Hacker News: zby

New comment by zby in "Binance-hacker-1029 – $5.6B stolen from Binance"

zby — Fri, 30 Oct 2026 09:53:05 +0000

If USDT gets to a frozen list - that means that Tether does not need to comply with requests to convert it into USD? I guess this is very useful for Tether and the other stable coin emitters.

New comment by zby in "The State of Context Engineering"

zby — Fri, 30 Oct 2026 09:27:56 +0000

Yeah - it depends on the frequency. I think the other guy is right that when it happens with low frequency then calling it 'context poisoning' makes sense - because cleaning the context mostly fixes it. I still would be very careful about using it - because it might be interpreted as if the poisoned context was the root cause - it might be a cause for the downstream processing - but it itself is caused by something else - so it will recur.

New comment by zby in "LLM Voice"

zby — Fri, 30 Oct 2026 09:11:26 +0000

And apparently I am repeating here what I already have in my KB: https://zby.github.io/commonplace/theory/llm-generation-rela... - I borrowed the model from Boretti. The agent says that the note is much more careful and better developed than my comment above. You can judge yourself - but I think it does have many more details and hopefully most of these details are the good kind of filling in - but I guess it might be harder to read.

New comment by zby in "LLM Voice"

zby — Fri, 30 Oct 2026 09:03:27 +0000

My model is about gaps - all ideas start with gaps. LLMs can fill in these gaps quickly - but some ideas are just bad - so the filling in does not improve them. Maybe it would be useful to treat that filling in as a kind of hallucination - the LLM trying to meed impossible requirements. But on other cases the ideas are good and the LLMs fill in the gaps in the right way. It is a kind of skill to see when LLMs are hallucinating in the gaps. I use LLMs very extensively and I am adding checks to that should catch when the filling in is weak - but it is still not fully autonomous.

I also try to keep the llm-enhanced (or even fully llm-generated) content separate from my human writing - because it is true that the failure modes are different. But think LLM writing might be useful even if it is not consumed directly - it can enhance LLM answering your questions.

New comment by zby in "The State of Context Engineering"

zby — Mon, 26 Oct 2026 12:31:45 +0000

My point is that calling it context poisoning is confusing because of two things. First - it is hard to establish how causal it is for the downstream. Second - cleaning the context would not fix it - because it would be poisoned on next round - you need active measures to fight it.

It is also a bit tongue in cheek - if you did not notice - because of course all of this can be explained if needed even if the name alone suggests something else.

New comment by zby in "The State of Context Engineering"

zby — Mon, 26 Oct 2026 11:46:27 +0000

"iced tea" in context was a symptom - it might influence the downstream - but it is hard to establish that. The root problem was in weights - naming it 'context poisoning' is poisoning our reasoning context :)

New comment by zby in "The State of Context Engineering"

zby — Mon, 26 Oct 2026 11:25:51 +0000

  > Several times, Gemini 2.5 became convinced it needed to get tea, even though it 
  > was playing the older game. The tea task for FireRed was in its weights, so it 
  > poisoned its context. It spent hours trying to find or give the guard tea. Once 
  > it had been added to its to-do list, the model could not get past it.

I don't understand why this is called context poisoning when the information was in the weights

New comment by zby in "Show HN: ADRs for AI – Deliberation records for human–AI work, versioned in Git"

zby — Mon, 26 Oct 2026 10:46:08 +0000

There is now a general consensus that agents should retain everything - but project from that retained state into more useful representations for each type of work. Your approach is good for creating evidence for all of the decisions - but the retained records will probably be too detailed as the main source for agents working in bigger or older repos. We need multilayer approach for this - but I am still not sure what it should be.

Here is a comparison of ADR4All and my approach (which I am now revising): https://zby.github.io/commonplace/work/decision-lifecycle-ev... - it lives in the whole workshop for revising my approach: https://zby.github.io/commonplace/work/decision-lifecycle-ev...

New comment by zby in "We should be more ambitious with the software we build"

zby — Mon, 26 Oct 2026 08:19:05 +0000

I wish someone applied this as being ambitious about the quality of code.

New comment by zby in "The foolishness of "natural language programming" (1978)"

zby — Sat, 24 Oct 2026 17:03:47 +0000

'instructing a machine' is programming - how about this?

New comment by zby in "The foolishness of "natural language programming" (1978)"

zby — Fri, 23 Oct 2026 12:49:58 +0000

Product managers did not write instructions to a machine.

New comment by zby in "The foolishness of "natural language programming" (1978)"

zby — Fri, 23 Oct 2026 11:52:46 +0000

It is all about definitions. Writing instructions for llms is a new activity and we can call it as we wish - but I like to think about it as a new type of programming language instead of thinking about it as something completely new, because many analogies do transfer and you can use them to reason about larger systems composed of prompts. It is after all a way to instruct a machine.

There are differences and the article highlights some of them - but there are difference between programming in a functional language and an imperative one, there are differences between programming for a RISC machine and a CISC machine, there a lots of different semantics that programming languages support. Now we have a language with underspecified semantics.

New comment by zby in "The foolishness of "natural language programming" (1978)"

zby — Fri, 23 Oct 2026 11:42:00 +0000

IMHO instructing llms is programming - the analogy is not perfect but it is so close that it is quite useful. Programming is instructing a machine. We have now two types of programming - the traditional one that follows strict semantics and the new way of programming by prompting. The article still holds by showing the limitations of this new kind of programming.

Rapid alternation of conscious and suppressed representations in primate brains

zby — Sat, 17 Oct 2026 09:26:16 +0000

Article URL: https://www.biorxiv.org/content/10.64898/2026.10.15.759299v1

Comments URL: https://news.ycombinator.com/item?id=50129385

Points: 3

# Comments: 0

New comment by zby in "Why harnesses matter for energy (and token) efficiency"

zby — Fri, 16 Oct 2026 22:08:58 +0000

I don't know - all of these cache hit rate advocacy is kind of goodhearting. Cache hit rates are less important than the accuracy of LLM answers and people seem to forget about it. For example I've seen articles how sub-agents poison the cache. Sure you can fill up your context with irrelevant data to have high cache hit rate - but that degrades the LLM work - sub-agents are about providing the LLM with a clean context - just the information needed to do its job, no distraction.

All of the main providers now offer cache management that can work with sub-agents - but it was kind of bolted on - and all of them have different apis - so nobody uses them anyway.

New comment by zby in "Recursive self-improvement through collective intelligence"

zby — Mon, 12 Oct 2026 08:58:24 +0000

RSI is about turning that extra computation into acceleration - that is applying the compute to the (useful_work / compute) factor - this is the recursive part.

New comment by zby in "Recursive self-improvement through collective intelligence"

zby — Mon, 12 Oct 2026 05:31:15 +0000

This is not a fad - this is a consequence of the Bitter Lesson. RSI is the only game in town now.

New comment by zby in "Has the Autonomous Trucking Revolution Arrived?"

zby — Sat, 10 Oct 2026 06:19:39 +0000

This is a hard question - but less overall deaths is more important than the correct punishment.

New comment by zby in "Grep beats LSP? Why coding agents ignore your fancier tools"

zby — Fri, 04 Sep 2026 07:24:53 +0000

Humans don't use command line lsp tools - why should agents use them?

I use lsp when it is integrated in the IDE - but I haven't seen yet any usable command line tools - even if theoretically it would be very useful to type 'lsp-python -replace-function-name foo bar'.

New comment by zby in "SQLite as a Document Database (2020)"

zby — Sun, 30 Aug 2026 10:35:35 +0000

Here is a realisation from my recent work: it is not if the data is relational - because if you need you can always push the data into relations - just like you can push it into hierarchies if all you have is files and directories. It is about how much churn there is in the relations. You can model relations with just links or something and if there is not much churn you can keep it in git and it will work OK - the problem starts when your relations start churning (like when you have reviews that need to be updated on both review instruction change and document change) this is when you see yourself start building a relational db (badly).