squares and the likes -- Kernel PLS).

Related video (TaskGen Paper): ua-cam.com/video/F3usuxs2p1Y/v-deo.html

Here's my discord group for the AgentJo discussion + Logo Design competition: discord.gg/bzp87AHJy5

Looking forward to following the development of AgentJo ( very cool name), keep up the excellent work Jon💪

AgentJo Repo (building on TaskGen for multi-agent systems): github.com/tanchongmin/agentjo TaskGen Repo: github.com/simbianai/taskgen

AgentJo Repo (building on TaskGen for multi-agent systems): github.com/tanchongmin/agentjo TaskGen Repo: github.com/simbianai/taskgen

AgentJo Repo (building on TaskGen for multi-agent systems): github.com/tanchongmin/agentjo TaskGen Repo: github.com/simbianai/taskgen

AgentJo Repo (building on TaskGen for multi-agent systems): github.com/tanchongmin/agentjo TaskGen Repo: github.com/simbianai/taskgen

AgentJo Repo (building on TaskGen for multi-agent systems): github.com/tanchongmin/agentjo TaskGen Repo: github.com/simbianai/taskgen

AgentJo Repo (building on TaskGen for multi-agent systems): github.com/tanchongmin/agentjo TaskGen Repo: github.com/simbianai/taskgen

AgentJo Repo (building on TaskGen for multi-agent systems): github.com/tanchongmin/agentjo TaskGen Repo: github.com/simbianai/taskgen

AgentJo Repo (building on TaskGen for multi-agent systems): github.com/tanchongmin/agentjo TaskGen Repo: github.com/simbianai/taskgen

AgentJo Repo (building on TaskGen for multi-agent systems): github.com/tanchongmin/agentjo TaskGen Repo: github.com/simbianai/taskgen

AgentJo Repo (building on TaskGen for multi-agent systems): github.com/tanchongmin/agentjo TaskGen Repo: github.com/simbianai/taskgen

TaskGen Repo: github.com/simbianai/taskgen AgentJo Repo (building on TaskGen for multi-agent systems): github.com/tanchongmin/agentjo

AgentJo Repo (building on TaskGen for multi-agent systems): github.com/tanchongmin/agentjo TaskGen Repo: github.com/simbianai/taskgen

Book Link: www.amazon.com/Will-ChatGPT-Take-Job-Strategies-ebook/dp/B0D6Y8ZX5Y DALL-E course: www.udemy.com/course/the-dall-e-master-course/ Upcoming Video Generation Course in Singapore (Thursday 24 Oct 2024 4pm): lu.ma/p0g5ksm9

AgentJo Repo (building on TaskGen for multi-agent systems): github.com/tanchongmin/agentjo TaskGen Repo: github.com/simbianai/taskgen

Thank you for this tutorial. Would love to see integrating LanceDB (multi-modal vector db) to TaskGen.

cool wrappers

The Design Philosophy and whole architecture for taskgen was a pleasure to watch. Got to learn so much from it. I would love to contribute to the Project. Do we have any next ideas/features that we want to develop for the Project ? I have joined your Discord Channel as well

Pretty powerful. Thanks!!

Hi John. Was chugging along well and fine with Ollama-mistral-nemo model. All works well right till Tutorial 2 - Shared variables. improvised with another function with sqlite dbase - works fine as well. Then came this 3rd Tutorial on Memory, having OpenAIError: The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable. Is your memory method strictly requires OpenAI API key to continue? Look forward. Cheers and appreciate your work very much.

Update: Proudly rejected at ENNLP Industry Track 2024 for not having enough experiments!

Cognitive Overload is the key motivation to design multiple agents.

loved it. knowledge graph support would be pretty awesome.

Thank you very much for your work! I already tried it with Ollama and your examples did work from the first try, really good job!

Firstly, this explains the inner workings well (I have jumped directly to the code and could only understand like 70-80% of it, but watching this video made it more sense of what's overall happening inside) So is there any way to track the number of API calls made for a given task and even the total number of input tokens sent and the total number of output tokens generated. I looked briefly through the code and could not find it. Would be happy to contribute for the same if such functionality is required

Loved it. Eagerly waiting for planning implementaion in Taskgen

bookmarking this one! question: have you tried using OCR capable LLM's like gemini as an alternative for CLIP embeddings ?

Where are these live streams conducted?

Love this on all levels. I have created multiple agent flows already which had impressive performance but I can’t wait to delve into hierarchical agents!

The multi agent concept really brings up many ideas.