Hacker News: YuriNiyazov

New comment by YuriNiyazov in "Claudette: Make Claude stop talking like a BuzzFeed article"

YuriNiyazov — Sat, 22 Aug 2026 19:54:10 +0000

Very interesting, thank you!

New comment by YuriNiyazov in "Claudette: Make Claude stop talking like a BuzzFeed article"

YuriNiyazov — Sat, 22 Aug 2026 15:54:56 +0000

Wefunder

New comment by YuriNiyazov in "Claudette: Make Claude stop talking like a BuzzFeed article"

YuriNiyazov — Fri, 21 Aug 2026 18:54:07 +0000

My GH repo: https://github.com/yn/claude-output-styles

My LI post: https://www.linkedin.com/feed/update/urn:li:activity:7495167...

New comment by YuriNiyazov in "Claudette: Make Claude stop talking like a BuzzFeed article"

YuriNiyazov — Fri, 21 Aug 2026 16:33:19 +0000

It's easiest to explain this while anthropomorphizing the model, I know some folks here hate that, sorry about that. I heard an interesting diagnosis for why Claude does this: the output is a compressed version of its thought traces, very dense because the model is under pressure to use as few tokens as it can and to pack as much (for accuracy) of its concepts into the output.

One of the reasons that "don't do X" type of instructions work reliably is because you are telling the model "don't think of a pink elephant". There's also Anthropic's related research that shows that when you tell a model "don't do X", and it does X later for whatever reason, it starts acting more misaligned. This is because it thinks "well, I guess I am the sort of model that disobeys instructions, whatever" - this was specifically about cheating on tests, but you can imagine this happens in other contexts as well like following instructions on what kinds of text to output.

So, what you want to do is to avoid telling Claude "don't do X", and tell Claude "in your thoughts, in memories and various notes that you write, use your Claude-ese. In your output to humans, translate everything into long full sentences."

If anyone's interested, I can share my Claude Code output style that reflects this.

(Hi Adnan! Long time! (Adnan is an ex-coworker))

New comment by YuriNiyazov in "The Fabled Flatbreads of Uzbekistan (2015)"

YuriNiyazov — Tue, 28 Jul 2026 20:31:36 +0000

Theres Sofia (ex-Uzbek) and uzbegim, what’s the third one?

New comment by YuriNiyazov in "Claude, with feedback from ChatGPT, writes a history of AI"

YuriNiyazov — Sat, 18 Jul 2026 07:13:26 +0000

The writing style is grating, it's not a pleasant read.

New comment by YuriNiyazov in "AI coding is a nightmare. Am I the only one experiencing this?"

YuriNiyazov — Fri, 03 Jul 2026 03:39:43 +0000

What model are you running? With what settings?

New comment by YuriNiyazov in "Incident Report: Railway Blocked by Google Cloud (Resolved)"

YuriNiyazov — Wed, 20 May 2026 02:21:33 +0000

Don't know about GCP, but our AE on AWS was also continuously rotating, and as best I can tell, their job was to figure out what we are planning to build, and to ensure that we should always use for that, rather than a competitor product or build it ourselves.

New comment by YuriNiyazov in "Claude becomes number one app on the U.S. App Store"

YuriNiyazov — Sun, 01 Mar 2026 00:38:38 +0000

Me too. It's great that my employer pays for it and there's basically no budget, because this configuration is 10x more expensive than the regular default Sonnet.

New comment by YuriNiyazov in "Show HN: How Useless Are You? A brutally honest skills check"

YuriNiyazov — Thu, 16 Oct 2025 19:41:38 +0000

I got 99/100

New comment by YuriNiyazov in "Claude Code 2.0"

YuriNiyazov — Mon, 29 Sep 2025 19:12:20 +0000

Editing Jupyter notebooks in VSCode side by side with Claude Code extension is a pretty good workflow.

New comment by YuriNiyazov in "Google's new AI mode is good, actually"

YuriNiyazov — Sun, 07 Sep 2025 16:08:47 +0000

The example itself that Simon puts up is questionable. I might be wrong about this, but I thought I read elsewhere that the “buy, scan, destroy” method was explicitly not the problem, and instead the issue was that anthropic downloaded libgen, and the settlement was for libgen.

Edit: https://news.ycombinator.com/item?id=45143392

New comment by YuriNiyazov in "How to stop feeling lost in tech: the wafflehouse method"

YuriNiyazov — Thu, 21 Aug 2025 07:14:14 +0000

Why are you at azure and not at a frontier ai lab?

New comment by YuriNiyazov in "o3 and Grok 4 accidentally vindicate neurosymbolic AI"

YuriNiyazov — Tue, 15 Jul 2025 04:02:00 +0000

Thanks for your reply; I can’t edit the original comment but I have updated my personal understanding of Marcus’ position.

New comment by YuriNiyazov in "o3 and Grok 4 accidentally vindicate neurosymbolic AI"

YuriNiyazov — Tue, 15 Jul 2025 04:01:52 +0000

Thanks for your reply; I can’t edit the original comment but I have updated my personal understanding of Marcus’ position.

New comment by YuriNiyazov in "o3 and Grok 4 accidentally vindicate neurosymbolic AI"

YuriNiyazov — Tue, 15 Jul 2025 04:01:35 +0000

Thanks for your reply; I can’t edit the original comment but I have updated my personal understanding of Marcus’ position.

New comment by YuriNiyazov in "o3 and Grok 4 accidentally vindicate neurosymbolic AI"

YuriNiyazov — Sun, 13 Jul 2025 19:10:49 +0000

motte, meet bailey. Gary Marcus' shtick the entire time has been "LLMs are the wrong approach", and now the claim is "actually, the entire time I've been claiming something much weaker: LLMs that call out to code interpreters are sufficient for neurosymbolic AI"/

New comment by YuriNiyazov in "Jank is C++"

YuriNiyazov — Fri, 11 Jul 2025 22:20:51 +0000

A long long time ago, at ClojureConj 2014, I asked Rich Hickey whether a cpp-based clojure was possible, and his answer was "well, the primary impediment there is a lack of a garbage collector". There were a lot of conversations going on at the same time, so I didn't get an opportunity to "delve" into it, but:

1. does that objection make sense? 2. How does jank approach that hurdle.

New comment by YuriNiyazov in "Knowledge-based society, my ass"

YuriNiyazov — Tue, 29 Apr 2025 04:51:50 +0000

Ex-iron curtain, amirite?

New comment by YuriNiyazov in "Ask HN: Who is accountable for cloud costs in your org?"

YuriNiyazov — Thu, 09 Jan 2025 04:39:40 +0000

Visibility is essential, and visibility is owned by the devops team. ALl the resources have to be tagged with the team that owns those resources, and you should have a meeting once a month or so with that team where you bring to them a report of "here are all the resources we have assigned to you, do you agree?" and if they agree, then great, they are responsible for it, and if they don't agree, then now you have to have a conversation where you bring in the PMs and the EMs, and the head of finance if you need to.

And it's essential that you check in regularly, rather than just give them a dashboard and say "ok, you go look here and tell me if anything is amiss", because they will never look.