Yesterday, Meta announced that they have released a new collection of AI models, Llama 4, in its Llama family.

(It consists of Llama 4 Scout, Llama 4 Maverick, and Llama 4 Behemoth.)

Historically, Open AI with its ChatGPT has been on the market for the longest period.

It has the biggest share (77.66%) and people are somehow used to it.

DeepSeek also experienced a huge boom but there were concerns about data because of China's origins.

Some people are inclined to Grok tho they are also beginning to doubt whether Musk will start applying some form of censorship and proofreading of information.

Gemini, Perplexity & Claude are also frequently cited models, but I don't feel they are used that much.

Which LLM model do you use, trust and why have you decided on that particular LLM? 

1. Tracking burnt calories during exercise is very inaccurate. All fitness trackers have a hard time estimating this value and studies show error margins up to 50%. This is because your calorie expenditure depends on things your tracker has no access to (how many calories you ate, how stressed you are, how is your metabolic health etc). Instead it's better to focus on calorie intake, and there are many good trackers such as Carbon Diet Coach 🍲

2. VO2 max is relevant for regular people too, not just athletes. In fact, it is probably more relevant for non-athletes since it is a better marker of health than performance and there is more variance between non-athletes than between athletes. In this study of over 1 million participants, a low VO2 max was linked with a 3-5x increase in overall mortality. This is an amazing finding as VO2 max is something we can increase through regular exercise, especially if done correctly. ❤️

3. Tracking daily steps is really simple but really valuable. There are many studies that show a strong correlation between daily steps and lifespan, but because it's such a simple (and maybe boring) metric we tend to overlook it. 🚶

Bonus: HRV is mostly irrelevant. Even pro athletes barely use this datapoint. Regular people are nowhere near the peak of their performance and most of us should not worry about being in the "optimal place" for training. We should just train and try to be as consistent as possible. 💪

Now if you have any questions, I'd love to know what they are and do my best to share what I've leant.

Thanks!

1. @Readdy

Build your dream websites by talking with AI - no drag-and-drop needed. When you're happy, publish instantly, or export as clean code or Figma files. Perfect for small teams with limited design resources, or agencies looking to deliver 10x faster.

2. Recall Augmented Browsing by @Recall

Ever read something and think, 'I've seen this before'—but can't remember where? Augmented Browsing resurfaces related content from your Recall knowledgebase, turning passive browsing into active discovery. Join 200K+ nerds and elevate how you consume content.

3. Waxwing 2.0 by @Waxwing

Upwork 2.0 for human-assisted AI agents: Get AI-generated previews of each service, DIY or hire AI-savvy experts, or run 500+ expert-built workflows. AI does the heavy lifting, humans ensure the outcome. Let's make AI great again!

4. HeroUI Chat by @HeroUI

HeroUI Chat turns prompts or screenshots into beautiful, production ready React applications with AI. Built on our open-source HeroUI library (23k+ stars, 600k+ downloads), it's design and code, all in one.

5. @EasyStaff Payroll

EasyStaff Payroll is a platform for convenient and secure payments to freelancers. With built-in compliance and simplified B2B2C contracts, you can effortlessly pay anyone, anywhere, anytime.

Congratulations to all these outstanding teams!

Which of these tools solves a problem you've been struggling with recently?

Drop a comment with your thoughts!

Juan from PH

OP-ED? Recently I've been finding myself actually buying and downloading apps more than before. The common thread? They're all silly things that almost do nothing. I say almost because what they do offer is a bit of joy during my work day. Some of the recent apps I've purchased or downloaded are @Klack, Googly Eyes, @Docko, @Ball,@TabTab, and @NotchNook. Some of these do have productivity or quality of life improvements (looking at the last two) but others are simply about making the computer fun again. For example @Klack has genuinely made me more focused when I type and I've been able to zone in on work. It's like each clickity-clack is driving me closer to where I want to go and idk, the feedback just feels GOOD. The audio is also really nice, not sure how I can explain it, but feels very high-def for something that is mimicking a tactical feeling. All these apps remind me of a time where shareware and P2P ( @Limewire ) was more popular. Where you might be okay buying a CD or floppy and installing something fun on your computer, then telling (sharing) your buddy about it. And with the rise of vibe coding, I think we're going to see vibeware become a thing. Where users will create something fun, quickly, using AI tools like @Cursor, @Replit, or @bolt.new/@Lovable and then put it at a super low cost or have a free-trial (shareware). Those that don't want to pay, will create their own iteration of it and choose their own distribution method (P2P) but it won't eat at the original. It's my genuine feeling that the internet is about to become fun again (it's already started) and I'm curious if I'm the only one feeling this way and/or embracing it? What do you think? Is the era of vibeware a good thing? And if not why should we refute it? This piece was written with FKJ - Just Piano in the background.

Recently stumbled across this Cursor pro-tip from Ian Nuttall on X: "1. ask it to recommend a folder structure

2. ask it to actually create the folder/files based on that this makes it 10x easier for me to get started and Cursor is more accurate using codebase cos it knows where to update files."

That got me thinking, what other pro tips are people using to generate better code, ship faster, organise your space better, etc. Drop em below:

Added PNG export to Text2Note. Use it to stick notes in Google Docs, slides, etc. Thank you @elena_yazovskikh for the suggestion.

Next, figuring out copy-paste for Figma/Figjam. Would be cool if it works.

Link of video

Demo video:

In yesterday's post, I broke down the goals (and achievements/failures for Q1 2025).

So happy to see your contributions as well and would like to know... What is on your plate for the next Q2 period?

(What steps do you want to take and possibly, how community can help you? 🙂)

My goals for Q2: 👉 Record 30 YT shorts according to scripts I created

👉 Edit at least 10 of them

👉 30 Twitter posts (research, write them, preparation)

👉 Prepare strategy for growing newsletter in terms of paid subscribers 👉 Write at least 2 articles (in collaboration with someone) 👉 Co-organise offline event 👉 To be interviewed into some videocast/podcast 👉 Start some new project 👉 Keep exercising, learning 3 languages and reading

SnoopDogg

Gary Vee

or Mark Cuban

Tho, they are not very active, it came to my mind:

Who would you like to see here and maybe ask them something in an AMA?

I recently started building Couples Hub (https://coupleshub.io/) a React-based application and Next.js based landing page using Bolt.new. Couples Hub is a product of my hobby brand "MD Meets Techie" which I've run for the past four years, creating digital products specifically for couples. Given my technical background, diving into Bolt.new was kind of a fun experiment (esp given how drab and boring my day job is). I noted several challenges along the way and I thought I'll share a few tips on what I've learned thus far. 

Feel free to add your insights or ask questions to make this post even more comprehensive! By no means do I claim to be an expert on anything mentioned below so I welcome critique as well :)

General Advice & Managing Your Bolt Codebase

• Bolt works well initially but can struggle as your codebase grows beyond roughly 100-200 prompts. Keeping your components short (under 300 lines each) helps manage complexity and Bolt's understanding of your code.

• Bolt uses the Claude Sonnet 3.7 model, which tends to be overly creative, suggesting unnecessarily complex solutions. Explicitly instruct Bolt, "I value simplicity and prefer straightforward implementations," to guide it towards simpler, practical solutions.

• Giving Bolt ambiguous prompts with multiple possible implementations often results in it choosing an unnecessarily scalable (and complex) approach that it might struggle to complete. Simpler is almost always better in Bolt.

• Maintaining markdown files that document your app’s current data model, product roadmap, and overall vision helps Bolt make more informed decisions—especially in the early and mid stages of development. (Once you're moving toward production, these references become less essential.)

Tactical Prompting Tips

• Explicitly instruct Bolt with phrases like, "Do not make code changes," during brainstorming sessions to prevent it from immediately jumping into code. This has been helpful for me when I just want to talk through a problem.

• Keeping a secondary AI assistant (like ChatGPT or Claude) available, and feeding it markdown reference files from your Bolt project, provides clearer, context-driven advice. This is especially useful in the later stages of a project when Bolt is often overwhelmed by the complexity of your codebase.

• When you're stuck, using terms like "think holistically" or "weigh the pros and cons in your approach" in your prompts encourages Bolt to approach problems more broadly, and has magically helped me break through blockages about 80% of the time.

Authentication

• Implement "Sign in with Google" as your primary authentication method, covering approximately 80-85% of typical user bases.

• Additional authentication providers like Microsoft or Apple usually add minimal extra coverage and are rarely necessary unless specifically required by your audience.

• Consider "Sign in with GitHub" for applications targeting developers or tech-savvy audiences.

UI Considerations

• I often find the hero section for my landing page from https://21st.dev/ and Bolt is able to handle the implementation fairly seamlessly.

• Bolt has the tendency to make landing page sections overly "Boxy". Just prompt it to give you another layout.

UX Considerations

• Be prepared to iterate multiple times on UX with Bolt. Initial versions are rarely perfect but improve significantly with continuous feedback and adjustments.

• Bolt often struggles with intuitive UX layouts. For instance, it's helpful to consider things like Hick’s Law (fewer choices = quicker decisions) and that users typically notice elements placed in the top-left first.

• Regularly seek external feedback from friends, users, or tools like ChatGPT or Claude to brainstorm and refine your UX design.

• Learning basic UX design principles significantly helps improve how intuitively your app presents information to users.

• Don't blindly use the suggested landing page copy recommended by Bolt. Iterate separately with ChatGPT or Clause based on the persona you're targeting. Bolt also tends to assume your app is already in production with "millions of users" - so you might want to make double check your copy to make sure it's not not blatantly lying.

Adding a Blog to Your Landing Page

• For scalable blogging on your landing page, I've experimented with solutions like Storyblok and Contentful but found them overly complex and more tailored towards marketers.

• I've had success converting Markdown directly to blogs, maintaining simplicity and scalability. If you need specific steps on how to achieve this, please reach out directly.

• I also figured out a hack to auto-generate and post my blog using a cron job that calls an API on a set schedule. It’s a pretty loaded topic, so I’ll share more details in a future post :)

General SEO Tips

• Don't overthink this too much. Just ask Bolt to take the necessary steps to implement SEO best practices. Just make sure you're asking it to do all things step-by-step rather than everything in one go.

Custom CMS and Data Management

• You can easily build a custom content management system within your Bolt application to preload and manage data in your Supabase database.

• Bolt can quickly create interfaces for uploading CSV or Excel files directly into your database, a helpful feature for applications requiring initial or bulk data uploads.

Email Integration (Using SendGrid)

• Bolt doesn't support native email capabilities yet. I successfully integrated SendGrid to handle user-related emails such as welcome messages and notifications.

• There's a learning curve, but manageable—I learned how to do this one one productive Saturday morning. If you're struggling or need guidance, feel free to reach out directly - it's a fairly loaded topic.

Analytics & Building Your Own Admin Tools

• Easily integrate Google Analytics by simply inputting your measurement ID into Bolt for basic user insights. Remember to ask it to track key events across your application.

• Alternatively, build your own internal admin-only analytics dashboard for more detailed engagement tracking, such as daily and monthly active users, and specific engagement metrics.

• Once your app is live, monitor feature that are getting used the most and proactively prune features that are no longer needed. This keeps your codebase clean, your UX sharper, and helps avoid a bloated app.

Performance & Security

• Before implementing complex features (for example: a SendGrid integration), always explicitly ask Bolt about secure and efficient methods to do so. For example, prompt it with: "What’s a secure but simple way to implement this? Do not make code changes yet"

• Bolt often defaults to generating numerous Supabase hooks, which may impact performance negatively. Clearly distinguish when to use backend APIs versus Bolt's default Supabase hooks to maintain optimal performance and security.

Hosting, Domain, and Deployment

• Do not embed API secrets like OpenAI keys directly into your client-side code. Always use Supabase Edge Functions (or Netlify functions or any other API solution) to handle these securely.

• Initially, I created a separate Netlify project exclusively for server-side functions before Supabase Edge Functions became available. Now, I strongly recommend using Supabase Edge Functions for backend APIs, especially to securely handle sensitive integrations like OpenAI APIs.

• Supabase Edge Functions make it easier than ever to run cron jobs and call external APIs like OpenAI in a secure and maintainable way. This significantly reduces the need for workarounds like separate Netlify functions.

• Use Namecheap for inexpensive domains (~$10-$15) and link them to Netlify for straightforward hosting.

Handling Roadblocks

• There are two main ways to handle roadblocks with Bolt:

  • Export and Debug Elsewhere: Export your project to Cursor or Windsurf. Tokens on Cursor and Windsurf are significantly cheaper than Bolt, making experimentation and debugging financially feasible. These tools also allow you to target specific files that you suspect are causing issues. Once you've found the issue and a potential fix, have Cursor or Windsurf craft a detailed prompt that you can directly feed back into Bolt to implement the solution. You don’t have to re-import the full project—just use the prompt.

  • Rollback Approach: Bolt has built-in backups allowing you to revert to a previous stable state. Rollbacks, although frustrating, can save significant time compared to debugging complex issues when Bolt is overwhelmed. Just keep in mind that while Bolt can rollback code, it cannot rollback your Supabase database changes, so plan accordingly when deciding to fork an earlier version.** Bolt has built-in backups allowing you to revert to a previous stable state. Rollbacks, although frustrating, can save significant time compared to debugging complex issues when Bolt is overwhelmed.

• While you can target specific files within Bolt, I’ve found it less effective than doing so in Cursor or Windsurf when debugging issues.

Advice for Fellow Learners (Pseudo-Technical Founders)

• Bolt is excellent for users with partial technical knowledge, such as product managers, technical founders, or students. Treat it as a knowledgeable yet inexperienced junior developer; guide its decisions explicitly, especially regarding complex integrations.

• Don’t expect this post (or any one guide) to teach you everything—your own intuition and learning will only sharpen as you build. Just start building.

Unfortunately, I've limited advice to give on marketing and monetization as those are things I'm still figuring out. If anyone has advice on creating social media posts via code generation, please let me know!

One final note: Bolt is shipping updates at an insane pace. Everything I've written here might become partially or completely obsolete in the next 6–8 weeks. So if you're reading this later, take all of this with a grain of salt! I'm still learning, so please feel free to share your experiences or ask directly for more specifics! :)

I hope this detailed breakdown helps those building or considering Bolt! I'm still learning, so please feel free to share your experiences or ask directly for more specifics.

Happy building!

I've tried a few but so far I've only gotten good usage from the Think tool which allows Cursor to basically jot down notes on it's process which it can then refer to later. Theoretically allowing more context than just the context window https://github.com/DannyMac180/mcp-think-tool Since I've installed it Cursor seems to use it a lot but it's hard to gauge how much it helps in practice. I'm glad the AI likes it though :)

Are there any must have MCP tools that you found have improved your workflow?