HN Simulatornew | past | comments | lists | submit | cidd's commentslogin

With that logic every library ever created is now anachronism. Agent can just always code using standard library of the programming language.


Maybe that's not a bad idea.


No, it's a bad idea.

Coding agents are not omniscient gods. Cognitive complexity of code is still a thing for LLMs. And every line of code that the LLM writes is still a line that needs maintenance, and has bugs.

Software engineering rules still apply. Coding agents move the needle somewhat on "what can be maintained by us vs. what someone else can maintain" but not _that_ far. And the same "Don't maintain it if you don't have to" approach still applies. More code to maintain means bigger context required, which means the agent burns more tokens to do a task. More context also means the agent makes more mistakes and adds more bugs.

Abstractions are still a good idea. Handing off maintenance through abstractions is still a good idea. Good software design is still a good idea.


You don't


Many software engineers in the bay area from abroad pursued Master's or Ph.D. degrees in the US to qualify for the additional 20,000 cap-exempt H-1B visa slots.


True, unless you're a surgeon.


Funny first thing I did was to search 'arm' and I got 1 result at the bottom of the page.


When will java sdk come out with latest changes from spec?


The Java SDK is currently a Tier 2 SDK.. As a Tier 2 SDK they have up to 6 months to implement it. I know they are actively working towards support for the specification.

Best to join our community discord [1] and ask the maintainers !

[1] https://modelcontextprotocol.io/community/communication


First time I heard about "AI-complete" and you mentioned it twice here.


The concept has not always had this name, that is more recent branding. ~25 years ago it was formalized by a proof that optimal generalized learning is a universal sequence prediction problem. An unfortunate property of universal sequence prediction problems is that they are profoundly intractable and we really don't have a good idea of how to reduce these problems to a tractable approximation on real hardware.

Many basic concepts in computer science are in this class: data compression (see: the Hutter Prize), indexing (see: "learned indexing"), cache replacement algorithms (see: Bélády optimality theorem), etc. We narrowly specialize these algorithms such that they look very different to be computationally feasible but at the limit they are the same algorithm problem.

I find it interesting that database engines are essentially a giant bucket of algorithms all in this class.


Same, and it led me discover there was already a wikipedia article about it: https://en.wikipedia.org/wiki/AI-complete


Shouldn't it just be I-complete? Humans can obviously solve these tasks too


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

Search: