News for hackers. Stuff that matters.
Re:Emerging Architectures for LLM Applications by bluecoconut on Tuesday June 20, 2023 @04:58PM (#36410480)
> So, agents have the potential to become a central piece of the LLM app architecture (or even take over the whole stack, if you believe in recursive self-improvement). ... . There’s only one problem: agents don’t really work yet.

I really appreciate that they called out and separated some hype vs. practice, specifically with regards to Agents. This is something I keep hoping works better than it does, and in practice every attempt I've taken in this direction leads to disappointment.

Re:Emerging Architectures for LLM Applications by liampulles on Tuesday June 20, 2023 @05:15PM (#36410747)
This mirrors my experience as well. I've tried to use them for pretty straightforward support agent type tasks and found that they very often go down wrong paths trying to solve the problem.
Re:Emerging Architectures for LLM Applications by jerpint on Tuesday June 20, 2023 @05:46PM (#36411123)
Similarly for retrieval augmented LLM agents, they break down very quickly once the question is not directly found in the documents
Re:Emerging Architectures for LLM Applications by majestic5762 on Tuesday June 20, 2023 @05:59PM (#36411282)
What vector DB are you using? What is the data structure that you're vectorizing? What is your chunk size? Have you implemented memory? What prompt or technique are you using (ReACT, CoT, few-shot, etc)? Are you only using vector DBs? Do you use sequential chains? Does it need tools? Depending on your data, business case and what output you expect from the agent, there is no one-size-fits-them-all.
Re:Emerging Architectures for LLM Applications by baner2022 on Tuesday June 20, 2023 @06:05PM (#36411347)
Ha, I had the exact same reaction

I feel like lots of paper are getting published and reviewed which is good as bad ideas don’t get to propagate for ages

Re:Emerging Architectures for LLM Applications by EGreg on Tuesday June 20, 2023 @07:54PM (#36412438)
I am so glad that top VCs are thinking along these lines, of architectures that incorporate AI as part of the flow.

We've spun off a company to realize the vision of bringing an open-source, standardized framework to the PHP ecosystem, where we've been building apps for communities for over a decade. It's "AI for the rest of us", but at the same time promoting positive collaboration between communities and AI. It also involves micropayments for tasks done by either an AI or human agent.

If you're a VC or an expert in the space, I'd love to get feedback on this: https://engageusers.ai/ecosystem.pdf

And if you want to get involved in any capacity, whether as an investor or developer, please email me greg at the domain engageusers.ai -- this time around we are planning to take on venture capital funding for this project, and syndicate a round later this summer.