Viewing profile — hypoxia87

My advice as a PM people leader: build stuff. Historically, as a PM, you couldn't do anything without an engineering counterpart. Now, with GenAI tools, new PMs can easily create a…

Jumping in based on our experience in case it's helpful: - Evals are very useful and a core part of the best practice for creating LLM apps - There are already excellent solutions …

We've actually found the opposite -- Every client project has been based on GPT4 or Gemini, with one exception for a highly sensitive use case based on Llama3.1. The main reason is…

+1 There are already many prompt/LLM routers available. We've never found value in them, for similar reasons as mentioned above.

Plus every company's files in OneDrive and SharePoint.

Claude 3 Opus

I assume it's RAG over your chats with heuristically driven questions that are then fed into your system and user prompts. Notably, this comes after the release of 1) "Custom instr…

I think it comes down to prioritizing speed of execution in the race for AGI, especially in the context of two constrained resources: 1. Compute (H100s are almost impossible to get…

(step 4 is something only some types of agents do) For another definition that incorporates these elements (explicitly or implicitly), see Llamaindex's high level concepts page [1]…

For me, they're systems that: 1. Have a goal (hard-coded, taken as input, etc) 2. Create a plan (of steps or tasks) to achieve the goal 3. Execute (the steps or tasks in) the plan …

This is an excellent question! I'd also like to know.

Yesterday OpenAI released ChatGPT and Whisper APIs: https://news.ycombinator.com/item?id=34985848 Since ChatGPT was released, I've always wanted to be able to input queries by spea…