Anand Narayan
@codeanand
http://chatsiva.com prompt to workflow agent. http://inba.ai zero-inbox agent. http://nanban.ai reduce mental load.
You might like
Bang on. Bootstrapping is the way to go for making your first few millions in your twenties.
Bootstrapping: you mostly just have to build a good business and you’ll be fine Raising venture: you have to build an incredible business and also play an underlying game where the rules change every 6 months Nothing wrong with either path, but picking the incorrect path…
me in may -> llm write code calling mcps in sandbox @Cloudflare code mode in september @AnthropicAI code execution with mcps in november just have to get chatsiva.com reliable and launched!
One solution is have the llm to write code calling these two mcps. And that code beings executed in a interpreter. which is what i am building at chatsiva.com
Claude Code is recommending that shift from GPT 4.1 to Claude in one of the apps I am building. I wonder if it was prompted to recommend itself. Or it learnt that Claude is better for this task. hmm
This gentleman is a real role model. Building something he wants. Building something insanely cool. With his own money. Real skin in the game. Tonnes of respect @waitin4agi_ . Wishing you the best
This one is dedicated to every kid who was told they couldn’t do something. youtu.be/2HqxXgUDxqA?si…
youtube.com
YouTube
Unleash the Avatar Gameplay Trailer | Early Alpha
On uploading a pic of my refrigerator order groceries. New workflow unlocked.
The omarchy folks. What do you use for text to speech. a wisprflow alternative.
This is exactly how chatsiva.com works “Mcp calls executed as a script in a sandbox” Bullish on this model and been building this for a few months now.
couple of thoughts about codemode/codeact (blog.cloudflare.com/code-mode/) - it's great but it's not a silver bullet. How it works? An agent, instead of doing N tool calls to meet the goal, writes the code that is calling these tools. Code is then evaled at secured sandbox and voila.…
writing readable modular loosely coupled code while trying to attain product market fit feels like trying to catch two mice together. is there some yc advice on this?
One measure of AI getting better is the sales of books especially (self help) trending down I see no point in reading 200 pages. when I can ask AI to do that job for me. Why would I read "Never split the difference" when I can ask ai to negotiate for me
Here is a html page that has Typescript examples of Complex vs Simple gistpreview.github.io/?cb77dc2d9e119… gist.github.com/sanandnarayan/…
The future of surveys is not forms. It’s talking to agents. Agents offer much more dynamism than conditional forms. #ideas
I want to give a similar talk in Coimbatore How to build your own coding agent. If anyone can set that up. Hit me up.
United States Trends
- 1. #SantaChat 1,400 posts
- 2. FINALLY DID IT 599K posts
- 3. The JUP 154K posts
- 4. Quinn Ewers 5,788 posts
- 5. Judon N/A
- 6. Mariah 48.5K posts
- 7. Algorhythm Holdings N/A
- 8. Jack Smith 21.7K posts
- 9. Fani Willis 4,190 posts
- 10. Gemini 3 Flash 6,702 posts
- 11. Robert E Lee 17.6K posts
- 12. Zach Wilson 1,171 posts
- 13. #jonita 16.4K posts
- 14. #wednesdaymotivation 2,852 posts
- 15. Jimmy Stewart 1,547 posts
- 16. #SomosBolivarianos 2,804 posts
- 17. QB Tua Tagovailoa 4,160 posts
- 18. Good Wednesday 39.2K posts
- 19. #NoWarYesPeace 3,983 posts
- 20. Four Republicans 2,259 posts
Something went wrong.
Something went wrong.