Hacker News: murkt

New comment by murkt in "Claude Cookbook"

murkt — Fri, 24 Jul 2026 11:25:11 +0000

Yeah, along with UPPERCASE labels, which is a staple of AI designed pages

New comment by murkt in "GPT-5.6"

murkt — Fri, 10 Jul 2026 08:23:07 +0000

It triggered for me on a completely pedestrian game design prompt a couple of days ago. I’ve sent feedback and continued with Opus, but that was really unexpected

New comment by murkt in "Show HN: I mapped 8.5M research papers into an interactive atlas"

murkt — Thu, 09 Jul 2026 18:16:49 +0000

I remember similar kind of visualization from a decade ago, called paperscape. Looked cool, worked on clustering using citations and references.

Never got any idea on any use case that would be covered by such visualizations, apart from looking cool.

New comment by murkt in "A global workspace in language models"

murkt — Tue, 07 Jul 2026 00:17:35 +0000

This supports my feelings of what works best when working with the models. Especially together with the directional bias in recall that’s mentioned here in the comments.

First, the model attention is actually limited, so less rules is usually better, but that’s common knowledge already. Or maybe it’s as common as common sense, and a lot of people still employ lots of rules and try to cram everything in one step.

Second, it’s often quite sufficient to just namedrop a technique and LLM will work differently. For example, when debugging, LLMs tend to try to brute force the problem and often end up in the weeds. Just add “use scientific method for debugging and keep journal file” is usually sufficient to improve their skill here.

Another example is refactoring. Just add “use Mikado method”, and it’s sufficient to wholly change the approach and produce much better results.

New comment by murkt in "Will It Mythos?"

murkt — Tue, 23 Jun 2026 06:03:09 +0000

Some problems are very hard to solve with stupid code. This can easily be the case (computational geometry)

New comment by murkt in "Ten years of ClickHouse in open source"

murkt — Sat, 20 Jun 2026 05:23:28 +0000

I am having a hard time picturing what could be the problem that you were solving.

Redis, Cassandra, RabbitMQ and Clickhouse. RabbitMQ looks like a black sheep in this lineup.

New comment by murkt in "Has AI already killed self-help nonfiction books?"

murkt — Fri, 19 Jun 2026 07:25:42 +0000

Yeah, probably different halves of the book. I've read it a few years ago, and it looks like I've just ignored/forgot all that "bending reality" stuff. It's not my cup of tea, so I remembered only the good parts of it

New comment by murkt in "Launch HN: Adam (YC W25) – Open-Source AI CAD"

murkt — Wed, 17 Jun 2026 18:28:37 +0000

Opus 4.5-4.7 was pretty bad at it, 4.8 was a bit better, and I have not tried Fable much.

So basically you have a good enough code that’s “intuitive” for a model, screenshots, and that’s it?

New comment by murkt in "Launch HN: Adam (YC W25) – Open-Source AI CAD"

murkt — Wed, 17 Jun 2026 18:14:20 +0000

I find all current LLMs to have pretty poor spatial awareness. It is becoming better, but still very poor. How are you dealing with that? Got any special tricks, any advice?

New comment by murkt in "Has AI already killed self-help nonfiction books?"

murkt — Wed, 17 Jun 2026 18:04:26 +0000

Touching shoulders and shaking hands palm-down is “persuasion” bullshit.

Can’t say anything about other books, but Never Split the Difference is about hearing and understanding other peoples’s wants and opinions. Not this pickup-artist-like bullshit.

New comment by murkt in "Has AI already killed self-help nonfiction books?"

murkt — Wed, 17 Jun 2026 07:23:27 +0000

Please read the actual book, it’s kind of the opposite from manipulation. You can read more detailed answers in the near branch of comments.

New comment by murkt in "Has AI already killed self-help nonfiction books?"

murkt — Wed, 17 Jun 2026 06:41:41 +0000

I’ve genuinely read only Never Split the Difference from your list, and it’s kind of the opposite from manipulation.

The book teaches how to actually hear people even in the very emotionally charged situations, how to properly ask them questions to understand their point of view and their needs.

If I understand my son’s needs and can give him what he wants in exchange of him giving me what I want, how is that a manipulation? I can yell at him, impose sanctions (eg no minecraft for two days) and we both will be greatly dissatisfied. Or we can both get what we want, which is a win-win.

New comment by murkt in "Has AI already killed self-help nonfiction books?"

murkt — Wed, 17 Jun 2026 04:17:26 +0000

“Never Split the Difference”, which is a book about how to successfully communicate with terrorists. Very suitable for talking with kids!

I’ve even read aloud a few chapters to my kids, because it’s very suitable for communication with parents as well

New comment by murkt in "Why Is Claude Turning into an a**Hole?"

murkt — Sun, 14 Jun 2026 23:10:17 +0000

The post matches my experience as well, I am asking a question like “does A work like this and that”, and Claude responds with “you’re conflating A and B! Only A does this and that, and B does that other thing!”

Well, I am perfectly aware of B and that other thing and did not conflate them at all. I also achieved enlightment, so I don’t argue with Claude here, just ignore the obnoxiousness and move on.

New comment by murkt in "Azure Linux 4.0 is Microsoft's first general-purpose Linux"

murkt — Fri, 05 Jun 2026 06:06:09 +0000

Ah, okay, my bad. Got too focused on the name. Googled the dates, Satya became CEO in 2014 and Sundar became CEO in 2015, so it’s actually not that different, especially when we look at the events more than a decade later.

New comment by murkt in "Azure Linux 4.0 is Microsoft's first general-purpose Linux"

murkt — Fri, 05 Jun 2026 05:40:37 +0000

Sundar Pichai does not work in Microsoft, though. A bit weird to anchor the MS timeline on his position. When he became the CEO, actually? I don’t remember the year even approximately

New comment by murkt in "Claude Opus 4.8"

murkt — Thu, 28 May 2026 20:11:18 +0000

Price hasn’t changes at all, though.

New comment by murkt in "Show HN: Needle: We Distilled Gemini Tool Calling into a 26M Model"

murkt — Tue, 12 May 2026 19:58:32 +0000

Can this be a Siri-like core? Set me a timer, tell me what’s the weather, etc. Here is transcribed text and available list of tools for the model to call, and voice the output.

New comment by murkt in "Learning Software Architecture"

murkt — Tue, 12 May 2026 13:52:34 +0000

The last one is about involving less people. You don't have to read it as "shut up and keep your thoughts for yourself". I read it more like "Do we really need to have six people working on this feature/present in this call?"

New comment by murkt in "Learning Software Architecture"

murkt — Tue, 12 May 2026 13:51:03 +0000

You can make the feature with one colleague, or you can call in five more people to weigh in and do their parts of the work.

If you involve five more, the result could be better in theory, but it will certainly take MUCH more time because of communication overhead.