ditenforcer retweeted
stop planning. just stop. there is literally no fucking point. my business plan? make money. i will simply do the thing that has the highest future probability that will make money. i won't sit there and think about it all day and pat myself on the back for thinking so hard
ditenforcer retweeted
There's a new kind of coding I call "vibe coding", where you fully give in to the vibes, embrace exponentials, and forget that the code even exists. It's possible because the LLMs (e.g. Cursor Composer w Sonnet) are getting too good. Also I just talk to Composer with SuperWhisper so I barely even touch the keyboard. I ask for the dumbest things like "decrease the padding on the sidebar by half" because I'm too lazy to find it. I "Accept All" always, I don't read the diffs anymore. When I get error messages I just copy paste them in with no comment, usually that fixes it. The code grows beyond my usual comprehension, I'd have to really read through it for a while. Sometimes the LLMs can't fix a bug so I just work around it or ask for random changes until it goes away. It's not too bad for throwaway weekend projects, but still quite amusing. I'm building a project or webapp, but it's not really coding - I just see stuff, say stuff, run stuff, and copy paste stuff, and it mostly works.
ditenforcer retweeted
If you are using Cursor AI to build any type of product it's highly recommended you provide as much context as possible about your project.
I've been using Claude Workbench to save & refine many of my prompts that help me quickly brainstorm ideas and requirements for each project I build.
This helps tremendously when you go back to cursor since you would have provided enough context for the models.
And this alone boosts execution at least by 50%.
Moreover having all this imported in a markdown file when imported to v0 works beautifully.
Always make sure you provide examples & inspirations from other products when asking v0 to generate the base layout of the product.
For me that's the biggest game-changer, because I can focus on the backend where I do most of the "traditional coding" without heavily relying on LLMs.
9/10 times v0 generally does the job okay and what's left for me since I got the right layout, color palette & fonts set up is to make some edits to my frontend.
Cursor & v0 are game changers, you will not build a product in a few hours but you will definitely save yourself a lot of hours of tedious development.
You just got to make sure you have the right foundation when using them, because in the right hands these tools are a godsend.
Remember context is king. Follow me for more,
@marioyordanov_
ditenforcer retweeted
v0 can now:
• Create and run full-stack Next.js and React applications
• Create multiple files in one generation
• Link and deploy to Vercel projects
• Use Vercel project environment variables
ditenforcer retweeted
"Service as Software" is Silicon Valley's hottest buzzword right now.
Everyone's talking about SaaS becoming service providers, but no one's explaining HOW. The answer? After 6 months of research and 100s of startup conversations, we have the answer: Systems of Agents.
We're looking at a $4.6T opportunity.
ditenforcer retweeted
Microsoft just killed Cursor today with the launch of GitHub Spark and introduced major updates to GitHub Copilot.
More details in the thread 🧵
📹 credit from Microsoft.
ditenforcer retweeted
The world will have 20% less startup founders if @X didn't exist
ditenforcer retweeted
Students at Stanford have built alphaXiv, an open discussion forum for arXiv papers.
ditenforcer retweeted
if you are just starting out. your goal should be being consistent and not fast progress.
fast progress will come as a byproduct of showing up daily
ditenforcer retweeted
The traditional Software as a Service business model is in crisis…
The biggest challenge in front of us for the next decade will be transform the current systems we have and implement agentic logic and reasoning to them.
Every SaaS if not fully automated will have to be at least augmented and powered by Gen AI.
No wonder why big enterprises are trying so hard to add AI features.
Future SaaS companies will be:
- agentic
- verticals
- pay-per-use rather than subscription. to
Now, knowing all that information makes you stop and think: “What is a crucial problem I could solve?”
As we’ve said already ideally it’s agentic and B2B industry-specific ( Vertical ).
What exactly is agentic?
Agentic means having one or multiple agents who are all about injecting intelligence and autonomy into a task.
Imagine an LLM on steroids with custom planning, memory and toolinn capabilities added.
DO NOT build just another GPT-wrapper like a content generator and something like that to sell at $19/mo
You really want to dig dee into boring industries and fields.
e.g
- law
- insurance
- real estate
- media buying
Luckily, you would already have some experience with a niche you’ve worked in. If not that’s okay, start researching and reaching out to people working in them.
Your task will be to simply grasp how they manage their SOPs and finad gaps where you can utilize GEN AI to speed up the process.
At the end, you should have a well-orhcestrated suit of AI Agents, each of them responsible for a specific task.
You can choose vertical architecture for your Agentic team meaning you have one agent on top to whom the rest report their work to.
I really think it’s a huge bliss to be living in these times.
I’m not sure many people realize that we have to opportunity to take a business operation, break it down into Its constituent parts and “translate it” into an agent. Tools are basically APIs, memory is vector DBs.
In the next post, I will share some Agent frameworks and sample projects you could build with them.
ditenforcer retweeted
Introducing Retrieve API: the best-in-class autonomous web information retrieval API.
Developers love our Agent API ❤️. Since its launch, we have consistently received feedback that many use cases rely on intelligently leveraging the Agent API to retrieve information from the web that is otherwise inaccessible.
That's why today we are introducing the Retrieve API: a faster, more affordable, best-in-class AI agent focused on web information retrieval. Learn more on our blog:
multion.ai/blog/introducing-…





















