←
DC1,841 posts
DC avatar

DC

@heydthree

Co-founder/CTO @mindcloudhq AI-native integrations + analytics $4.65M ARR · profitable · $3M raised 🐙 OSS 16k ⭐ · /dthree 🗝️ thesecretsproject.com

◷ Joined November 2021▧ 55 Photos and videos
Jensen Huang avatar
⟳ DC retweeted
Jensen Huang@JensenHuang·Nov 17

Over the past week, I’ve been overwhelmed by the love and support of friends, industry colleagues, and people I've never met. Thank you to everyone who has shown kindness to my family and me. It means the world to me. I came to the United States 53 years ago, and becoming an American citizen is one of the greatest gifts and proudest moments of my life. NVIDIA has been my life’s work. Building it into the company it is today alongside my colleagues has been a privilege and an honor. Nowhere but in America could a company like NVIDIA be possible. I love our country, and I love NVIDIA. I did not live up to the standards expected of everyone at NVIDIA, and I have made serious mistakes in my personal life. I created problems for the Board that I deeply regret. I own my mistakes completely, and I am committed to cooperating with the Board’s independent investigation. Since my departure, I’ve seen an outpouring of calls from NVIDIA’s employees, investors, business partners, and customers for me to return as CEO. Many continue to reach out to me directly as the company navigates complex technology, market, competitive, and geopolitical dynamics. NVIDIA is a once-in-a-generation company. If the Board of Directors decides that my return is in the best interest of our shareholders, our employees, the company, and America, I would be honored to answer these calls and return as CEO. Thank you again to everyone who has shared their good wishes. I am profoundly humbled by your support. To my family: I love you, and I will spend the rest of my life being worthy of yours. Jensen

DC avatar
DC@heydthree·Nov 12

How many months until Claude Car Wash?

Introducing Claude Meetings: add Claude to your team’s video call and it builds docs, whiteboards, and other artifacts with you while you’re still talking. Starting to roll out in beta on Team and Enterprise plans.

1:03
DC avatar
DC@heydthree·Nov 12

Have you built your own local UI or workflow on top of Claude for orchestrating your agents + queue work? I want to see it!

DC avatar
DC@heydthree·Nov 10

It's weird to build the thing that's building the thing that's building it.

DC avatar
DC@heydthree·Nov 10

What are your agent worktree preferences? - One worktree per thread? - Small similar changes on one worktree/pr? - Raw dog on master?

DC avatar
DC@heydthree·Nov 10

Mind boggling how trash iOS Siri is still. These are not hard problems.

DC avatar
DC@heydthree·Nov 9

Biggest takeaway is that Opus 5.5 High was and is a monster.

In early testing on FrontierCode 2.0, Fable 5.2 at High effort scored about level with Opus 5.5 at Max effort, for roughly half the cost per task. At Xhigh effort, it scored the highest of any released model tested. Medium is the default in Claude apps and Claude Code.

Post attachmentPost attachmentPost attachmentPost attachment
DC avatar
DC@heydthree·Nov 9

Here we go again.

Introducing Claude Fable 5.2 and Claude Mythos 5.2, designed to tackle the most daunting technical challenges. They’re capable collaborators on ambitious projects in many fields, and show improvements in areas like coding, reasoning, and vision.

0:19
DC avatar
DC@heydthree·Nov 9

Your new role is tastemaker. It’s the last role. Accept it early and get better at it.

I've changed how I work over the last few weeks. I now have one lead agent for each area of focus, running all the time, and a chief of staff agent that oversees them. Each lead manages its own sub-agents that write code, test it, chase reviews, and coordinate with team members. Everything I need to decide or review comes into one prioritized queue, a simple local web app. Each product review includes screenshots and a video demo of the feature. I clear the queue in batches, mostly by voice and keyboard shortcuts. The leads also bring back ideas I hadn't considered. Working from one queue, instead of switching between dozens of chats, has cut a lot of mental overhead. The system keeps learning my preferences and distilling my judgment into a "Brian brain," so its recommendations and first drafts get better before they reach me. The goal is fewer corrections per change. Every change still goes through the same human review and security checks. It is eliminating tasks, not human judgment. What an exciting time to push the frontier of productivity, especially as we build the economy for agents (agentic finance). We should all keep pushing in this direction.

DC avatar
DC@heydthree·Nov 8

As soon as you’ve resolved agent trust as the blocking concern, the primary bottleneck to your productivity is attention and personal context overload.

DC avatar
DC@heydthree·Nov 6

Agent instructions for writing agent instructions are low-hanging fruit. Without them, every prompt fix your agents make can make things worse. This is the one we use internally, and it’s been worth its weight in gold.

DC avatar
DC@heydthree·Nov 5

Formula to break out on X: get your site ripped off.

DC@heydthreeNov 4

When your site designed by @jamesm is straight up ripped off 🤣

Post attachmentPost attachmentPost attachment
DC avatar
DC@heydthree·Nov 5

This would actually be a great idea for a homepage.

its over once swarm of AI agents start doing everything for us

0:20
DC avatar
DC@heydthree·Nov 4

When your site designed by @jamesm is straight up ripped off 🤣

Post attachmentPost attachmentPost attachment