Hacker News: Artgor

New comment by Artgor in "A Backlash Against Anthropic Is Brewing in Silicon Valley"

Artgor — Wed, 29 Jul 2026 12:05:48 +0000

Claude Code made Anthropic the favourite LLM provider for many SWE. But the public PR failures and the issues with token consumption in Spring 2026 eroded the trust.

New comment by Artgor in "Sam Altman says AI won't shorten the workweek because humans enjoy being busy"

Artgor — Wed, 29 Jul 2026 09:48:05 +0000

being busy != working

New comment by Artgor in "Is Kimi K3 Better Than Opus? It Was Until Opus 5"

Artgor — Fri, 24 Jul 2026 19:08:59 +0000

Insert a meme "The world's new most powerful AI model"

New comment by Artgor in "Andrew Ng made an open source agent"

Artgor — Fri, 24 Jul 2026 08:56:53 +0000

How is it different from literally any other wrapper?

New comment by Artgor in "No one wants to be the boss: Why is Gen Z turning down promotions?"

Artgor — Wed, 22 Jul 2026 13:22:38 +0000

Well, yeah - middle-level management is one of the worst positions to be in. You have a lot of responsibilities, but not enough ways to influence things. And the pay often isn't higher than before.

New comment by Artgor in "Writing by Hand is Good for your Brain"

Artgor — Wed, 22 Jul 2026 10:00:58 +0000

"Don’t use a pencil (or a cheap ballpoint)"

I think that at this point, the idea becomes just a gatekeeping.

I have been writing notes in notebooks by my hand for years. But gradually I switched to typing notes in a notepad or drawing with a stylus on a gadget - and I don't notice any real difference.

Starting and iterating on a Kaggle competition in Google Antigravity

Artgor — Fri, 10 Jul 2026 10:37:16 +0000

Article URL: https://andlukyane.com/blog/kaggle-antigravity-s6e7

Comments URL: https://news.ycombinator.com/item?id=48858152

Points: 1

# Comments: 0

Cayley graph search with Claude Code: what puzzle competitions look like in 2026

Artgor — Wed, 08 Jul 2026 14:40:28 +0000

Article URL: https://andlukyane.com/blog/cayleypy-kaggle-with-claude

Comments URL: https://news.ycombinator.com/item?id=48832621

Points: 3

# Comments: 0

Testing MiniMax M3 on refactoring, screenshot debugging, music recommendations

Artgor — Wed, 10 Jun 2026 16:48:11 +0000

Article URL: https://andlukyane.com/blog/minimax-m3

Comments URL: https://news.ycombinator.com/item?id=48479066

Points: 3

# Comments: 0

Testing MiniMax M2.7 via API on three real ML and coding workflows

Artgor — Wed, 20 May 2026 04:51:42 +0000

Article URL: https://andlukyane.com//blog/minimax-m27-workflows

Comments URL: https://news.ycombinator.com/item?id=48203249

Points: 30

# Comments: 2

New comment by Artgor in "Muse Spark: Scaling towards personal superintelligence"

Artgor — Wed, 08 Apr 2026 16:29:43 +0000

I'm cautiously waiting for the feedback from the first users. Meta has produced a lot of great models (LLama), maybe this is a comeback... but I'm cautious, as the jump in the quality is almost too high.

Also, I think people aren't used that using such models requires meta.ai or meta ai app.

New comment by Artgor in "Take better notes, by hand"

Artgor — Mon, 30 Mar 2026 19:30:03 +0000

I love writing things down when I brainstorm; it helps me think. But taking notes by hand is not feasible for me. My handwriting is atrocious (always has been); if I want to write a nice-looking text, I have to slow down significantly, and then it becomes too slow. Also, searching, indexing, and everything - it works better with digital.

Redesigning My Personal Website with Claude Code

Artgor — Mon, 23 Mar 2026 11:18:41 +0000

Article URL: https://andlukyane.com//blog/redesigning-my-personal-website

Comments URL: https://news.ycombinator.com/item?id=47487899

Points: 2

# Comments: 1

New comment by Artgor in "Ask HN: Share your personal website"

Artgor — Wed, 14 Jan 2026 20:19:51 +0000

https://andlukyane.com/ - I write paper reviews, share experience of working in ML and my language learning journey.

New comment by Artgor in "Yearly analytics on my spaced repetition results"

Artgor — Mon, 05 Jan 2026 19:00:16 +0000

I prefer to start immersion at ~B1 level. I know some people want to do comprehensive input right from the start, but I prefer to build foundations. I start with popular books that I have already read before - The Little Prince, Harry Potter, etc. Then I take books that are interesting for me and work through them. There are graded readers, but the stories are usually very boring. I prefer to read what I like.

New comment by Artgor in "Yearly analytics on my spaced repetition results"

Artgor — Mon, 05 Jan 2026 16:24:44 +0000

I sympathise. I did ~200k reviews in Anki and no idea how many in Renshuu in 2025 for language learning: German, Spanish and Japanese... and I think I got into Anki hell. For a long time, Anki was really useful for me, it pushed my Spanish and German forward, but now I plan to decrease the number of reviews significantly. I hope to spend no more than 30 minutes per day of flashcards, and the rest of time on immersion.

StackOverflow: An experiment on pairing askers with experts in the community

Artgor — Fri, 30 May 2025 11:42:19 +0000

Article URL: https://meta.stackoverflow.com/questions/433999/an-experiment-on-pairing-askers-with-experts-in-the-community

Comments URL: https://news.ycombinator.com/item?id=44135182

Points: 2

# Comments: 0

New comment by Artgor in "AI: Accelerated Incompetence"

Artgor — Wed, 28 May 2025 12:13:22 +0000

You know, sometimes I feel that all this discourse about AI for coding reflects the difference between software engineers and data scientists / machine learning engineers.

Both often work with unclear requirements, and sometimes may face floating bugs which are hard to fix, but in most cases, SWE create software that is expected to always behave in a certain way. It is reproducible, can pass tests, and the tooling is more established.

MLE work with models that are stochastic in nature. The usual tests aren't about models producing a certain output - they are about metrics, that, for example, the models produce the correct output in 90% cases (evaluation). The tooling isn't as developed as for SWE - it changes more often.

So, for MLE, working with AI that isn't always reliable, is a norm. They are accustomed to thinking in terms of probabilities, distributions, and acceptable levels of error. Applying this mindset to a coding assistant that might produce incorrect or unexpected code feels more natural. They might evaluate it like a model: "It gets the code right 80% of the time, saving me effort, and I can catch the 20%."

New comment by Artgor in "Claude 4"

Artgor — Thu, 22 May 2025 16:52:25 +0000

OpenIA's Codex-1 isn't so cool anymore. If it was ever cool.

And Claude Code used Opus 4 now!

New comment by Artgor in "Ask HN: Cursor or Windsurf?"

Artgor — Mon, 12 May 2025 06:51:09 +0000

Claude Code. And... Junie in Jetbrains IDE. It appeared recently and I'm really impressed by its quality. I think it is on the level of Claude Code.