Hacker News Reader

Agents are very good at making us think the tower is rising, when in fact it is falling beneath our feet.

__0x01on The Writers Who Wrote the Most in History

Thanks for this. I especially enjoyed the section on word counting software and word linking games.

__0x01on An OpenAI model has disproved a central conjecture in discrete geometry

From the companion paper:

> The argument relies crucially on ideas that may, at least in retrospect, be attributed to Ellenberg-Venkatesh, Golod-Shafarevich, and Hajir-Maire-Ramakrishna.

Can someone please elaborate on this?

__0x01on Everything in C is undefined behavior

> A problem with this is that in order to confirm the findings, you’ll need an expert human. But generally expert humans are busy doing other things.

The article suggests using LLMs to identify and fix UB. However as per the above, I think the issue is that we need more expert humans.

LLM generated code will eventually contain UB.

EDIT: added "eventually"

__0x01on We rewrote JSONata with AI in a day, saved $500k/year

> Correctness: 1,778 test cases from the official jsonata-js test suite + 2,107 integration tests in the production wrapper.

The AI generated code can still introduce subtle bugs that lead to incorrect behaviour.

One example of this is the introduction of functions into the codebase (by AI) that have bugs but no corresponding tests.

EDIT: correct quotation characters

__0x01on OpenAI is walking away from expanding its Stargate data center with Oracle

Can a datacenter practicably upgrade to the next generation of GPU every year?

__0x01on The Brand Age

What was the interesting problem that Swiss watchmakers could have focused on, instead of pursuing brand?

__0x01on There is an AI code review bubble

Please can you elaborate? We are more intersted in "the end" in what sense?

__0x01on There is an AI code review bubble

Is "AI code review" a correct term?

A code review requires reasoning and understanding, things that to my knowledge a generative model cannot do.

Surely the most an AI code review ever could be is something that looks like a code review.

__0x01on AI Destroys Institutions

> This is nothing but speculation

Did you read the paper?

__0x01on Claude Cowork exfiltrates files

I also worry about a centralised service having access to confidential and private plaintext files of millions of users.

__0x01on Don't fall into the anti-AI hype

Often when I look closely at the output of LLM generated code, I see repetition, redundant logic and deeply hidden bugs.

Notwithstanding the above, to my understanding LLM services are currently being sold below cost.

If all of the above is true, at some point the degredation of quality in codebases that use these tools will be too expensive to ignore.

__0x01on How to code Claude Code in 200 lines of code

These LLM tools appear to have an unprecedented amount of access to the file systems of their users.

Is this correct, and if so do we need to be concerned about user privacy and security?

__0x01on Sugar industry influenced researchers and blamed fat for CVD (2016)

Please can you provide a source for the above?

__0x01on Sugar industry influenced researchers and blamed fat for CVD (2016)

My understanding was that atherosclerotic plaques are comprised of cholesterol or fatty deposits [1] and that these can lead to CVD.

The fat mechanism I understand, but what is the mechanism for sugar in CVD?

[1] https://www.heart.org/en/health-topics/cholesterol/about-cho...

__0x01on Elevated errors across many models

Engineering Room, panning over a bunch of hot Blackwells

"I can't change the laws of physics!"

__0x01on Claude Is Down

The monster babbleth no more, sire.

__0x01on Vibe engineering

Is cost a risk here? I'm assuming that sometime in the future the price for vibe coding/engineering will go up significantly.

__0x01on Blender 4.5 LTS

I have noticed that many of the most used and loved projects use C/C++.

With all of the unpopular press that they get, why has history often proven C/C++ to be the right choice time and time again?

__0x01on Telo MT1

Is this cheaper to run than the gas equivalent?

__0x01on Phoenix.new – Remote AI Runtime for Phoenix

What LLM does Phoenix.new use?

__0x01on The Languages of English, Math, and Programming

I thought this was going to be an essay on the impact of English, Math and Programming on humanity.

I would place English (or all spoken/written languages in general) first, Math (as discovered) second, and programming languages last.

__0x01on The Death of the Magazine

honest-broker is the only Substack publication I have found to consistently hold my attention. Reading Gioia's writing feels like eating nutritious food.

I am most likely ignorant, however. Are there any other Substack publications of the same quality?

__0x01on GPTs and Hallucination

This is the most prescient point I have read hitherto regarding LLMs. We are fashioning for ourselves gods of wood and stone.

__0x01on Debugging in the Multiverse

Is this designed to be run in production?

__0x01on AI solves International Math Olympiad problems at silver medal level

Please could someone explain, very simply, what the training data was composed of?

__0x01on Panic at the Job Market

"October 2008

The economic situation is apparently so grim that some experts fear we may be in for a stretch as bad as the mid seventies.

When Microsoft and Apple were founded." [1]

"A programmer can sit down in front of a computer and create wealth. A good piece of software is, in itself, a valuable thing." [2]

These words give me hope.

[1] https://paulgraham.com/badeconomy.html [2] https://paulgraham.com/wealth.html

__0x01on Binance built a 100PB log service with Quickwit

Error level logging can exist with a metrics focused approach.

__0x01on How to think in writing

What books can I read to reason like this?

EDIT: shortened sentence

__0x01on Ship Something Every Day

My final draft is often completely different to my first draft, which I wouldn’t want to ship.

Most of the time I only start to see the real shape of the solution after a few days of work.

Those iterations each day have value as they propel me toward a solution. But it’s more of an internal type of shipping. I’m shipping to myself.