Hi, I’m Anand (RC)....
Claude Opus 4.6 dropped yesterday. Agent Teams is in research preview. The Superpowers plugin now offers subagent-driven execution. Plan Mode still exists. And somewhere in the middle of all this, you're staring at a Claude Code session wondering: which of these overlapping features do I actually use, and when? I spent the last couple of days trying to sort this out. Here's what I found. The…
These are my current goto web chat AI agents: Grok 3 in X - base, Deepersearch, Think Qwen Max or QwQ with Search and Think, Search, Think, neither (for code, web prototypes, json responses) - Claude 3.7 Sonnet with extended thinking, web, code, artifacts ChatGPT o3-mini-high with or without web search Local models via open-webui/ollama on mac (you may pick smaller or larger variants depending on…
I stumbled upon this by chance. I was trying to get subcategories for some categories. I prompted different LLMs to generate subcategories for these categories. Particularly, I asked for exhaustive lists of subcategories in json format. The number and kind of subcategories for each category given by each model gives a great insight into several things: how each model categorizes different topics…
The temptation is to say the least to say the least
This is a detailed response to a question by @karpathy on X: When working with LLMs I am used to starting "New Conversation" for each request. But there is also the polar opposite approach of keeping one giant conversation going forever. The standard approach can still choose to use a Memory tool to write things down in between… — Andrej Karpathy (@karpathy) March 20, 2025 The best shot at a…