Figured out how to make ChatGPT Dots an outrageously powerful agent: Use it as a project manager, not an assistant (skill linked below) The strength of ChatGPT is its harness. The desktop app is excellent and has an outrageous amount of tools So if you use your Dot to project manage other threads/tools, it can get a lot more done than other personal assistants that you just ask to make you reservations You can have it work on other projects for you continuously, loop over apps you're building, keep an eye on progress of other work, and just do a ton of things at once You DO NOT want to be using this as just a personal assistant. The model and harness are too good to be just booking you dinner reservations. Here is how I have it act as more of a project manager: have it start and keep an eye on other ChatGPT threads Give it a goal for that thread (build an awesome video game, create this business idea for me, build this presentation) Then have it manage that thread, working towards that goal step by step As it goes along, have it test every step then update a ChatGPT Space with information on that thread Then, do this with multiple projects and threads. It's really good at multitasking. If you set the right expectations for project management, you can get a tremendous amount of work done at once. Way more than you could with just a basic personal agent like Muse I built a project management skill you can give your Dot that sets all the expectations I mentioned above. You can check it out here: Does Dots have wildly different features than other agents? No But if you take advantage of it's strengths the right way, you can be wildly productive

Figure nearly tripled quarterly profits: loan volume past $4.3B, $226M in net revenue and $87M in net income. Onchain lending is real revenue now, it does not need another philosophical defense. Distribution is the next layer. #onchainfinance# #lending#

Figure just committed $3.5B to deploy up to 100,000 $NVDA Vera Rubin GPUs for humanoid robotics and Helix AI. Nscale is also taking an equity stake and becoming Figure’s preferred compute partner tying its robotics roadmap directly to a dedicated AI infrastructure buildout.

FIGURE SIGNS $3.5B COMPUTE DEAL WITH NSCALE Figure is partnering with Nscale to deploy up to 100,000 NVIDIA $NVDA Vera Rubin GPUs for its humanoid robotics and Helix AI models. Initial deployments are targeted for H2 2027 in Barstow, Texas, with $3.5B of committed compute and plans to scale beyond $6B. Nscale will also invest in Figure, become a shareholder and serve as its preferred compute provider.