Hacker News: zby

New comment by zby in "Show HN: OpenKnowledge – open source AI-first alternative to Obsidian/Notion"

zby — Fri, 26 Jun 2026 07:29:46 +0000

select text and comment on it - then let the llm read all comments

New comment by zby in "Show HN: OpenKnowledge – open source AI-first alternative to Obsidian/Notion"

zby — Fri, 26 Jun 2026 05:02:40 +0000

The feature I am waiting for in all of these editors is integrating 'red lining' as a channel for LLM input. This is the best interface for working on a text. https://www.roughdraft.md/ does the core idea pretty well - but is not well integrated with the rest (browsing, etc).

New comment by zby in "Prompt Injection as Role Confusion"

zby — Mon, 22 Jun 2026 21:02:23 +0000

If the action is decided by code based on metadata - then what is really the LLM task? And if you say that it is only the type of action that is decided by code - then this is maybe a mitigation - but the llm still can do a lot of harm. And also it is very limiting - using the llm to decide the action is very useful. This is different from SQL injection - where the action is determined by the code and the injection is really making a code parsing error.

It might still be the way to go - but calling it 'the real solution' is overselling it.

New comment by zby in "Prompt Injection as Role Confusion"

zby — Mon, 22 Jun 2026 20:49:10 +0000

They do predict what injections might be effective - so it is a theory. I don't know how novel it is and it is not very deep (as you noted the general mechanism is quite obvious) - but they do it quite systematically so it is useful.

New comment by zby in "Agentic coding deserves more than a chat box bolted onto VS Code"

zby — Wed, 17 Jun 2026 16:54:41 +0000

The video seems to be about mushrooms.

New comment by zby in "But yak shaving is fun (2019)"

zby — Tue, 16 Jun 2026 17:26:49 +0000

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

New comment by zby in "Israeli firm BlackCore suspected of meddling in New York and Scotland votes"

zby — Sat, 13 Jun 2026 09:37:57 +0000

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

New comment by zby in "Show HN: Skill for your agent to visualize your gbrain and Obsidian"

zby — Sat, 13 Jun 2026 09:35:50 +0000

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.

New comment by zby in "Ask HN: What are tools you have made for yourself since the advent of AI?"

zby — Mon, 08 Jun 2026 21:39:16 +0000

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/

New comment by zby in "Zerostack – A Unix-inspired coding agent written in pure Rust"

zby — Sun, 17 May 2026 09:27:54 +0000

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

New comment by zby in "Zerostack – A Unix-inspired coding agent written in pure Rust"

zby — Sun, 17 May 2026 09:13:37 +0000

There is also https://github.com/Dicklesworthstone/pi_agent_rust

I vibed a comparison/review of these two systems using my llm wiki: https://zby.github.io/commonplace/work/pi-agent-zerostack-co...

(the prompt is in https://zby.github.io/commonplace/work/pi-agent-zerostack-co...)

New comment by zby in "Inventing Cyrillic (2024)"

zby — Fri, 08 May 2026 09:13:56 +0000

"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.

New comment by zby in "Nobody Reviews Compiler Output"

zby — Fri, 08 May 2026 08:53:00 +0000

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.

New comment by zby in "AI slop is killing online communities"

zby — Thu, 07 May 2026 20:46:19 +0000

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

New comment by zby in "Nobody Reviews Compiler Output"

zby — Thu, 07 May 2026 20:37:53 +0000

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.

New comment by zby in "Agents need control flow, not more prompts"

zby — Thu, 07 May 2026 20:15:25 +0000

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...

New comment by zby in "Nobody Reviews Compiler Output"

zby — Thu, 07 May 2026 19:51:02 +0000

""" we need to build:

    Formal specification layers that agents execute against, not just prompts

"""

It is probably easier to just write that program.

New comment by zby in "Show HN: Auto-Architecture: Karpathy's Loop, pointed at a CPU"

zby — Wed, 29 Apr 2026 12:48:05 +0000

It is not novel - but with the new models it is just becoming practical.

New comment by zby in "Simulacrum of Knowledge Work"

zby — Sat, 25 Apr 2026 21:32:07 +0000

If you have a test that fails 50% times - is that test valuable or not? A 50% failure rate alone looks like a coin toss, but by itself that does not tell us whether the test is noise or whether it is separating bad states from good ones. For a test to be useful it needs to have positive Youden’s statistic (https://en.wikipedia.org/wiki/Youden%27s_J_statistic): sensitivity + specificity - 1. A 50% failure rate alone does not let us calculate sensitivity and specificity.

I can see a similar problem with this article - the author notices that LLMs produce a lot of errors - then concludes that they are useless and produce only simulacrum of work. The author has an interesting observation about how llms disrupt the way we judge knowledge work. But when he concludes that llms do only simulacrum of work - this is where his arguments fail.

New comment by zby in "AI agents that argue with each other to improve decisions"

zby — Sat, 25 Apr 2026 20:29:21 +0000

I don't know - looks like an interesting idea - but ... I am struggling to put that in a polite manner. When I go into the repo and find out that it does stuff like lip syncing of talking avatars then I start to think what percentage of the development effort goes into marketing?