sbinnee

I have no idea what shell means either! Isn’t it called ricing to customize desktop environment? Since when do people started calling it shell?

It's hilarious that atm I see "Moltbook" at the top of HN. And it is actually not Moltbot anymore? But I have to admit that OpenClaw sounds much better.

Playing Metal Gear Solid 2 was one of my fondest memories I cherish. I could play it only at Taekwondo gym I was attending to. I couldn't finish it because I only had a couple of hours at the gym and I could play only during break time. Oh and I was always waiting for the break time!

I have a samurai game, Kengo 3, that I really liked on PS2. I still have that CD at my parents'. Can anyone recommend me a PS2 emulator?

Is that tiling window management by default? Huh, finally the right choice to maximize small display area for laptop!

As a user, I am like this decision.

I enjoyed writing git commit messages. I value good commit messages. But at work I recently created a slash command (for those who don’t know, it’s like a snippet for anything) that writes a git commit for staged changes with optional jira tags. Although I always end up amending it, it is so convenient. Does it mean I don’t value good git commit messages? I don’t know… I try my best to review every commit at least.

I didn't know about WoW64 mode. I remember when trying to install an old windows program I had to install a bunch of 32-bit translation library for audio and stuff. This WoW64 means that I can just simply use 64-bit arch. This is fabulous.

WoW64: https://en.wikipedia.org/wiki/WoW64

To me, Apple's ML business was all about federated learning. I know this concept was pre-transformer era, I conjectured one of the reasons Apple didn't adopt LLM right away was that Apple couldn't find a reasonable way to do federated learning with LLMs. I wonder Apple will give up this idea. And I would like to see how it could be done with current AI systems.

A week ago I pitched to my managers that this form of general purpose claude code will come out soon. They were rather skeptical saying that claude code is just for developers. Now they can see.

AI slop indeed. But it caught my eyes nonetheless because I have been doing some work around the same concept. These days I found that GitHub is just flooded with "AI Agent Memory" modules, where in fact they are all skills-based (meaning all text instruction) solutions.

I am glad that I restrained myself from buying a macbook and went for a thinkpad. I think I saw icon issue on Tahoe not long ago on HN.

I know that macbook has been crushing laptop market with their M chip. Macbook is amazing for sure. I very much enjoy using it at work. But for personal computing, I need Linux setup.

Description alone sounds like something I would love to give a try.

As someone who never opened tiktok, how does the app handles that? Do people even upload recipes on tiktok? I thought tiktok posts are mostly videos. So does it mean that it uses some AI model?

Now I am more afraid than ever to upgrade to Tahoe.

I was referring to this paper a lot when it was hyped, when people cared about architectural decisions of neural networks. It was also the year I started studying neural networks.

I think the idea still holds. Although the interest has been shifted towards test-time scaling and thinking, researcher still care about architectures like nemotron 3, recently published.

Can anyone give more updates on this direction of research, more recent papers?

I will wait for the actual reviews from users. But I lost faith in Intel chips.

I was in CES2024 and saw snapdragon X elite chip running a local LLM (llama I believe). How did it turn out? Users cannot use that laptop except for running an LLM. They had no plans for translation layer like Apple Rosetta. Intel would be different for sure in that regard, but I just don't think that it will fly against Ryzen AI chips or Apple silicon.

I see how the power of HN community manifests. Really cool work!

It is so inspiring. Recently, I've been thinking of making a side project using LLMs for learning new languages too. Transformers were originally designed for machine translation and now we have much better ones. My idea is to write a mobile app which I have zero experience.

The best RSS reader program I have been using for years

I actually believe that the era of lives will come. But I can't wait for UBI. Nobody can't. Even if the era of jobs ends, for us who are living in this era, the event is not going to be a period but an ellipsis. I can't wait to see how it unfolds. Yet, I doubt that I would see the end happening in my lifetime.

What struck me most was the requirement. I've been self-hosting librechat on a raspberry pi. I was hoping to test Onyx on it, but no way. Its requirement is 4 vCPU and 10GB RAM? I wish I can take out components that resource hungry and have only the basic so that I can serve it on a less demanding server.

As much as I am excited by the price, the tools they called "the advanced tool"[1] look so useful to me; Tool search, programmatic tool calling (smolagents.CodeAgent by HF), and tool use examples (in-context learning).

They said that they have seen 134K tokens for tool definition alone. That is insane. I also really liked the puzzle game video.

[1] https://www.anthropic.com/engineering/advanced-tool-use

I really enjoyed the book series. This is an amazing work! Thanks for sharing.

Oh no. What's with the scrolling in the blog page. What a terrible experience. It's clearly vibe-coded and AI-tested. If a senior saw mingling with the scrolling behavior, it would have been never in production.

You don’t sound like a layman knowing the looped latents and others :)

As a native Korean, every time I see something related to Korea, I am just amazed how much passion these people have. I briefly remember seeing a detailed map of the whole Korean peninsula from the elementary school, I think. I appreciate this finding!

North Korea is kind of invisible if you live in South Korea. You may see some news that they launched some rockets and did some military actions. People are so used to these news that they don't pay attention anymore. You forget about the North one and just live your life.

> It is universally agreed between the two governments (and their citizens) that a unification should happen at some point, so it is obvious that we should be using a map that covers the whole peninsula. We (as South Koreans) also learn 'our country' as the whole peninsula.

When I was growing up, I learned that too. But is it still true? I don't see any unification news or mention of it from media anymore. I don't think that schools still say or can say that to students. It didn't take me a long time after I got out of the public education system to realize what propaganda schools and media were selling.

> Unlike OpenRouter, LiteAPI focuses exclusively on premium enterprise-grade models (OpenAI, Anthropic, Google) and offers up to 50 % lower cost through our VC-backed credit sourcing system

I got my answer. I will gladly use AIs with other people’s money.

It's rare for one person to achieve many things. Her ImageNet was certainly HUGE. But she is a researcher. I think the true power of researchers is to persist. I also often think that researchers are too much absorbed into their topics. But that is just their purpose.

It could be a dead end for sure. I just hope that someone figures out the `spatial` part for AIs and brings us closer to better ones.