Everything that was previously just called automation or pipeline processing on-top of LLM is now the buzzword "agents". The hype bubble needs constant feeding to keep from imploding.
Thank you! I'm not against such hype TBH :)
LLM Agents Are Simply Graph – Tutorial for Dummies
21–30 of 82 posts
Re: LLM Agents Are Simply Graph – Tutorial for Dummies
#22Great write up! In my opinion, your description likely accurately models what AI agents are doing. Perhaps the graph could be static or dynamic. Either way - it makes sense! Also, thank you for removing the hype!
Thank you!
Re: LLM Agents Are Simply Graph – Tutorial for Dummies
#23Earlier quoted context omitted.
Hey, sorry for the confusion. This tutorial is focusing on the low-level internals of how agents are implemented—much like how intelligent large language models still boil down to matrix multiplications at their core.
Despite the memes, this reductivism is not exactly insightful. Like why stop there? Matrix multiplication is just a bunch of dot product. Which in turn is just cos and magnitude. What insights were generated from this?
If you can reduce complex matrix multiplications into simpler terms, then you may be able to focus the training based on those constraints to increase performance/efficiency.
Re: LLM Agents Are Simply Graph – Tutorial for Dummies
#24Hey folks! I just posted a quick tutorial explaining how LLM agents (like OpenAI Agents, Pydantic AI, Manus AI, AutoGPT or PerplexityAI) are basically small graphs with loops and branches. For example: OpenAI Agents: for the workflow logic: https://github.com/openai/openai-agents-python/blob/48ff99bb... Pydantic Agents: organizes steps in a graph: https://github.com/pydantic/pydantic-ai/blob/4c0f384a0626299... Langch…
Thanks for this write up. It'll be inspiring my ruby framework.
Re: LLM Agents Are Simply Graph – Tutorial for Dummies
#25Earlier quoted context omitted.
Hey, sorry for the confusion. This tutorial is focusing on the low-level internals of how agents are implemented—much like how intelligent large language models still boil down to matrix multiplications at their core.
Despite the memes, this reductivism is not exactly insightful. Like why stop there? Matrix multiplication is just a bunch of dot product. Which in turn is just cos and magnitude. What insights were generated from this?
ok, then how would you do it?
Re: LLM Agents Are Simply Graph – Tutorial for Dummies
#26It is hard to put a pin on this one because there are so many thing wrong with this definition. There are agent frameworks that are not rebranded workflow tools too. I don't think this article helps explain anything except putting the intended audience in the same box of mind we were stuck since the invention of programming - i.e. it does not help. Forget about boxes and deterministic control and start thinking of er…
what exactly do you mean with "error tolerance and recovery"?
Re: LLM Agents Are Simply Graph – Tutorial for Dummies
#27Hey folks! I just posted a quick tutorial explaining how LLM agents (like OpenAI Agents, Pydantic AI, Manus AI, AutoGPT or PerplexityAI) are basically small graphs with loops and branches. For example: OpenAI Agents: for the workflow logic: https://github.com/openai/openai-agents-python/blob/48ff99bb... Pydantic Agents: organizes steps in a graph: https://github.com/pydantic/pydantic-ai/blob/4c0f384a0626299... Langch…
Thanks for this write up. It'll be inspiring my ruby framework.
Thank you!
Re: LLM Agents Are Simply Graph – Tutorial for Dummies
#28Hey folks! I just posted a quick tutorial explaining how LLM agents (like OpenAI Agents, Pydantic AI, Manus AI, AutoGPT or PerplexityAI) are basically small graphs with loops and branches. For example: OpenAI Agents: for the workflow logic: https://github.com/openai/openai-agents-python/blob/48ff99bb... Pydantic Agents: organizes steps in a graph: https://github.com/pydantic/pydantic-ai/blob/4c0f384a0626299... Langch…
Minor comment: do you mean "LLM Agents Are Simply Graphs". Personally, I'd drop the adjective to "LLM Agents are Graphs" as I think it sounds better, but the plural is needed.
Re: LLM Agents Are Simply Graph – Tutorial for Dummies
#29Earlier quoted context omitted.
I think you’re referring to function calling: https://platform.openai.com/docs/guides/function-calling This still returns a string. You need to explicitly program the branch to the right function. For example, check out how OpenAI Agents, released a week ago, rely on a workflow: https://github.com/openai/openai-agents-python/blob/48ff99bb...
No I'm referring to the newest generation of agentic models one of which I linked to. These are not fully released but it is where the newest generation of research is headed.
That remains to be seen. Manus, a standard agent built with Claude 3.7, outperforms o3 agentic model on the GAIA benchmark.
Re: LLM Agents Are Simply Graph – Tutorial for Dummies
#30Hey folks! I just posted a quick tutorial explaining how LLM agents (like OpenAI Agents, Pydantic AI, Manus AI, AutoGPT or PerplexityAI) are basically small graphs with loops and branches. For example: OpenAI Agents: for the workflow logic: https://github.com/openai/openai-agents-python/blob/48ff99bb... Pydantic Agents: organizes steps in a graph: https://github.com/pydantic/pydantic-ai/blob/4c0f384a0626299... Langch…
Minor comment: do you mean "LLM Agents Are Simply Graphs". Personally, I'd drop the adjective to "LLM Agents are Graphs" as I think it sounds better, but the plural is needed.
Oh, that’s embarrassing ... pardon my poor English, and thanks so much for pointing that out!