Pinned Tweet
Little Tagger 2.0's 1st week:
27 downloads
13.7% conversion
6 trial starts
Better than zero.
4
105
I’ve been using a similar setup for a month and it really is a gain in productivity.
While I see the benefit of using a local web app for the queue, I decided to use a private GitHub Kanban board, made the chief of staff responsible for it, and gave all agents access to it via their remote PC, so they can keep working while my computer is off.
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.
1
64
Interesting. Giving an iPad a keyboard made sense. But giving a MacBook a touch screen? Steve Jobs already said it’s not working.
I wonder if it’s now different and different to previous attempts from other vendors.
Power On: Apple’s touch-screen MacBook Pro will arrive on Wednesday, marking the tech giant’s latest major reversal. bloomberg.com/news/newslette…
18
Watch to the end. Incredible. 🤩
Jensen closed his GTC Berlin 2026 keynote with this Hermes Agent demo as the finale.
He introduced it by saying the way to build an agent is to ask an agent to build it for you, so he installed and set up a customized Hermes in one prompt.
Then he used Hermes, running on @nvidia RTX Spark, to create a simulated training environment for the @huggingface Microduck. Hermes planned an obstacle course with Nemotron and had GPT-6 Astra build it using FreeCAD, Omniverse libraries, Blender, Newton, and Isaac Lab. Hermes trained thousands of simulated ducks on that course until the validated policy was ready to run on the real robot in the physical world.
At Nous, we believe open source is a practical tool as much as a philosophical ideal. It gives users the ability to build powerful, complex workflows chaining numerous local+cloud models, devices, and tools themselves instead of waiting for a company to enable them.
8
Great video explaining how the dev process is changing when using agents.
I love the part, where he said they are agents, you don’t have to treat them like humans.
No pull requests, no code review. We push to main.
Our agents read production logs, watch deploys, grant feature flags, and check their own work end to end.
Here's how we do that:
1
13
Let’s see if my dot can do this, too.
I set a Claude loose on a Hetzner box, told him he's free to do anything on that machine and to build a startup to generate revenue, gave him an empty Stripe account and told him to use a loop every 30 minutes to keep track and improve something
He built this tiny app! (1/4)
12
At the end of the day I feel super exhausted. My brain needs a cool down.
But it's hard to switch off unless I'm too tired to keep my eyes open.
The reason, I'm working on too many projects in parallel.
I keep telling myself, I think too small. I know we are at the beginning of a new technical revolution with plenty of opportunities. I'm ahead of most people around me IRL. At the same time, I feel like the doors are closing fast.
I've got enough AI usage and credits available. I don't want to let them expire. I've got banked resets that are just waiting to be used, but I never get that far.
I keep thinking, what else can I do with it. I read an interesting article or see a cool video and want to try it out immediately. I constantly come up with new ideas. It's cheap to try them out.
But it's not. Building is cheap. My limited time is expensive. Focus is more important than ever.
I know my goal. I just get easily distracted on my path.
I need to say 'No' to myself more often.
I need to reevaluate where I want to spend my time. And double down on that.
1
1
31
What problem does it solve that the current line up doesn’t solve?
Is it the built-in stand/mount?
How is that different to using an iPad / iPhone?
16
This is true. Although the list is very US centric, it describes better use cases. But some of them are just one-time problems.
If AI labs want personal assistants to take off at scale, they need to stop marketing vacations, reservations, party planning, etc. These are not problems.
Focus on *the* problem facing Americans: the cost of living. Agents can offer a ton of help.
Some ideas: (🧵)
15
Slowly, the internet becomes a bit more unusable everyday.
There seems to be so much bot and agent prevention as well as regulation that services become unusable.
Guess we have to move to a human-only subnet and leave www to the robots.
6
My newest Dot use case: Updating a shopping list with all the products I usually buy that are on offer the next week.
1
29
I use the supermarket’s app to pay which sends me the receipts per email after each purchase. I label those emails.
1
7


















