My thoughts on Grok 3 after 24hrs: - it’s *really* good for code - context window is HUGE - utilizes context extremely well - great at instruction following (agents!) - delightful coworker personality Here’s a 5min demo of how I’ll be using it in my code workflow going forward.

As mentioned it’s the 1st non o1-pro model that works with my workflow here:

Regarding my agents comment: I threw a *ton* of highly specific instruction based prompts with all sorts of tool calls at it. Nailed every single request, even on extremely long context. So I suspect when we get API access it will be an agentic powerhouse.

It appears they may be doing some form of context truncation behind the scenes? Context summarization maybe? The web app does not error out on context until about 1M tokens, but an xAI employee says its context window is 128k tokens. This would make it 1:1 with o1 pro.

Overall I’m just thrilled to be living in a world with so many great companies making so many great models. OpenAI, Anthropic, xAI, and Google are all making exceptionally great models and I’m a very happy user/customer of each. Great multi-model world to be living in :)

This is the biggest productivity cheat code right now. Kiss reading documents goodbye. You can get an instant summary of any document with this tool.

@iruletheworldmo Trade talk, real-time. @XFlowChat.

Love RepoPrompt @pvncher

@pvncher Eric is the goat

This is cool. I'm excited to run my own experiments with Code Gen and grok 3. I'm assuming all of this isn't built into Cursor yet, right.

No Cursor integration just yet

grok is super underrated IMO

It’s extremely good