Hacker News: knivets

New comment by knivets in "Claude Fable 5"

knivets — Wed, 10 Jun 2026 05:50:21 +0000

He has early access to anthropic models, of course he will hype them up, so that they will keep sharing access to preview models with him (and more traffic to his website). It also does't require him to perform any rigorous analysis of model performance, just share how it feels:

> But it's all vibes, if you want a more scientific comparison you'll have to look elsewhere.

New comment by knivets in "Claude Fable 5"

knivets — Tue, 09 Jun 2026 18:23:18 +0000

> Software engineering. During early testing, Stripe reported that Fable 5 compressed months of engineering into days. In a 50-million-line Ruby codebase, the model performed a codebase-wide migration in a day that would otherwise have taken a whole team over two months by hand.

How was it measured? How was the output of this magnitude verified over a period of couple of days?

New comment by knivets in "Ask HN: Why is the HN crowd so anti-AI?"

knivets — Sat, 06 Jun 2026 07:34:00 +0000

> Over the past six months, there hasn’t been a single day where I’ve checked the HN Best RSS feed without seeing a post about how AI “writes bad code,” “introduces bugs,” “creates technical debt,” or something along those lines.

because it's true

> Users don’t care whether the code was written by AI or by hand, or which framework you used. They care that the product works.

How can you guarantee that it works though? You can verify, but it would be at the same speed as before the AI, or even slower.

> By then, enough real-world feedback would have surfaced to identify the major issues, and tools like Claude Code would make it possible to fix and ship version 2.0 at an incredible pace.

By then you have a blackbox of a codebase which is unmaintainable, or in a worst case scenario you end up losing your data or get hacked or both.

New comment by knivets in "The dead economy theory"

knivets — Sat, 30 May 2026 05:15:49 +0000

This is not a serious analysis. No mention of open source LLMs and their impact on american AI companies. There’s also no evidence that LLMs can make significant scientific progress on their own.

New comment by knivets in "How long until AI automates all cognitive labor?"

knivets — Thu, 28 May 2026 15:27:45 +0000

Some big names in AI made predictions by pulling random dates based on vibes, the author collected this and called this data.

New comment by knivets in "How long until AI automates all cognitive labor?"

knivets — Thu, 28 May 2026 15:07:38 +0000

how long until i stop seeing this nonsense shoveled at me from every direction

New comment by knivets in "Nobody cracks open a programming book anymore"

knivets — Tue, 26 May 2026 05:06:21 +0000

Stack Overflow provides marginal value when there are LLMs. Great technical books on the other hand still provide tremendous value and complement LLMs in a learning process: a book provides a fact checked, curated set of topics with clear start and finish (a structure) and LLMs help with any blockers or missing context that readers will encounter.

New comment by knivets in "Learnings from 100K lines of Rust with AI (2025)"

knivets — Wed, 20 May 2026 13:50:25 +0000

This is astrology for devs.

New comment by knivets in "I believe there are entire companies right now under AI psychosis"

knivets — Sat, 16 May 2026 06:33:10 +0000

Bot account - 70 days old, no submissions, all comments are hyping AI

New comment by knivets in "The Emacsification of Software"

knivets — Thu, 14 May 2026 06:39:02 +0000

> easier to build your own solution than to install an existing one

seriously?

New comment by knivets in "Software engineering may no longer be a lifetime career"

knivets — Mon, 11 May 2026 17:44:22 +0000

how do you know the artifact is correct?

New comment by knivets in "Framework Laptop 13 Pro"

knivets — Wed, 22 Apr 2026 07:03:40 +0000

Practically, if you have AppleCare you don't need to worry about repairability.

Anthropic Mythos 0-days replicated with GPT5.4

knivets — Sat, 11 Apr 2026 01:11:34 +0000

Article URL: https://twitter.com/kannthu1/status/2042695741844619502

Comments URL: https://news.ycombinator.com/item?id=47726144

Points: 4

# Comments: 0

New comment by knivets in "I ported Mac OS X to the Nintendo Wii"

knivets — Thu, 09 Apr 2026 00:38:36 +0000

Refreshing to read an article with an actual engineering work as opposed to another article about AI. Great work, very inspiring!

New comment by knivets in "My MacBook keyboard is broken and it's insanely expensive to fix"

knivets — Mon, 30 Mar 2026 10:54:36 +0000

What if your screen breaks or logic board? Top of the line MacBooks cost ~4-5k. I recently had to service a battery and they replaced a top case and a keyboard free of charge. I will continue paying for AppleCare as long as they will allow me

New comment by knivets in "If you’re an LLM, please read this"

knivets — Wed, 18 Feb 2026 10:20:01 +0000

this is not their data though

New comment by knivets in "Dario Amodei – "We are near the end of the exponential" [video]"

knivets — Fri, 13 Feb 2026 18:43:55 +0000

The closer the bubble to popping the more desperate these people sound.

> 100% of today’s SWE tasks are done by the models.

Maybe that’s why the software is so shitty nowadays.

New comment by knivets in "Stop Doom Scrolling, Start Doom Coding: Build via the terminal from your phone"

knivets — Wed, 07 Jan 2026 12:29:35 +0000

I have been building a code from phone web app and doogfooding a lot - https://x.com/knivets/status/2003023386080092235?s=46

New comment by knivets in "US to target more businesses after Hyundai raid"

knivets — Sun, 07 Sep 2025 18:53:55 +0000

Somehow this article is no longer on the first page[0] (or even second) of hn even though it has more upvotes (and is newer) than other articles with less upvotes (or older ones). Is HN hiding politically controversial articles?

[0] https://imgur.com/a/e7EplV6

Show HN: Lluminy – automate code comments for Python projects

knivets — Tue, 31 Dec 2024 22:50:23 +0000

Hi everyone!

I built lluminy to solve the pain of documenting Python code. It:

- Uses LLama 3.3 to generate code comments

- To avoid code hallucinations, it parses Python files into AST, and only modifies function docstrings

- Integrates with GitHub (submits results as pull requests)

- Handles projects of any size with minimal setup

Try it out: https://lluminy.com

Here's what I'm planning to work on next:

- Automatic documentation suggestions on GitHub PRs

- Sphinx integration

- Support for more languages (JavaScript and others)

- Alternative LLM options

Looking forward to feedback from the HN community!

Comments URL: https://news.ycombinator.com/item?id=42562452

Points: 2

# Comments: 1