Alephinitesimal

My guess is that very few people actually believe the "Tang dynasty never existed" stuff. Most people are just watching it because it’s entertaining, like a historical conspiracy soap opera told with a completely straight face.

Last year I remember another one going around about a Qing empress dowager having an affair with a Han Chinese official, and somehow it turned into this whole theory that the Qing royal bloodline had already been secretly replaced. I doubt many people seriously believed it, but after a long day, "the Qing imperial family was secretly replaced" is exactly the sort of nonsense that suddenly makes your brain go like, okay, I need to hear the rest of this.

It's kind of like the micro dramas that are popular in China right now，dumb, ridiculously, and yet somehow you still want to see what happens next.

So I think the history is almost beside the point. The entertainment value is the point.

At least San Ti are transparent about what they're thinking.

Maybe they'll be cute though. Like Grogu.

Old dystopias were too neat. Even the evil systems had a plan. Reality is messier and more absurd. Maybe aliens are the only thing left that's still safely fictional.

A Chinese example of this for me is Jin Yong, probably the most influential wuxia (Chinese martial-arts fiction) novelist in the Chinese-speaking world. His books are popular fiction in the most literal sense: enormously entertaining, widely read, and for many people first encountered simply as page turners.

As a kid, that was how I read them too.

Only after I started working did I realize how perceptive some of the character writing was. Murong Fu, for example, is genuinely capable, but his ambition is even greater. Everyone around him, friends, followers, even people who love him, is ultimately someone he is willing to sacrifice for his goal. I have met people who seem to reproduce almost the whole arc: the ambition, the triumphs, the disappointments, the pain, the struggle, and sometimes even the madness. Suddenly Murong Fu no longer feels like an exaggerated fictional character.

The book never changes. I had finally acquired the experience to see what was already there. That feels like thickness to me.

I was only using a single DGX Spark, and this was earlier in the year, so I was running some pretty aggressively quantized models — probably in the 1–3 bit range.

My main issue at the time was that my financial data had lots of messy notes, comments, and irregular annotations. The quantized models often failed to process all of that context consistently and would miss things. So I ended up generating a fake dataset with the same structure, asking Claude Code to work out the analysis on that, and then bringing the result back to the local model for the final pass.

I was mainly using llama.cpp at the time, before B12X support was integrated into vLLM, so I think I wasn't using it then.

I did try some finance analysis earlier this year. I was using a DGX Spark, so I could run some relatively large models, but the results were pretty mixed at the time. I honestly can't remember which models I used anymore.

Might be worth trying again now though.

That's interesting since both models are dense. I wonder if this is more of an optimization issue with 3.8 rather than something inherent to the architecture.

I mostly use local models when the data has personal information. Earlier this year, I felt the coding quality was still not as good as Claude Code.

One thing that works for me is to ask the local model to make some fake data with the same format, let Claude Code work on the fake data, and then bring the code back and run it locally on the real data.

This way the real data never leaves my machine, but I can still use a stronger model for most of the coding.

Baking is a good metaphor, though lately it also feels a bit like making liquor. Distillation is a surprisingly important part of training.

I saw this announcement when it came out and completely forgot about it. That explains why Claude Code felt so surprisingly generous these past few months.

I once spent two days on a pr and got an obviously AI generated review that contradicted what we agreed one before. So I had AI respond to it. The next day he asked if I'd used AI. I used the same justification he'd used for his review. Fight magic with magic. He never reviewed my pr that way again.

The NVIDIA+AMD support is the part I find really interesting. I know OpenMP and SYCL can already target multiple GPU vendors, but doing this while keeping Rust's safety model seems pretty compelling. I'm curious how portable the performance is in practice.

I learned this. I had what I thought was a pretty good lock, but the chain was cut very clean. The cut was almost perfect flat, so I assume they used a power tool.

I think solitude is great. The hard part is finding the right people to talk to. I'm not sure if this is a Silicon Valley thing, but I've met some people who use a lot of jargon in a way that feels partly about status. At first I thought they just had a lot of ideas. Then they started talking about things in my own field, and I realized they were getting some pretty basic concepts wrong.

My guess is that some of this comes from listening to too many podcasts. You can pick up a lot of jargon and big ideas pretty quickly, and some podcasts are better at giving you that "oh, now I get it" feeling than actually helping you understand the ideas.

Yeah, exactly. Even when I lower the effort to medium or low, it still tends to act for several rounds before explaining what it’s doing.

Haha, I only used /btw when the agent was in the middle of doing something. Never thought to just use it directly. Thanks!

I’ve been running into this too. It’s especially frustrating when you ask Claude to explain one of its own terms or summaries, and instead of just defining it plainly, it sometimes goes through several rounds of tool calls before giving you a usable explanation. I really don't think such time/tokens should be wasted.