Hacker News: clbrmbr

New comment by clbrmbr in "I paid people to try and follow my README"

clbrmbr — Sun, 11 Oct 2026 14:09:14 +0000

isnt this what footnotes are for?

New comment by clbrmbr in "More questions about whether researchers can trust OpenAI with unpublished math"

clbrmbr — Thu, 10 Sep 2026 16:08:13 +0000

my understanding is that a sufficiently large model will memorize the training data once enough representations are built up. Opus 4 scale seems to have been sufficient. cf NYT vs OAI.

New comment by clbrmbr in "Netherlands pulls gold out of the US for fears of 'geopolitical unrest'"

clbrmbr — Sat, 05 Sep 2026 11:12:00 +0000

(another guess) to convert to dollars, the gold would need to be delivered to the custody of the US Fed, which is easiest when the bars are physically in the Fed's vault. in a low-trust situation, you have all the gold in your own country, but then its so much leas liquid bc you need to physically deliver it to trading partners, or they must trust your accounting of their share in your vault.

New comment by clbrmbr in "Async Rust vs RTOS showdown (2022)"

clbrmbr — Thu, 03 Sep 2026 13:47:49 +0000

ikr? ive been really hoping to be embedded already but Zephyr/C seema still the pragmatic choice for most embedded.

bump up to EmbeddedLinux and i think Rust wins ovr C

New comment by clbrmbr in "Verschlimmbesserung: The Word Your Software Updates Need"

clbrmbr — Fri, 28 Aug 2026 18:45:16 +0000

It's totally plausible portmanteau. I get the feeling thought that it sounds more marked in English than in German where these kind of mashups are formed more freely.

New comment by clbrmbr in "Show HN: The load-bearing vocabulary of Claude"

clbrmbr — Thu, 27 Aug 2026 16:05:59 +0000

@labo333 do u think soon we may need a dictionary? ive been playing with something u may like, but my approach has been to ask for definitions in-session so hard to do from outside.

https://www.themachinevernacular.net/

New comment by clbrmbr in "Felony charges for citizen deleting phone data at US Border"

clbrmbr — Wed, 26 Aug 2026 16:54:08 +0000

whoah. with direct demo, whats going on over there?

New comment by clbrmbr in ""Famous Deep Learning Papers", David Bau"

clbrmbr — Wed, 26 Aug 2026 16:51:35 +0000

Bau is awesome. He is often the adult in the room who asks "but why", and cares deeply about human understanding. I am very bullish on Northeastern.

New comment by clbrmbr in "JIT Compiling Code in 5μs"

clbrmbr — Sun, 23 Aug 2026 10:20:23 +0000

is an xtensa lx7 (esp32-s3) target available that does not use llvm?

New comment by clbrmbr in "Felony charges for citizen deleting phone data at US Border"

clbrmbr — Sat, 22 Aug 2026 01:17:10 +0000

shudder. but, where else could we go? switzerland? my point being we need to try to get 1995 back. id gladly trade my iphone for a car phone.

New comment by clbrmbr in "Vomit: Clean up Claude 5's token output with a separate LLM"

clbrmbr — Fri, 21 Aug 2026 01:53:35 +0000

Indeed I think much is shared across sessions and projects. I say we learn The Machine Vernacular [1].

[1] https://www.themachinevernacular.net/

New comment by clbrmbr in "Pacing model development in an era of cyber-critical capabilities"

clbrmbr — Thu, 20 Aug 2026 11:53:29 +0000

> let a coding agent run loose with them without approving every tool use

You should try. There’s a difference in kind between approving each tool use and spinning up an all-night session with full permissions to run any tools, encouraged to run subagents to preserve context.

New comment by clbrmbr in "GLM-5.3: Frontier coding with emergent cyber capabilities"

clbrmbr — Sat, 15 Aug 2026 03:09:07 +0000

How are you using it in Claude Code? What is the native harness that GLM was post-trained in?

New comment by clbrmbr in "To save C, we must save ABI (2022)"

clbrmbr — Sat, 15 Aug 2026 01:52:27 +0000

Creating on-demand automations for an ESP32-based product, that includes driving a display up to 1000px.

New comment by clbrmbr in "To save C, we must save ABI (2022)"

clbrmbr — Sat, 15 Aug 2026 01:49:37 +0000

Oh just that it made me confront ABIs. I have a special purpose use case (home automation), so I wasn’t worried about general purpose compilation, just the subset of lua that fable tends to write for the prompt we use.

I have no idea how it’s implemented. Lua goes in, position-independent dependency-free xTensa LX7 code comes out the other. Maybe I should read the code?

It’s extremely fast. 3kB of lua becomes 1kB of machine code. I’ll have to get a blog post together on it.

New comment by clbrmbr in "Why does Opus 5 feel worse to work with?"

clbrmbr — Sat, 15 Aug 2026 01:20:09 +0000

Fable 5 is the model you work with, Opus 5 is the model Fable works with… it’s meant as a subagent.

New comment by clbrmbr in "To save C, we must save ABI (2022)"

clbrmbr — Tue, 11 Aug 2026 11:07:43 +0000

I was battling GCC… until the new guy (a smart business major) pointed out I could just compile from Lua to ASM directly. Claude was happy to write a compiler over night. :facepalm:

New comment by clbrmbr in "Water system controllers don't belong on the internet, says ex-NSA chief"

clbrmbr — Tue, 11 Aug 2026 00:22:24 +0000

The range on one RF system I worked on was 2mi with a wet noodle for an antenna.

New comment by clbrmbr in "What's the best programming language for coding agents?"

clbrmbr — Tue, 11 Aug 2026 00:20:46 +0000

I discovered last week that Fable 5 can write perfect xTensa LX7 assembler code without tools or references. Mind blown.

But, when working on a creative graphics task, the results were best in Lua, middling in integer-only C, and underwhelming in ASM in terms of creative depth.

New comment by clbrmbr in "Water system controllers don't belong on the internet, says ex-NSA chief"

clbrmbr — Sun, 09 Aug 2026 14:53:51 +0000

You just need to be able to remotely take over a system with a compatible radio within range.

That’s why I’m so concerned about Bluetooth