Hacker Newsnew | past | comments | ask | show | jobs | submit | more ekusiadadus's commentslogin

I actually tried it out and it feels pretty good. Especially with SvelteKit, where the library ecosystem is still somewhat limited, a library like this is really exciting. I particularly love that it works at runtime, since implementing that myself would be a hassle—so I really appreciate it.


thanks!


How about Japan? Many people from Nepal live there.


Indeed, Linux has improved a lot, but for many people whose main applications are gaming and Office, the adoption cost still feels too high.


That’s my roadblock. I need Office and still want to be able to play Fortnite.


It doesn’t really look like the solution was simply forcing engineers to join sales calls. The real issue seems to have been a breakdown in communication between engineers and those relaying customer needs.


It’s not only MIT students—poetry is being read and written at many schools. The claim that this is a > "symbolic event for thinking about the meaning of human expression in the age of AI” feels a bit exaggerated.

Did the author actually compare MIT with other universities?


Waiting for Pixel 10a. Pixel 10 is so expensive.


What triggers the timing of the emails?


The 1st email is based on a trigger based on changes in customer's subscription data. Subsequent emails are 2-3-4 days after the previous email and configurable


Does it also support videos?


How are you actually running this in practice with Claude Code? Do you just tell Claude to always read and follow AGENTS.md, or do you also use an MCP server to strictly control which commands (like pnpm test or pnpm lint) it can run? I’d love to hear what workflows or best practices have worked well for you in day-to-day use.


I have Claude Code maintain the files and reference links between them.


Isn't it consuming more tokens ?


Feels like less than jr vibe coding to me.

It looks up what it should and shouldn’t do. I can make sure it always or never does something a certain way again.

Claude max is also worth it.


Markdown is certainly easy for humans to write, but as OpenAI pointed out last week, wouldn’t an XML-based format be easier for LLMs to parse and understand?


> but as OpenAI pointed out last week

What are you referring to here?


https://cdn.openai.com/API/docs/gpt-5-for-coding-cheatsheet....

From OpeAI's last week document for coding with gpt5.

> #3. Use XML-like syntax to help structure instructions


I don't know if GPT-5 is an exception and is overcooked on XML specifically, but in general Markdown and XML seem to work about equally well for LLM inputs, the important part is just that they like hierarchical structured formats. The example on that page could probably be replaced with:

  ## Code Editing Rules

  ### Guiding Principles

  - Every component should be modular and reusable
  ...

  ### Frontend Stack Defaults

  - Styling: TailwindCSS
Without any meaningful change in effectiveness.


LLMs should make it easier for us, not the opposite


they are just moving goal posts because agents still largely suck for everything except a couple of super saturated problem domains that really shouldn’t require anything special from a dev anyways


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: