hackerbone
hackerbone on Hacker News
This is what I was thinking while doing some work on my projects. I've been a full stack focused developer way before the AI age and at that time DX was something that was a priority for me.
But now, its just about AX (Agent experience lol) how easy can you make it for the agentic system/model to achieve better outcomes. Its as easy as letting the agent choose it's way of doing things - let it choose its own project framework be it Astro, using bun, using handlebars even.
Nowadays people have shifted from writing code anyways - claude code or codex or any agent can do it, all we do is plan and review.
I'm just feeling bad just because stackoverflow was my coding bible (back when AI did not exist)
Getting second hand sadness
and that too using three.js haha
its only a few months away when we'll be vibe coding GTA 7 full e2e - make no mistakes kinda vibe
Makes sense, but still can't imagine a post apocalyptic world and how I'll live without power :(
All this is interesting, but I always had a question: in a state of disaster or some mishap even if you have an light LLM running - most important is a power source/electricity. Without it nothing will work.
People don't realise how easy it is to get started with AI agents, LLMs, agentic workflows - especially people like my parents and in their age group.
They think that its some rocket science to "operate" AI agents, but quite frankly they just need to spend a few hours on it.
AI can literally automate most of their tasks in an instant, the bar is just starting.
Ahh right, finding "hacker" news on HN - its still funny how random number generator used literally returned "4"
So the model route layer should be something that you would have to internally build on the inference POV - like opting for an OpenRouter or creating your own AI Gateway.
I've created an ai gateway myself with fallback models - this manages TPM/RPM rate limits and works seamlessly!
native mcp tools are the way to go - frontend is essentially dead.
The future is you having an OpenClaw/Hermes agent connected to these native MCPs and you texting on telegram/whatsapp etc.. with your agent to get information.
I'm already doing this - the future is now!!