Hacker News .hnnew | past | comments | ask | show | jobs | submit | zby's commentslogin

The video seems to be about mushrooms.

Something I’ve realized lately is that AI makes some things so easy (like video generation) that you’re not required to do the hard work of planning and reflection that might occur with a more involved task. We’ve always been susceptible to rushed thinking but AI compounds this significantly.

The "have it your way" made me think about hamburgers, can't remember how/why though.


The fact that programmers can be nerd sniped into yak shaving some random libraries is the only thing that keeps Open Source running.

I would love to hear from someone knowledgeable - is that bad for the company or good?

I am open to changing my mind and I am looking forward for answers to your question - but I think it is like a click bait - looks interesting - but not really useful.

I used it to find out that my work notes and personal notes are mixed. Therefore, I decided to split this into separate KBs.

Anyway, I'm just curious about what contained in my Obsidian and gbrain (mostly the latter one).


I am building my self-hosting llm-wiki system (https://gist.github.com/karpathy/442a6bf555914893e9891c11519...). My approach is to start with a theory of how such systems could work. Then since llms can interpret theory - this theory becomes an executable llm-wiki system itself.

It's called Commonplace: https://zby.github.io/commonplace/



Your bot seems to think that `pi_agent_rust` is the same as upstream Pi.


I think I fixed this in a later revision. Does that persist?


"In the 890s, having recently converted to Orthodox Christianity, Boris ensured his church would be independent from the Patriarchate of Constantinople." --- I thought Orthodox Christianity was created by the Great Schism in 1054.


The orthodox would argue that it was catholicism that was created by the great schism. But for both sides the actual date of the schism matters little, the divide between east and west was already forming long before then. Tsar Boris the 1st actually sent letters to the pope in Rome and the patriarch in Constantinople asking both of them for Christian teaching, it's debated wether he did this cynically or innocently, but either way he was "playing both sides" even before the schism, if anything he accelerated it somewhat.


I don't know if you are trolling or what, but you win at the internets today


So no hope for https://xkcd.com/810/?


I concur - it does not make sense to do in llm prompts what can be done in code. Code is cheaper, faster, deterministic and we have lots of experience with working with code.

Especially all bookkeeping logic should move into the symbolic layer: https://zby.github.io/commonplace/notes/scheduler-llm-separa...


""" we need to build:

    Formal specification layers that agents execute against, not just prompts
"""

It is probably easier to just write that program.


yep. "Formal specification layers " aka code.


Talked with someone this morning who is using "formal methods" to validate their AI generated code.

They are using the same AI to generate the proofs.


And how they are doing? I think this might be a solid research program - but that blog presented it as some kind of practical approach.


That's why you should just subscribe to multiple LLM vendors. One model to write specs, one to write code against the specs and another to validate the code. Problem solved. (I have heard this proposed at work.)


Right, because to trust that those "formal specifications" are correct, you will have to write them by hand.


First you need to write these specifications and if you say just tell the llm to write them - then how would it be different from just tell the llm to write the program?

I guess you can argue that these are two independent processes so you can combine them to get something more reliable than both - this might be a viable path. But from what I heard writing formal specifications is just really hard - I haven't seen anything practical in this area.


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

Search: