HNHacker News
TopNewBestAskShowJobs

zby

2,817 karma · joined August 15, 2007

http://brudnopis.blogspot.com

meet.hn/city/pl-Warsaw

Socials:

- github.com/zby

- linkedin.com/in/zbigniewlukasiak

- x.com/zby ---

submissionscomments
zby··on Colon cancer now leading cause of cancer deaths under 50 in US
Hmm - but has its incidence increased or just other causes have fallen down faster?
zby··on Don't post generated/AI-edited comments. HN is for conversation between humans
I just found the xkcd that expresses my opinion on this:

https://xkcd.com/810/

I am surprised that apparently I am in a minority here.

zby··on Don't post generated/AI-edited comments. HN is for conversation between humans
I also feel the frustration of the llm reverse-compression - when a whole article is generated from a single sentence. But when I post something edited by AI it is usually a result of a long back and forth of editing and revising. I guess I could post the whole conversation thread - but it would be very long.

Personally I would just like to read the best comments.

zby··on Deterministic Programming with LLMs
Here is my theory about weaving deterministic code and prompts: https://github.com/zby/llm-do/blob/main/docs/theory.md . Plus a library that realises the unified call space that I propose.

I think co-recursion between prompts and code is crucial, but I also think that the ephemeral nature of code in Recursive Language Models is impending deployment time learning (https://github.com/zby/llm-do/blob/main/kb/notes/deploy-time...).

zby··on EU bans the destruction of unsold apparel, clothing, accessories and footwear
I think these rules should have a pre-determined shelf life. They are not bad at the current state of the world - they push in the right direction - but they complicated law, and I bet there will be many second-level outcomes that are hard to predict now. Besides that - once the capabilities for reuse are built - they should be sustainable - so the second level outcomes will actually dominate.
zby··on Agent Skills
Hmm - maybe I should not call it index - people lookup stuff in the index when needed. Here the whole index is inserted in the conversation - it is as if when starting a task human read the whole table of contents of the manual for that task.
zby··on Agent Skills
The instructions are standard documents - but this is not all. What the system adds is an index of all skills, built from their descriptions, that is passed to the llm in each conversation. The idea is to let the llm read the skill when it is needed and not load it into context upfront. Humans use indexes too - but not in this way. But there are some analogies with GUIs and how they enhance discoverability of features for humans.

I wish they arranged it around READMEs. I have a directory with my tasks and I have a README.md there - before codex had skills it already understood that it needs to read the readme when it was dealing with tasks. The skills system is less directory dependent so is a bit more universal - but I am not sure if this is really needed.

zby··on Towards a science of scaling agent systems: When and why agent systems work
Computers are finite - but we use an unbounded model for thinking about them - because it simplifies many things.
zby··on Towards a science of scaling agent systems: When and why agent systems work
Reasoning is recursive - you cannot isolate where is should be symbolic and where it should be llm based (fuzzy/neural). This is the idea that started https://github.com/zby/llm-do - there is also RLM: https://alexzhang13.github.io/blog/2025/rlm/ RLM is simpler - but my approach also have some advantages.
zby··on What I learned building an opinionated and minimal coding agent
I've got the wording from an llm. I knew there was this pattern in all traditional tools - but I did not know the name.
zby··on What I learned building an opinionated and minimal coding agent
Pi has probably the best architecture and being written in Javascript it is well positioned to use the browser sandbox architecture that I think is the future for ai agents.

I only wish the author changed his stance on vendor extensions: https://github.com/badlogic/pi-mono/discussions/254

zby··on Show HN: Agent Skills Leaderboard
I would double - do skills reliably work for you? I mean are they reliably injected when there is a need, as opposed to being actively called for (which in my opinion defeats the purpose of skills - because I can always ask the llm to read a document and then do something with the new knowledge).

I have a feeling that codex still does not do it reliably - so I still have normal README files which it loads quite intelligently and it works better than the discovery via skills.

zby··on How to wrangle non-deterministic AI outputs into conventional software? (2025)
Yeah - the author seems oblivious to that option. But to be fair - this post is more about the more basic step of choosing the schema - he argues that it is still a task for a human. In his next post https://www.domainlanguage.com/articles/context-mapping-an-a... applying some output schemas would be more useful.

By they way you don' need to use library to have output schemas: https://platform.openai.com/docs/guides/structured-outputs , https://platform.claude.com/docs/en/build-with-claude/struct...

zby··on The recurring dream of replacing developers
Classic Jevons Paradox - when something gets cheaper the market for it grows. The unit cost shrinks but the number of units bought grows more than this shrinkage.
zby··on Claude Code gets native LSP support
LSPs should expose their api through shell commands - then integrating it with any LLM would be trivial. And it would also be very useful for humans.
zby··on Ask HN: What Are You Working On? (December 2025)
This week I vibe coded an golem-forge (https://github.com/zby/golem-forge) - exploration of prompting as programming. Since then I found https://github.com/badlogic/pi-mono and https://github.com/johnlindquist/mdflow and I think I'll rather use these existing tools to explore my idea. But I think it might be still interesting project because it is entirely vibe-coded - I don't even know Typescript (I know some Javascript from before React - but none of the new stuff). I did not look into the Typescript code at all - only at what the LLM presented to me when editing it and the docs. At some point I discovered that when I tried to have a core logic and two UI packages the LLM put only types in the core package - so I had drive a hard refactoring - but it worked.

I haven't yet tried this very extensively - but another profound change in programming that this showed me is that it is now very easy to borrow parts of Open Source libraries. It used to be that you could only base your work on a library - borrowing parts of projects that were not designed to be shared (used as libraries) was prohibitive - but with llms it is entirely possible to say: "now please borrow the UI ideas from project X" and it does that. Maybe you need to add some planning.

The project is about 27kloc now.

zby··on Ask HN: Should "I asked $AI, and it said" replies be forbidden in HN guidelines?
I like when someone links to where he found the information.
zby··on Ask HN: Should "I asked $AI, and it said" replies be forbidden in HN guidelines?
I thought that the point was to post valuable thoughts - because it is interesting to read them. But now you suggest that it depends on how they were generated.
zby··on Ask HN: Should "I asked $AI, and it said" replies be forbidden in HN guidelines?
I don't know - the linked examples were low quality - sure.
zby··on Ask HN: Should "I asked $AI, and it said" replies be forbidden in HN guidelines?
Why? This is like saying that you should not use a car - because you should walk. Sometimes yes - but as a general rule?
zby··on Ask HN: Should "I asked $AI, and it said" replies be forbidden in HN guidelines?
Well - the point of involving the AI is that very often it explains my intuitions way better than I can. It instantiates them and fills in all the details, sometimes showing new ways.

I find the second paragraphs contradictory - either you fear that I would agree with random stuff that the AI writes or you believe that the sycophant AI is writing what I believe. I like to think that I can recognise good arguments, but if I am wrong here - then why would you prefer my writing from an LLM generated one?

zby··on Ask HN: Should "I asked $AI, and it said" replies be forbidden in HN guidelines?
What is banned here? I can only find guidelines: https://news.ycombinator.com/newsguidelines.html not rules.
zby··on Ask HN: Should "I asked $AI, and it said" replies be forbidden in HN guidelines?
The contribution is the prompt.
zby··on Ask HN: Should "I asked $AI, and it said" replies be forbidden in HN guidelines?
What if I agree with what AI wrote? Should I try to hide that it was generated?
zby··on Ask HN: Should "I asked $AI, and it said" replies be forbidden in HN guidelines?
I strongly disagree - when I post something that AI wrote I am doing it because it explains my thoughts better than I can - it digs deeper and finds the support for intuitions that I cannot explain nicely. I quote the AI - because I feel this is fair - if you ban this you would just lose the information that it was generated.
zby··on The "confident idiot" problem: Why AI needs hard rules, not vibe checks
Most of things that were considered reasoning are now trivially implemented by computers - from arithmetic, through logical inference (surely this is reasoning - isn't it) to playing chess. Now LLMs go even further - what is your definition of reasoning? What concrete action is in that definition that you are sure computer will not do in lets say 5 years?
zby··on The "confident idiot" problem: Why AI needs hard rules, not vibe checks
"The LLM learns 2nd hand heresay, with no idea of what's true or false, what generalizations are valid, or what would be hallucinatory, " - do you know what is true and what is false? Take this: https://upload.wikimedia.org/wikipedia/commons/thumb/b/be/Ch... - Do you believe your eyes or do you believe the text about it?
zby··on The "confident idiot" problem: Why AI needs hard rules, not vibe checks
When I expect it to do that I just end my prompt with '. Discuss' - usually this works really well. Not exactly human like - it tries to list all questions and variants at once - but most with good default answers so I only need to engage with a couple of them.
zby··on Claude Advanced Tool Use
There is huge difference between tools executed on the client and those that run on the server - I wish it was made more clear in announcements like this one what it is referring to.
zby··on Claude Advanced Tool Use
I think this is about tools that are executed on the server instead of on the client. This is all very confusing - so I might be mistaken.
← PreviousPage 4 of 34Next →