Why Agents Don't Scale: It's an Engineering Problem, Not an AI Problem (blog.r-lopes.com) 5 points by dovelome 1mo ago ↗ HN
[–] sermakarevich 29d ago ↗ I think they do scale:-- check this bug report from AMD where they say they run fleet of 50 agents 24x7 https://github.com/anthropics/claude-code/issues/42796-- here I am running 3 coding agents 24x5 (not yet 7 so far) https://news.ycombinator.com/item?id=48520757I was using multi-coding agents for poc projects first, now for production research and poc second and soon plan to get to production. [–] dovelome 27d ago ↗ I like what you are doing! I suggest you create a proxy service that will route the traffic to the AI provider.You can cache questions and answers heavily and use a B25 search with a vector embedded to retrieve the best results for you. RAG pipeline ├── BM25 + TF-IDF + RRF retrieval ├── cross-encoder reranking ├── knowledge-graph entity linking └── multi-angle intent detection │ ▼ LLM synthesis (Claude / local models)
[–] dovelome 27d ago ↗ I like what you are doing! I suggest you create a proxy service that will route the traffic to the AI provider.You can cache questions and answers heavily and use a B25 search with a vector embedded to retrieve the best results for you. RAG pipeline ├── BM25 + TF-IDF + RRF retrieval ├── cross-encoder reranking ├── knowledge-graph entity linking └── multi-angle intent detection │ ▼ LLM synthesis (Claude / local models)
3 comments
[ 6.0 ms ] story [ 649 ms ] thread-- check this bug report from AMD where they say they run fleet of 50 agents 24x7 https://github.com/anthropics/claude-code/issues/42796
-- here I am running 3 coding agents 24x5 (not yet 7 so far) https://news.ycombinator.com/item?id=48520757
I was using multi-coding agents for poc projects first, now for production research and poc second and soon plan to get to production.
You can cache questions and answers heavily and use a B25 search with a vector embedded to retrieve the best results for you.