Lucas Sánchez

Comparto Frameworks y Estrategias para Simplificar y Escalar Negocios┃Co-fundador de @mastermeup, &

[Lucas Sánchez @luquimbo]

@steipete @steipete thanks for sharing… for what are using OpenClaw?

[Lucas Sánchez @luquimbo]

@naval Humans still need to have control and a chat is not usually the best UI for everything.

I think UI’s are not killed. Have to be redesigned for agents ans humans collaborating.

[Lucas Sánchez @luquimbo]

@TheMattBerman @Meta @HubSpot @Calendly Money

[jack @jack]

https://t.co/jgZkBvYOPt

[Aakash Gupta @aakashgupta]

Andrej Karpathy said it himself. The hierarchy for connecting tools to Claude Code: CLI at the top, API in the middle, MCP at the bottom.

MCPs eat context the moment they connect. Every MCP you load is sitting in your context window doing nothing until you call it. You could have five MCPs connected and lose 15-20% of your usable context before you've typed a single message.

CLIs use zero context until the moment you need them. The GitHub CLI, Vercel CLI, Firecrawl CLI. The AI calls them directly from your machine. No handshake, no persistent connection, no context cost.

Carl Vellotti ran a web research task with 10 tool calls and 30,000 tokens through a sub-agent. His main session moved from 16% to 16.5% context used. Without the sub-agent, that same task would have filled to 25%. The difference between a session that lasts 30 messages and one that compacts after 5.

Most PMs loaded up MCPs because that was the tutorial everyone shared in January. The PMs getting the best outputs right now ripped most of them out and switched to CLIs.

[Lucas Sánchez @luquimbo]

@TheMattBerman @openclaw ugc

[Lucas Sánchez @luquimbo]

@AskPerplexity @grok when Computer is coming to Pro Plans?

[Computer @AskPerplexity]

THE FUTURE OF AI APPLICATIONS

Jensen Huang: “Another breakthrough happened… the first time I realized Perplexity was using multiple models at the same time, I thought it was completely genius.”

The future isn’t one great model…

It’s orchestrating multiple great models at every step of the reasoning chain.

Multi-model. Multimodal. Multi-cloud.

[Lucas Sánchez @luquimbo]

@TheMattBerman @openclaw @rapidapi 1000

[Lucas Sánchez @luquimbo]

@FynCas PRO

[Lucas Sánchez @luquimbo]

@marclou Congrats dude

[Lucas Sánchez @luquimbo]

@corbin_braun @wen_hsu32824 Had great resulta with Auto mode with both front and backend

[Lucas Sánchez @luquimbo]

@Zephyr_hg Hooks

[Lucas Sánchez @luquimbo]

@elonmusk @grok Missing advanced features for Work, lile GPT creation and Dev Mode for MCP Support

[Lucas Sánchez @luquimbo]

@elonmusk @elonmusk love Grok but missing advanced features for Work, lile GPT creation and Dev Mode for MCP Support

[Lucas Sánchez @luquimbo]

@aryanXmahajan Gemini 3.0 was launched this quarter. How is possible that you had that results last quarter? Early access?

[Lucas Sánchez @luquimbo]

@aryanXmahajan OUTBOUND

[Lucas Sánchez @luquimbo]

@marclou 👏👏👏

[Lucas Sánchez @luquimbo]

@santisiri @AlanDaitch tiene un nuevo proyecto sobre eso https://t.co/eu5TvJX1Yv

[Lucas Sánchez @luquimbo]

@marclou Im impressed with the new features of Data Fast, will implement it tomorrow (coming back after cancellation). Keep shipping! 👏👏👏