501–510 of 512 posts
Earlier quoted context omitted.
The choice is not binary. I use DeepSeek (paid) for coding, and Qwen (free) for casual stuff from the browser chat UI.
I mean paying for deepseek is sending money to China, and any company in China is pretty much an extension of the CCP (or can become one at the snap of their fingers). I don't think this is much better or worse than the American AI companies.
Earlier quoted context omitted.
That's a weird way to look at it. Any car gets you to your destination, but some people prefer driving a sports car or an SUV. They get something out of it that isn't just a marketing delusion, but subjective joy from the interaction with one product over another.
Oh I've always thought people like SUVs just because they want a bigger and pricier toy than the other guy. Is it not so? > isn't just a marketing delusion, but subjective joy What is the difference? When a product is being marketed, isn't the subjective joy created by the marketing?
I used to love sports cars because I’d get out to the track a few times a year, and enjoyed the performance engineering in them.
Today I enjoy and drive a SUV because I enjoy camping in remote locations that my old (awesome) sports car would not begin to be able to get to. In the future if I decide to build my own house, odds are I will find a pickup truck is a better fit than either sports car or SUV.
It’s weird to see these choices through the lens of marketing. Marketing may influence which vehicle I buy, but it’s hard to imagine sports car marketing tricking me into buying a Ferrari to go camping.
Earlier quoted context omitted.
Someone who bought a 4090 "a few years" ago can now sell it for more than they paid for it, but never mind that.
Do you think GPUs are going to keep going up in value forever like houses? The current situation (game console price rises years into their lifecycle) is unprecedented and irrelevant to my point. And if you need SOTA then you can sell your old card sure, but the next xx90 card is now 2x the price as the last gen. So you're not any better off.
If Xi goes for Taiwan, then yes, GPUs will appreciate like real estate ("Buy now! They're not making any more of it, you know!") for the next 10 years.
Earlier quoted context omitted.
I’ve been using DeepSeek V4 in OpenCode exclusively for about a month. I think it’s great, but coming from Claude Code it did feel like going back in time by ~6 months in model capabilities. This isn’t a big deal to me for what I do, but the difference is definitely there.
So my GPU comparison is pretty apt then. Paying 4-10x to be slightly ahead of the curve.
I do think more expensive models are valuable in some cases. For example, I’ve noticed that Opus (even 4.7) is much better than DeepSeek V4 at noticing information with small amounts of representation in a large context history, you should pick Opus if you need to find needle(s) in a large haystack. I’ve never worked on a project with millions of lines of code, but I’m guessing it becomes relevant in those situations.
A big thing, too, is that it’s work to get a non-frontier coding stack setup. I’ve spent many hours of free time getting OpenCode to do what I want, but I enjoy it so it’s NBD. If you don’t like puttering around with your development tools, $100/mo for Claude Code really isn’t all that much and you can call it a day.
I never want to hear from developers again that they are not susceptible to marketing. I see meet ups specifically about Claude often. Modern tupperware party. A colleague was convinced Claude is better so we played a game. We used the claude code and codex harness and I implemented some prs they needed with gpt5.5 and opus4.7 and asked them to identify which came from which only from the code. Couldn’t tell. Edit: i…
I can’t tell the difference between code written in vim or vs code but it matters substantially to the person writing the code. There’s stuff beyond just the output that goes into tool choice.
Earlier quoted context omitted.
Haven't heard about the universal subspace hypothesis yet, so I appreciate the digression.
Ya, super interesting research area the authors explored of basically trying to answer the question: "Is there a canonical/intrinsic way that concepts/representations/information are 'stored' in the universe/reality?". They tested that by performing "spectral analysis of over 1100 models - including 500 Mistral-7B LoRAs, 500 Vision Transformers, and 50 LLaMA-8B models ... by applying spectral decomposition techniques…
Ah, it’s a good time to check in with gwern on our conversation about oAI vs Anthropic: https://news.ycombinator.com/item?id=40816755 and our predictions (ca two years ago). Upshot - poetry expertise does not seem to be the primary focus these days, perhaps to the detriment of the entire world. We did move on from training scaling to “test time” scaling (which I hate as a name btw), Ilya does not seem to have been ne…
Did you also talk about "head and shoulders" and "pennant" patterns in stock charts? Or where the "smart money" is at? I'd like to subscribe to your paid newsletter.
What about the original conversation seems correct / incorrect / interestingly correct or incorrect to you? What about my summary now seems correct/incorrect, etc?
Ultimately the big value is to me — I get to look back at some dialogue and then check where I had it right, wrong and interestingly wrong. My personal hypothesis is that doing this a lot compounds in a good way.
Earlier quoted context omitted.
Ya, super interesting research area the authors explored of basically trying to answer the question: "Is there a canonical/intrinsic way that concepts/representations/information are 'stored' in the universe/reality?". They tested that by performing "spectral analysis of over 1100 models - including 500 Mistral-7B LoRAs, 500 Vision Transformers, and 50 LLaMA-8B models ... by applying spectral decomposition techniques…
Maybe related: https://news.ycombinator.com/item?id=47322887
Earlier quoted context omitted.
So my GPU comparison is pretty apt then. Paying 4-10x to be slightly ahead of the curve.
I think so, I think you’re getting downvoted because of how you’ve framed it. People don’t like it when you tell them that you think they’ve made a stupid purchase. :-P I do think more expensive models are valuable in some cases. For example, I’ve noticed that Opus (even 4.7) is much better than DeepSeek V4 at noticing information with small amounts of representation in a large context history, you should pick Opus i…
Like you say a combination of frontier and cheaper models is probably the optimum and that would require setup if you didn't want to choose models manually each time.
Earlier quoted context omitted.
Do you think GPUs are going to keep going up in value forever like houses? The current situation (game console price rises years into their lifecycle) is unprecedented and irrelevant to my point. And if you need SOTA then you can sell your old card sure, but the next xx90 card is now 2x the price as the last gen. So you're not any better off.
A lot depends on what happens with China. I don't think Xi will attack Taiwan, but then I didn't think Putin would attack Ukraine, either. If Xi goes for Taiwan, then yes, GPUs will appreciate like real estate ("Buy now! They're not making any more of it, you know!") for the next 10 years.