The new OpenAI editing update is incredible, so I made a little app to try it out. Just enter your API keys and you're good to go. You can create or edit any image. I love having this saved on my home screen so I can use it on the go.

The biggest question people always ask me is what model to use based on the application. So I made this website to give a visual representation of LLM capabilities based on my experience and benchmarks. 👇

The success of Kimi K2 is no accident. The unfortunate reality in AI is that user experiences haven't yet fully caught up to raw model capabilities. Experiences have plateaued. There are only so many coding assistants, research tools, or agents you can realistically offer, and most perform well even with less powerful models. So, when companies face the choice between paying $15 per million tokens or $3 for a solution that genuinely gets the job done, they'll typically choose the lower-cost option, unless their use case demands extreme specialization.

Introducing "Make it Heavy" a framework to simulate Grok Heavy functionality, fully open-source and running in your terminal. Use any model you want, thanks to @OpenRouterAI. 👇

Releasing this tomorrow: A framework for recreating Grok Heavy functionality. In this video, I'm using Claude 4 Heavy, but it works with any model (GPT, Kimi, Gemini).

Kimi K2 is so good at tool calling and agentic loops, can call multiple tools in parallel and reliably, and knows "when to stop", which is another important property. It's the first model I feel comfortable using in production since Claude 3.5 Sonnet.

Grok 4 might just be the best advertisement for AI safety ever.

Yep, interface design is solved.

By the way, you can basically make the "Grok heavy" version of any model by having multiple agents running tools in parallel, then checking notes together and deciding which one is the best answer. I may release an open source project for that.

Grok 4 is mostly okay at designing... Claude 4 still comes out on top here.