Hacker News: zbyforgotp

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

zbyforgotp — Sun, 17 May 2026 14:21:51 +0000

Too late for fixing it - but of course I meant https://www.qubes-os.org/

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

zbyforgotp — Sun, 17 May 2026 07:47:07 +0000

In the limit we want the llm to write the code (like in RLMs).

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

zbyforgotp — Sun, 17 May 2026 07:39:20 +0000

We don’t trust llm execution- so we add user approvals. But task decomposition calls for co-recursion between code and prompts. This means that the approvals should be evocable at any depth. I think we need some kind of protocol for that (à la the Cubes OS protocols for cut and paste between vms).

Maybe a workaround could be to use bubblewrap of the scripts ther recursively call the llm (and run the agent in yolo inside the wrap).

New comment by zbyforgotp in "Specsmaxxing – On overcoming AI psychosis, and why I write specs in YAML"

zbyforgotp — Sun, 03 May 2026 11:31:04 +0000

The idea is that the spec is somehow compressed in comparison to the code.

New comment by zbyforgotp in "The agent harness belongs outside the sandbox"

zbyforgotp — Sun, 03 May 2026 11:26:31 +0000

You need supporting environment on both sides of the sandbox.

New comment by zbyforgotp in "Show HN: MDV – a Markdown superset for docs, dashboards, and slides with data"

zbyforgotp — Sun, 19 Apr 2026 06:35:57 +0000

Frontmatter should now be in the markdown standard.

New comment by zbyforgotp in "Deterministic Programming with LLMs"

zbyforgotp — Sun, 01 Mar 2026 13:53:07 +0000

I have been struggling with that. Thanks! Let me reword it - natural language lacks a strict semantics - so also programs for the llm machine ( I.e. prompts) cannot have it. LLMs always have to project from all possible semantics into one (are there any experiments with superpositions?)

New comment by zbyforgotp in "The RCE that AMD won't fix"

zbyforgotp — Fri, 06 Feb 2026 13:00:35 +0000

What is the root cause of this? It is said that AMD is hardware company and neglects software - but recently they issued lots of declarations of becoming software firs now.

New comment by zbyforgotp in "Show HN: Agent Skills Leaderboard"

zbyforgotp — Wed, 21 Jan 2026 11:10:51 +0000

The point is for the agent to have an index of available skills so that it can decide autonomously if it needs to load one.

https://zzbbyy.substack.com/p/what-are-skills

In my experience it doesn’t work too well with codex, but I expect llm providers to train them on that use case and improve the situation soon.

New comment by zbyforgotp in "Gas Town Decoded"

zbyforgotp — Mon, 19 Jan 2026 00:22:16 +0000

At some point evolving software instead of designing it will work. Now the evolutionary pressure leads towards churning more tokens.

New comment by zbyforgotp in "Rob Pike goes nuclear over GenAI"

zbyforgotp — Fri, 26 Dec 2025 22:58:37 +0000

Property is a local low - it applies to a thing that exists in one place. Intellectual property is trying to apply similar rules to stuff that happen remotely - a text is not a thing, and controlling copying might work in some technological regimes while in others would require totalitarian control. When you extend these rules to cover not just copying of texts but also at the level of ideas it gets even worse.

New comment by zbyforgotp in "Claude Opus 4.5"

zbyforgotp — Tue, 25 Nov 2025 09:53:27 +0000

There is something not right with expecting that artificial intelligence will have the same characteristics as human intelligence. (I am answering to the quote)

New comment by zbyforgotp in "The Bitter Lesson of LLM Extensions"

zbyforgotp — Tue, 25 Nov 2025 09:48:55 +0000

That’s why we need progressive hardening: https://github.com/zby/llm-do/blob/main/docs/concept_spec.md

New comment by zbyforgotp in "Kimi K2 Thinking, a SOTA open-source trillion-parameter reasoning model"

zbyforgotp — Fri, 07 Nov 2025 14:03:17 +0000

The American labs are paranoid. The secrecy kills innovation. Open Source means ideas can meet and have sex and produce offsprings.

New comment by zbyforgotp in "Jack Kerouac, Malcolm Cowley, and the difficult birth of On the Road"

zbyforgotp — Fri, 31 Oct 2025 08:25:56 +0000

Destroying high trust society is a lot of fun.

New comment by zbyforgotp in "The new calculus of AI-based coding"

zbyforgotp — Tue, 28 Oct 2025 06:45:00 +0000

TLDR: ai changes the economic calculus of software development. It makes automated testing more beneficial in comparison to costs.

I think he is right.

New comment by zbyforgotp in "Claude Memory"

zbyforgotp — Fri, 24 Oct 2025 08:49:54 +0000

They should just give the user some control over this

New comment by zbyforgotp in "It's just a virus, the E.R. told him – days later, he was dead"

zbyforgotp — Mon, 06 Oct 2025 21:29:04 +0000

Just to be precise. The sepsis alarm was not blocking x-ray or antibiotics but rather suggesting them.

“”” Agyare had instructed Banerjee to hydrate Sam right away but to wait for the results of Sam’s lab work before ordering a chest X-ray or the strong antibiotics used to treat sepsis. “””

New comment by zbyforgotp in "Terence Tao: The role of small organizations in society has shrunk significantly"

zbyforgotp — Thu, 25 Sep 2025 05:34:50 +0000

The problem is that people gravitate towards more impersonal relationships themselves because it frees them from the complexity of social calculations. We escape small organisations, we try to be independent from each other and prefer to depend on impersonal institutions.

New comment by zbyforgotp in "LLM Daydreaming"

zbyforgotp — Wed, 16 Jul 2025 17:59:30 +0000

I think our minds don’t use novelty - but salience and it also might be easier to implement.