Hacker News: kesor

New comment by kesor in "Your File System Is Already A Graph Database"

kesor — Wed, 08 Apr 2026 17:43:03 +0000

So you have some folders with markdown files ... which are insanely hard to query without a tool ... impossible to traverse via their relationships ... and you call that a graph database? WHAT?!

Clicked the link expecting to see some tool or method that actually allows graph-like queries and traversals on files in a file system, all I found was some rant about someone on the internet being wrong.

Waste of time.

New comment by kesor in "US economy unexpectedly sheds 92k jobs in February"

kesor — Fri, 06 Mar 2026 15:38:51 +0000

160,000 if you take the revisions into account

New comment by kesor in "Phoenix: A modern X server written from scratch in Zig"

kesor — Thu, 25 Dec 2025 07:55:58 +0000

I would argue that Desktop Linux finally took off because of Steam Proton, and because of Windows 10/11 and macOS starting version fartascular or whatever their versions are named.

New comment by kesor in "OpenSCAD is kinda neat"

kesor — Sat, 20 Dec 2025 21:14:30 +0000

OpenSCAD can load STLs and cut holes in them.

New comment by kesor in "If you're going to vibe code, why not do it in C?"

kesor — Fri, 12 Dec 2025 13:31:14 +0000

Diffusion models for images are already pretty much binary code generators. And we don't need to treat each bit individually, even in binary code there are whole segments that can be tokenized into a single token.

Regarding training, we have many binaries all around us, for many of them we also have the source code in whichever language. As a first step we can use the original source code and ask a third party model to explain what it does in English. Then use this English to train the binary programmer model. Eventually the binary programmer model can understand binaries directly and translate them to English for its own use, so with time, we might not even need binaries that have source code, we could narrate binaries directly.

New comment by kesor in "If you're going to vibe code, why not do it in C?"

kesor — Wed, 10 Dec 2025 03:17:46 +0000

Why would you think its more complex? There are less permutations of generating transistor on/off states than there are all the different programming languages in use that result in the exact same bits.

Who said that creating bits efficiently from English to be computed by CPUs or GPUs must be done with transformer architecture? Maybe it can be, maybe there are other ways of doing it that are better. The AI model architecture is not the focus of the discussion. It is the possibilities of how it can look like if we ask for some computation, and that computation appears without all the middle-men layers we have right now, English->Model->Computation, not English->Model->DSL->Compiler->Linker->Computation.

New comment by kesor in "If you're going to vibe code, why not do it in C?"

kesor — Wed, 10 Dec 2025 01:41:38 +0000

You are missing the whole point of the article.

New comment by kesor in "If you're going to vibe code, why not do it in C?"

kesor — Wed, 10 Dec 2025 01:39:56 +0000

You, like many others, seem to imply that humans write "good" code, but they absolutely do not--unless they are running some million dollar team with checks and cross checks and years of evolving the code over failures. I've tested every junior developer using simple Javascript leetcode quizes and they all produce erroneous spaghetti slop.

The difference is, we forgive humans for needing iteration. We expect them to get it wrong first, improve with feedback, and learn through debugging. But when AI writes imperfect code, you declare the entire approach fraudulent?

We shouldn't care about flawless one-shot generations. The value is in collapsing the time between idea and execution. If a model can give you a working draft in 3 seconds - even if it's 80% right - that's already a 10x shift in how we build software.

Don't confuse the present with the limit. Eventually, in not that many years, you'll vibe in English, and your AI co-dev will do the rest.

New comment by kesor in "If you're going to vibe code, why not do it in C?"

kesor — Wed, 10 Dec 2025 01:33:29 +0000

Why you hate on prose? This article has been a joy to read, unlike a lot of the other slop on the internet.

New comment by kesor in "If you're going to vibe code, why not do it in C?"

kesor — Wed, 10 Dec 2025 00:51:10 +0000

Binary bits are also a language. A structured language that transistor-based computers execute into some result we humans find valuable. Why wouldn't a model be able to write these binary instructions directly? Why do we need all these layers in between? We don't.

New comment by kesor in "If you're going to vibe code, why not do it in C?"

kesor — Wed, 10 Dec 2025 00:49:34 +0000

Probably because then it wouldn't be software anymore. That is because you will be required to do a physical process (print an integrated circuit) in order to use the functionality you created. It can definitely be done, but it takes it too far away from the idea the author expressed.

But I don't see a reason why the LLM shouldn't be writing binary CPU instructions directly. Or programming some FPGA directly. Why have the assembly language/compiler/linked in between? There is really no need.

We humans write some instructions in English. The LLM generates a working executable for us to use repeatedly in the future.

I also think it wouldn't be so hard to train such a model. We have plenty of executables with their source code in some other language available to us. We can annotate the original source code with a model that understands that language, get its descriptions in English, and train another model to use these descriptions for understanding the executable directly. With enough such samples we will be able to write executables by prompting.

New comment by kesor in "If you're going to vibe code, why not do it in C?"

kesor — Wed, 10 Dec 2025 00:44:37 +0000

I don't think there is a need for an output language here at all, the LLM can read and write bits into executables directly to flip transistors on and off. The real question is how the input language (i.e. prompts) look like. There is still a need for humans to describe concepts for the machine to code into the executable, because humans are the consumers of these systems.

New comment by kesor in "If you're going to vibe code, why not do it in C?"

kesor — Wed, 10 Dec 2025 00:40:17 +0000

Don't train them to emulate humans. Train them to emulate compilers instead.

New comment by kesor in "If you're going to vibe code, why not do it in C?"

kesor — Wed, 10 Dec 2025 00:39:35 +0000

No need for using assembler, LLMs should be writing machine bits directly into executables. It is also fairly simple to teach them how to do it. Provided we have some executable that was written in some human-readable computer language. We can read through the bits of the executable, and describe each portion using English, based on the description of what the original human-readable language is doing. This new model will only learn the English representation of chunks of bits and how they go together into an executable. After learning several billion such narrated executables it will be excellent at writing machine code.

Michael Burry Foundations: My 1999 (and part of 2000)

kesor — Fri, 28 Nov 2025 13:20:11 +0000

Article URL: https://michaeljburry.substack.com/p/foundations-my-1999-and-part-of-2000

Comments URL: https://news.ycombinator.com/item?id=46078402

Points: 2

# Comments: 0

DoiT Alliance with Ingram Micro, Reshapes the Value of FinOps Worldwide

kesor — Thu, 13 Nov 2025 18:29:08 +0000

Article URL: https://finance.yahoo.com/news/doit-announces-strategic-alliance-ingram-130000713.html

Comments URL: https://news.ycombinator.com/item?id=45918579

Points: 1

# Comments: 0

DoiT and Ingram Micro Team on FinOps for AWS Partners

kesor — Thu, 13 Nov 2025 18:25:35 +0000

Article URL: https://www.channelinsider.com/channel-business/finops-aws-xvantage-integration/

Comments URL: https://news.ycombinator.com/item?id=45918535

Points: 1

# Comments: 0

New comment by kesor in "Dating: A mysterious constellation of facts"

kesor — Sun, 02 Nov 2025 05:52:24 +0000

So ... dating apps just need to remove text messages and replace them with voice messages. Problem solved. Thanks!

New comment by kesor in "Show HN: Why write code if the LLM can just do the thing? (web app experiment)"

kesor — Sun, 02 Nov 2025 05:44:08 +0000

This is just like vibe coding. In vibe coding, you snapshot the results of the LLM's implementation into files that you reuse later.

This project could use something like that. Perhaps ask the LLM to implement a way to store/cache the snapshots of its previous answers. That way, the more you use it, the faster it becomes.

Reinforcement Fine Tuning a Pangu Model

kesor — Wed, 22 Oct 2025 04:27:11 +0000

Article URL: https://www.youtube.com/watch?v=n5g6hgituDY

Comments URL: https://news.ycombinator.com/item?id=45664875

Points: 2

# Comments: 0