Tony Dinh

The new type of software is going to be “dynamic”: - A strong foundation of data access layer and integrations - A smart LLM layer to operate on the data - On-demand dynamic UI for the end users, most other interactions become conversational. For example, an email app will work like this: I connect with my email account, then I just talk (or chat) to the app. If I want to check emails the old way, I would just say “show me an email review interface, group incoming emails by sender and date”, then the AI will show me an on demand UI so I can scroll and click around. If I use any particular UI a lot, I will just bookmark that UI somewhere and later I just reopen it directly. All of these UI will become hyper-personalized that fit with the habit and workflows of each user individually. There is no need to design a UI for your software anymore. The same email app may look completely different for each person.

A new type of software is emerging: a folder full of text files containing instructions that can be run on any AI agent system.

OpenClaw

New like animation on X. Tap ❤️ to see.

Really surprised to see my product get into Nano Banana Pro training data

You don't need a "Longterm Memory MCP", just create a LEARNING md file in your project and put this in CLAUDE md: - The `http://learning.md` file contains insights, tips, and best practices discovered during previous tasks. Read this file before running new tasks to benefit from prior knowledge. Update it with any new findings after each task run if necessary (only when new information is available or when you need to update existing information) You have full access to the entire memory, plus you can track changes via git.

I made Cursor work for 44mins at a time, running new automation test cases 👀

How to start becoming a solo entrepreneur: Build small side projects, finish and polish them (aim for less than 2 weeks), making them well-scoped, functional small products. Then move on to creating more small products, gradually increasing complexity and adding payment options so people can pay if they want to. Still, each should be finished with a proper website, checkout flow, etc. These products don't have to be extremely useful or solve a painful problem, they're just for training your "building muscle". Naturally, you'll start creating more useful products later on. Now learn at least some marketing channels that suit your skills and interests: SEO, cold email, paid ads, influencers, etc. Then practice one week building, one week marketing, and repeat. If everything goes well, you'll unlock a profitable business in about 1-2 years.

Installing OpenClaw. If my MRR doesn't double in 48 hours I'm going to be PISSED!!

Build to learn. Then build to make money. Then build to create something new or make an existing thing better, faster. Then build something truly meaningful to you and make the world better. Many people stop at step 2.

Renaming TypingMind to OpenMind

If you have a side project, share below. I'll retweet some interesting ones to give you more attention 😄 I'll do this every month to encourage more people to build side projects and escape 9-5.

The AI replies are crazy in the post below and it is making this platform less enjoyable for everyone else There is nothing anyone can do about it because people just voluntarily post what AI tells them to. Maybe a new kind of social network is needed 😂

Wow Atlassian did it again, they officially killed Loom. Can't watch a video the 2nd time without logging in. Optimizing for some weird shit metrics that the PMs think will look good on their performance review. And I'm on a webview in a 3rd-party app, they probably don't know how annoying it is to log in in this state. Even if I log in now, the next Loom link I click will ask me to login again because it is a fucking webview with no permanent cookies. Looking for an alternative now. Rant over, thanks for reading