I don't get these model providers forcing people to use their (bad) software. I just downgraded my anthropic account because I can't stand the bugfest that is Claude. I won't even touch google for AI. Doesn't matter if your model is good if I have to use your software.
With open-weight models getting closer and closer to parity with frontier models for specific tasks (coding,etc) the frontier labs are trying to make moats via their software.
Personally, this is why I foresee Anthropic/OpenAI/Google taking a bath once their creditors come calling. I think the individuals most attached to a specific app are the ones least willing to pay the true cost of inference. (IE: your grandma using chatgpt to ask for recipe recommendations probably isn't going to pay $400/mo).
"programming is solved" has also been said, I don't know how someone can say that with a straight face, let alone going on a podcast tour with it as the mantra
Claude has been creeping me out a lot recently when it comes to overstepping. Yesterday, I asked it for recommendations for software to scroll a video file frame by frame (I was debugging an issue in a game that only happened on one frame). I expected a list of software, what I actually got: Claude searched my documents and found my video file unprompted with no hint towards the name, then it searched my entire hard drive to find Krita, whch apparently has ffmpeg built in, then it used that to extract about 1000 jpegs of frames. All. Without. Asking. It was geniuinely creepy. It also ended up being useless, $45 of API spend later and I had a bunch of bloated and broken diagnostics code. I fed the same prompt into ChatGPT and it left my computer alone and told me to hit a checkbox in unreal engine, which was the actual problem. Really not a fan of Opus 5.
The cloud stuff is definitely a much better economic value, but I would argue:
1. You learn a lot more running this stuff yourself (especially since you can poke at its internals if you're interested or watch the reasoning chain.) Just being a consumer of this stuff doesn't really teach you much about it other than model & harness specific tricks that become obsolete pretty quickly. (IE, your Claude.md from 6 months ago probably needs a rewrite). Which is fine, I don't think you're going to be "left behind" if you're not a hardcore AI enthusiast or anything (I'm not), but as a guy that's always been interested in computer science I want to see how it ticks.
2. You can't really depend on this subsidization lasting forever IMO. I know the financials thing has been beaten to death but I guess I'm in the camp that it's good to be in control of your tools so that you can go elsewhere if the economics change.
I like to check in with ccusage pretty frequently, and honestly like if I were paying API prices for Claude I'd probably be paying thousands a month.
There’s no law or business advantage preventing me giving my financial transaction and medical info to Google/Anthropic/OpenAI but I just don’t want to.
Curious, how are you running it and what quantization are you using? I've mostly been using MTPLX; 125B sort of looks like it'd be right at the limits of my 128GB MacBook once you factor in KV cache and context window.. wondering if it's worth it compared to the 27B model which gives me a lot of headroom or even a 72B model.
Yeah, I ran into an overthinking loop with it a couple days ago on a task that shouldn't have been that hard. (It's kind of interesting to watch the internal conversation happening with it). Overall I'm impressed with it, but setting the /effort to medium is what you usually want (it defaults to xhigh). I do wonder if I had made it write out a plan if I would have avoided that though.
Yes. xhigh can not just overdo the answer, it can also trip itself up and end up writing worse code.
Even in the lower reasoning levels I find I want to like Qwen 3.8 27B and mostly don’t; it’s OK in the low reasoning effort, though.
Muse Glimmer is the one I actually enjoy working with, at least so far.
But I am trying to use it more as a sidekick than as a long horizon developer, because that is a better fit for how I want to use AI, and it appears to have been well trained for that.
Not to mention, hasn't the pharmaceutical industry taught us that curing diseases is a bad capitalist strategy? After all, why cure something if you can simply treat it, expensively, indefinitely.
> I think that ordinary people don’t trust companies, governments, or the tech industry and always suspect that we are cooking up some new way to screw them over.
Well, yeah Dario. You keep PUBLICLY TALKING about ways you want to fuck over people and everyone has noticed. I'm sorry, but when a lot of people are living paycheck-to-paycheck and watching layoffs everywhere, being like "well it'll take all the jobs and maybe kill humanity" is going to set off a LOT of alarm bells, despite your attempts to make concerned looking faces. You're trying to solve hypothetical problems in unproven ways, while worsening real problems people actually face. These people are SO disconnected from the society they live in.
reply