Hacker News: wanderingmind

New comment by wanderingmind in "I were 17, I'd learn how to build LLMs from scratch"

wanderingmind — Tue, 25 Aug 2026 02:56:28 +0000

I like the hacking spirit suggestion. But my disagreement is the specificity of it. The suggestion here seems more inline with not tinkering and hacking but first principles learning typical of science and math curriculum. What made hacking radios and JS cool was the short feedback loops to see the progress you made. Unfortunately for LLMs starting from scratch doesnt give a good feedback loop on improvement, although starting from pre-trained model to quantising, fine-tuning might be more aligned with the hacking culture

New comment by wanderingmind in "Don't Paste the AI, please"

wanderingmind — Thu, 20 Aug 2026 12:08:46 +0000

This is excellent. Would love to see the rest of the principles of AI usage.

New comment by wanderingmind in "How I use LLMs to learn complex topics"

wanderingmind — Mon, 10 Aug 2026 00:31:51 +0000

Good to know other people who get migrane reading LLMs dense prose. I started reading books again recently, since everything online is polluted by LLM prose. What i realise, is that a human author, especially a teacher understands the learning pathways of new learners, they motivate the learning, and start from simplest concepts (a spherical cow), and then building all the complexities. This helps us to emphasize on most important concepts, while throwing away unnecessary complexities. While reading LLM prose is like reading a research article, that is written to an expert in the area, that talks about bleeding edge, with full of jargons, caveats, that just is not conducive to the learning process for a new learner.

New comment by wanderingmind in "NASA figured out how to keep its Voyager 2 probe running for another year"

wanderingmind — Sat, 08 Aug 2026 04:51:43 +0000

A slight tangent here is a technical deep dive on Voyager 1 fixing a memory corruption error in 2023 by hand 15 billion miles away. Blows my mind of the reverse engineering done to achieve this https://www.youtube.com/watch?v=YcUycQoz0zg

New comment by wanderingmind in "Why do we think we understand the world more than we actually do?"

wanderingmind — Tue, 28 Jul 2026 05:10:25 +0000

100 percent can relate on the relentless curiosity of a child. I was dumbfounded yesterday by this question -> if cars go at high speed, and breaks stop it suddenly, how come the friction doesn't generate enough heat to start a spark?

New comment by wanderingmind in "Show HN: I mapped every US golf course"

wanderingmind — Sun, 26 Jul 2026 10:08:13 +0000

This is supercool. But I have a tangential question. I see projects like this built on top of OSM for different use cases. Does this data gets contributed back to OSM. A lot of them seems hobby projects, so it's hard to maintain long term, but the data is quite useful and could be used beyond the lifetime of these projects if they can be contributed back to OSM somehow.

New comment by wanderingmind in "Ask HN: Is anyone experimenting with different ways of using LLMs for coding?"

wanderingmind — Fri, 03 Jul 2026 22:12:12 +0000

Looks like my approach is as old school as it gets. For complex piece of work, the only way to be in flow for me is when I'm driving the engagement. I start with a high level requirement and a high level design plan to achieve it. I also provide constraints that needs to be satisfied (efficiency, performance, cost, scale etc) and write it all into a markdown document and ask LLMs to review it, find blindspots and refine it until I can get a detailed design for that phase.

Then I pass that to another LLM provider to review and check for any bloat that can be cut or blindspots that need to be addressed.

Finally I get a test plan to help me test different components directly and in debug mode. I then ask LLMs to implement in stages where I can test them in small components as possible.

I think I end up spending more time (easily 2x) than hand rolling. But the upside is the design is more thought out compared to hand rolled code. It has fewer accidental complexities and I have a clear mental model of the entire design that can also be shared to others through the document

New comment by wanderingmind in "Oomwoo, an open-source robot vacuum you build yourself"

wanderingmind — Thu, 02 Jul 2026 07:06:48 +0000

Assuming you live in a crazy big house (1000 m2), it cleaned your house 74000 times. Given S5 was released 8 years ago, even approximating it to 10, that's 20 times a day. I can imagine it taking about an hour to do one clean run. Jesus, did it ever stop cleaning

New comment by wanderingmind in "TOP500 at ISC’26: We have a New Number 1 Supercomputer"

wanderingmind — Mon, 29 Jun 2026 07:26:06 +0000

My sense is you only submit if you are in the business of selling supercomputing cluster (IBM, Cray). If you are a consumer or build to consume internally, you would care less.

New comment by wanderingmind in "What Apple and Google are doing to push notifications"

wanderingmind — Wed, 27 May 2026 23:16:25 +0000

The default must be pull, unless opt in for push. At the moment I would like notifications once a day or once a week for most apps. But instead I ha e turned it off completely, because of the push abuse. If I can configure to pull all the notifications on a predetermined cycle, it makes my life even better

New comment by wanderingmind in "A fundamental principle of aeronautical engineering has been overturned"

wanderingmind — Mon, 25 May 2026 11:27:15 +0000

The actual paper: https://www.cambridge.org/core/journals/journal-of-fluid-mec...

The Human Body's Hidden Pathways

wanderingmind — Tue, 12 May 2026 07:34:18 +0000

Article URL: https://www.nytimes.com/interactive/2026/05/11/magazine/interstitium-anatomy-acupuncture-medicine.html

Comments URL: https://news.ycombinator.com/item?id=48105315

Points: 4

# Comments: 0

New comment by wanderingmind in "Good developers learn to program. Most courses teach a language"

wanderingmind — Sat, 02 May 2026 02:16:29 +0000

This, we learn natural language like English first before we can use it to express ideas, argue for or against those ideas with evidence. The problem is not teaching a programming language, the problem is stopping there and not teaching how to use it to solve real problems.

New comment by wanderingmind in "Where the goblins came from"

wanderingmind — Thu, 30 Apr 2026 10:07:52 +0000

Humanity has been using steel for over a millenia, however it's only in the past 100 years or so we have a good understanding of how carbon interacts with iron at an atomic level to create the strength characteristics that makes it useful. Based on this argument, we should not have used steel, until we had a complete first principles understanding.

New comment by wanderingmind in "Before GitHub"

wanderingmind — Wed, 29 Apr 2026 03:04:20 +0000

To add salt to the wound: https://killedbygoogle.com/

New comment by wanderingmind in "To my students"

wanderingmind — Tue, 28 Apr 2026 01:03:04 +0000

No disrespect to the person, but this seems to be written by someone who has spent their life in academic bubble, without having to deal with people and entities with diverging interests and the impact of time on any decisions. I'm sure many artists will love to spend more time perfecting their art, based on their subjective interests. However, if they prioritize that, without understanding what their customer wants, they will go bankrupt. Nourish your interests through your hobbies. If they align with money making capability, you are one of the lucky few. For a significant majority, they do not align.

New comment by wanderingmind in "Sabotaging projects by overthinking, scope creep, and structural diffing"

wanderingmind — Sat, 25 Apr 2026 06:38:09 +0000

Technical feedback yes, but always reject any career feedback from your advisor since the data shows it's unlikely a good model for future career success

New comment by wanderingmind in "YouTube users get option to set their Shorts time limit to zero minutes"

wanderingmind — Thu, 16 Apr 2026 01:59:01 +0000

No, it doesn't the easiest way is to always use it in Firefox and use the following uBlock filters

https://github.com/i5heu/ublock-hide-yt-shorts

New comment by wanderingmind in "Project Glasswing: Securing critical software for the AI era"

wanderingmind — Wed, 08 Apr 2026 00:49:07 +0000

Its not, if you dont trust Anthropic, I hope you trust Daniel Steinberg of curl, who has said AI has gotten really good at detecting bugs and vulnerabilities. Here is his LinkedIN post https://www.linkedin.com/posts/danielstenberg_hackerone-acti...

New comment by wanderingmind in "Project Glasswing: Securing critical software for the AI era"

wanderingmind — Wed, 08 Apr 2026 00:43:41 +0000

So Mozilla is not part of this consortium, i'm guessing for deliberate reasons to make safari and chrome the default browsers. I don't think Firefox can survive the upcoming attacks, without robust support from foundational AI providers to secure the browser.