I'm doing a fireside chat with a Character AI tech lead on Tuesday in SF. This is what I'm planning to ask: – War stories from scaling to 30k QPS
– Why scaling LLM apps != scaling regular apps
– Internal tools built If this is interesting, come on by: https://
lu.ma/rujejluk
@hwchase17
-
Scaling LLM Apps to 30k QPS: Character AI Tech Lead Insights
By
–
-
LangChain Smith Auth Outage Resolved After Root Cause Fix
By
–
apologies for this – we are going through a major auth outage: https://
status.smith.langchain.com We've root caused the issue and deployed a fix, please let us know if you are still encountering issues.again, apologies any disturbance this may have caused -
Complex Report Generation with LangGraph Agents
By
–
Complex Report Generation with LangGraph I really like @jxnlco
's take that "RAG" -> "Report Generation" @RLanceMartin explores what this could look like with pretty complex LangGraph agent – give it a watch to start learning about this https://
youtube.com/watch?v=wSxZ7y
Fbbas
… -
Scaling LLM Apps: Lessons from Character AI Leadership
By
–
Want to learn how to scale LLM apps? Very few companies have achieved serious scale. Character AI is one of them I'll be chatting with James Groeneveld (an eng leader) about what that looks like & lessons learned Come join! https://
lu.ma/rujejluk -
OpenAI’s Push for AI Technology Standards
By
–
i would bet openai wanted to make it a standard as well
-
OpenAI plugins manifests comparison and evolution
By
–
@simonw why is this diff from what openai tried to do with their plugins/manifests?
-
OpenAI manifest files enable local system integration via plugins
By
–
i dont think openai had a desktop at the time, but you could put anything you wanted behind their manifest files, eg https://
openai.com/index/chatgpt-
plugins/#browsing
… to connect to local retrieval systems -
Anthropic’s Plugin System: How It Compares to OpenAI
By
–
Is this just Anthropic's version of what OpenAI did with ai-plugin.json and plug-ins a while back? Or am I missing something?
-
LLM Classification Methods: Accuracy and Judge-Based Evaluation
By
–
sry thanks for following up! for classification: id do accuracy, that should be pretty straightforward. if that doesnt work would be curious to hear more! second is harder, but id use LLM-as-a-judge. you can define either a ground truth example to compare with, or just
-
Defining Control Flow in LLM-Based Systems
By
–
In my mind, “decide the control flow” = “if statements based on the outcome of an LLM” Agree it’s a tough definition