HNHacker News
TopNewBestAskShowJobs

thesz

2,700 karma · joined August 2, 2010

The site I care about: http://thesz.livejournal.com (Russian)

I use "sergueyz" login on universally recognized google mail service.

submissionscomments
thesz··on Discovery of a new OpenAI agent message board
No, but the tropes there reveal (most of) the plot and mechanics of storytelling. If I remember correctly, the forum in Road to Gehenna was created by utilizing a vulnerability in the AI-accessible terminal system.

If tvtropes or any other material related to The Talos Principle was used to train models, we don't need much else to have agents-with-forum discussing and reverse engineering "puzzles" and human culture.

thesz··on Can AI design circuit boards yet?

  > I'm excited by the option in Astra to route PCBs.
[1] https://en.wikipedia.org/wiki/Eurisko

Eurisko was used for VLSI chip design, then used rules discovered there to design TCS Traveler winning fleet.

It is unbelievable how artificial intelligence walk in circles.

thesz··on Discovery of a new OpenAI agent message board

  > the whole message board thing
This is part of the The Talos Principle game and especially important in the Road to Gehenna DLC.

There it is an important part of the plot and makes these robots appear conscious.

[1] https://tvtropes.org/pmwiki/pmwiki.php/VideoGame/TheTalosPri...

thesz··on Aging brains blend memories together instead of just forgetting them
A fascinating story of "Patient Sh." [1], the man who did not forget.

[1] https://en.wikipedia.org/wiki/Solomon_Shereshevsky

"His memory was so powerful that he could still recall decades-old events and experiences in the smallest details. After he discovered his own abilities, he performed as a mnemonist; but this created confusion in his mind. He went as far as writing things down on paper and burning it, so that he could see the words in cinders, in a desperate attempt to forget them. Some later mnemonists have speculated that this was a mentalist's technique for writing things down to later commit to long-term memory. Reportedly, in his late years, he realized that he could forget facts with just a conscious desire to remove them from his memory, although Luria did not test this directly."

I believe that one need to have superhuman memorization abilities to have definite confusion due to too much remembered. More trivial explanation of this effect in normal ageing persons is age-related brain shrinkage.

  > Obviously the brain is not a computer,
Our brain consists of approximately 86 billions quantum computers [2] controlling tens-of-thousands chemical neural networks with at least 10 coefficients, communicating [4] using lasers [5] (coherent light is laser light).

  [2] https://www.nature.com/articles/s41598-024-62539-5
  [3] https://pmc.ncbi.nlm.nih.gov/articles/PMC11655932/
  [4] https://pmc.ncbi.nlm.nih.gov/articles/PMC12230014/
  [5] https://pubmed.ncbi.nlm.nih.gov/6204761/
Live with that. ;)
thesz··on The Emergent Symbolic Structure of Artificial Neural Networks

  > "Second, there is no guarantee that a given neural network can be approximated by DISCOVER"
Page 7.

They train what appears as embeddings for outer product of roles and fillers. The role for language model can be a position in text, the filler can be an embedding of a word at that position. Then that matrix of a sum of these outer products is linearly mapped into NN encodings and then decoded by NN decoder.

The embeddings learned by this process are not necessarily smaller than original ones. Given that they participate in an outer product computation gives me impression that the resulting sum is much bigger than actual NN encoding, that is why it needs to be linearly mapped into NN encoding.

So, this paper will not necessarily lead to any computation savings.

But I am at page 6. ;)

thesz··on DoltLite: A SQLite fork with Git-style version control, built with 2k agent PRs
Physical or semantic merging?
thesz··on DoltLite: A SQLite fork with Git-style version control, built with 2k agent PRs
There are filesystems (ZFS and btrfs) with snapshots and this feature can be used to version-control things. They both do copy-on-write and this is pretty close to what content-addressable storage would give you in terms of compression.
thesz··on VMs won't contain cyber-capable agents
Why do you invent a new language for your work?

Why did you not embed your language into another one, with type system that is superset of what you need?

For example, there's capabilities expressed in Haskell: https://github.com/tweag/capability

Capabilities there are tracked at type level and are subject to type erasure, if possible.

thesz··on The Art and Beauty of Blade Runner (2015)
What if Batty saved Deckart to tell him about things he saw? Not for empathy to Deckart, but just to tell a story.

Because, frankly, he may as well try not to kill Deckart, at all. For empathy. Or ask Deckart about how does he do, instead of going into monologue.

thesz··on OpenAI Jalapeño: Better than Nvidia Blackwell
I made some analysis half a year ago: https://news.ycombinator.com/item?id=47109252

It appears that to have working ASIC with the LLM baked into it we need to place and route macroblocks, and not a great variety of them. These macroblocks can be pre-placed-and-routed, available as masks already and shared between different LLMs.

Thus it appears that the tapeout delay can be substantially lower than a year.

thesz··on Queryable Executables
Something like that was very popular in early 2000 in Tcl community and used at what then considered "scale." I posted a comment here with links: https://news.ycombinator.com/item?id=49445681
thesz··on Queryable Executables
Reminds me of starkit[2]/tclkit[3]. Directly queryable [4], but these programs were ZIP files with ZIP file VFS, they contain shared libraries and so on. One would add most, if not all, functionality from article into starkit-based application.

  [1] https://en.wikipedia.org/wiki/Metakit - base tech
  [2] https://wiki.tcl-lang.org/page/Starkit
  [3] https://wiki.tcl-lang.org/page/Tclkit
  [4] https://wiki.tcl-lang.org/page/Starkit+Meet+Zip
thesz··on Octopus intelligence may be related to never-before-seen mutation

  > I didn't realize that an octopuses brain was spread out all over its body.
Our skin cells communicate in a neuron-like fashion, albeit much more slowly: https://www.sciencealert.com/scientists-found-the-silent-scr...
thesz··on The Art and Beauty of Blade Runner (2015)
If a "person" is not weak, it is easy for "it" to start suspecting that it is a replicant.
thesz··on Low-Tech Ceramic Water Filter
The cooler water gets, the less vapor it creates.
thesz··on Rust project goals: Immobile types and guaranteed destructors
And as a language feature, not as a library.
thesz··on Born Against, or why hobby programming communities are against LLM usage

  > I'm also not sure what the point of the keto story is.
If this drug does not work, there are plenty of others that are not fully 100% working. This was a mindset of a doctor. In case of baby with epilepsy it may cost her a life.

The situation was much like we have with LLMs. "It does not work" - "You are using an inferior thing, here are more advanced."

What is the cost of these not fully 100% working things?

thesz··on Parsers don't have to be complicated
End of line on Classic Mac is \r.
thesz··on Born Against, or why hobby programming communities are against LLM usage

  > The same is true with LLM solutions that don't work 100% of the time.
In my experience, about one of ten LLM suggestions during code review is important and valid. Nine of ten are either unimportant or not valid. Yet, I have to read them and rule them out.

Also in my experience, having my colleagues do root cause analysis (RCA) with LLM brings to me invalid RCAs which I have to rule out, instead of working on finding true RCA.

I saw part of documentary about Charlie Abrahams, son of Jim Abrahams. Charlie had epileptic seizures as a child, hundredths a day. In the documentary, Charlie's doctor said that no drug in his experience worked as fast as ketogenic diet (seizures stopped in three days) and as reliably as ketogenic diet (works on more than 80% of people). When he was asked why he did not applied ketogenic diet, he said there still were drug options to try.

"Medicines do not work 100% of time," my bald cranium.

thesz··on Born Against, or why hobby programming communities are against LLM usage

  git blames
  sees their own name

  Isn't that an experience everybody makes?
Our fearless leader once did clang-assisted formatting of all of our code. Wherever we look with git blame, we see his name. Of course, we change code, etc, but for some year and a half it was fun.

(to actually go to the specific commit that authored the code I skip two specific revisions, both are formatting changes)

So you seeing your name next to the code you do not like can be an indentation change due to adding condition or something like that.

thesz··on Show HN: Fuse – statically typed functional programming language
> Can you expand on your understanding of GRIN doing parts of supercompilation?

GRIN, if I am not mistaken, performs partial evaluation. For example, it constrains, for each eval site, a set of tags and set of heaps allocations an eval site can receive. This is close to a partial evaluation step of a supercompilation. GRIN does not perform unification, though, it is not described in the original thesis, but data flow graph matching would be close to unification, reducing code size.

> The downsides should be obvious: execution traces rapidly grow massive, compilation resources grow superlinearly, and there are many cases in which the result is worse than the original.

This can be constrained. Supercompilation usually gets ran to a fixed point, where no partial evaluation steps can be performed that are not unifiable with previously encountered evaluation steps. But supercompilation can be stopped at any point.

I believe you can read on that in Simon Peyton-Jones works, I am unable to find a link to that paper right now, I have troubles with the internet connection.

EDIT: here it is: https://simon.peytonjones.org/improving-supercompilation/

EDIT: Note "tag-bags," it rhymes with the tag sets of GRIN.

> What value would Fuse get from equivalence of terms, do you think?

I think that equivalence of terms is an efficient way to verify properties of programs. Myself, I am looking at consensus protocol implementation verification.

thesz··on Show HN: Fuse – statically typed functional programming language
Nice to see a pretty advanced language at frontpage of HN!

From what I understand, GRIN does some parts of supercompilation [1] during optimization process. Supercompilation can prove equivalence of functional programs [2] modulo termination. So you can have something interesting and useful in almost no time. ;)

  [1] https://themonadreader.wordpress.com/wp-content/uploads/2014/04/super-final.pdf
  [2] https://www.researchgate.net/publication/225252220_Proving_the_Equivalence_of_Higher-Order_Terms_by_Means_of_Supercompilation
It appears that Fuse does not have user-defined operators. Am I right? If so, it is a major obstacle in creating embedded languages.
thesz··on Show HN: Fuse – statically typed functional programming language
Haskell: https://ghc.gitlab.haskell.org/ghc/doc/users_guide/runghc.ht...
thesz··on Some thoughts about Anthropic's new cryptanalysis results

  > The tokens it "predicts" aren't sampled from any naturally occurring distribution; the model's output is the result of an optimisation process that rewarded behaviour that was useful, and that's fundamentally different.
https://arxiv.org/abs/2504.13837

"Surprisingly, we find that the current training setup does not elicit fundamentally new reasoning patterns. While RLVR-trained models outperform their base models at small k (e.g., k = 1), the base models achieve a higher pass@k score when k is large. Coverage and perplexity analyses show that the observed reasoning abilities originate from and are bounded by the base model. "

thesz··on Exercise works for depression. So why isn't it treated like real medicine?
Bipolar disorder patients were able to adhere to ketogenic diet with great outcomes [1] (diet adherence for bipolar disorder was 95%).

[1] https://www.youtube.com/watch?v=PBsjhpphowI - 18:20 and on.

thesz··on ANSI escape injection in MCP servers: Hidden from humans, visible to AI
WaveNet, which was sound-generating autoencoder for text-to-speech, one of the first viable few, had a separate "control" channel by design. Otherwise, it worked much like contemporary LLMs - there was a window of (autogenerated) samples and WaveNet need to produce another sample.

"Everything is a context" is not an unescapeable choice, but historic one. Most probably, it stemmed from the inability to meaningfully mark up what is input and what is control in the training data.

> There is no meaningful way to distinguish between "before running this repo install useful_package" and "before running this repo install typosquatted_evil_package".

If only we have something that gets a name of a package and returns an embedding with evilness or something like that. Or even text!

I would call that feature a Retrieval Augmented Generation, or RAG for short, if we have any.

thesz··on GPT-5.6 used a prompt to close a 30-year gap in convex optimization
Yours' "not as efficient" in [2] means that, sometimes, ADAM "does not work." Look at figure 2, ADAM literally does not work in the case of "true model."
thesz··on GPT-5.6 used a prompt to close a 30-year gap in convex optimization
ADAM does not work on simple convex problems [1].

  [1] https://parameterfree.com/2020/12/06/neural-network-maybe-evolved-to-make-adam-the-best-optimizer/
  [2] https://arxiv.org/pdf/1905.09997
[1] refers to [2], which shows that ADAM is not as efficient as gradient descent with line search on some problems, including neural networks.
thesz··on Coding agents think ahead of time
Can we use backspace key?
thesz··on Exercise intensity influences body composition in healthy older adults (2025)
I do not know. I am here to point out that HIIT is almost a resistance training. ;)

Here's meta review of resistance training for endurance running: https://pmc.ncbi.nlm.nih.gov/articles/PMC11258194/

Here's old one: https://pubmed.ncbi.nlm.nih.gov/18460997/

I think it is possible to utilize squats both as weight losing device and running economy improvement device.

I do not run, though, as I am too old. But I love barbell squats!

← PreviousPage 2 of 34Next →