knapcio

Np, good luck! PS I’ve been using Sol 6 and Opus 5.5 today and they’ve been great so far. The new Opus is smart, fast and cheap. It makes mistakes but after every task I ask Sol to review it and it catches most of them. I need to test the models properly but it looks promising so far! Hope they won’t nerf them again. I think DS may still be cheaper though (and it’s 300 TPS via the API which is sick).

Well, to be honest it’s all based on my subjective experience. I started benchmarking models on 10 of my real tasks ranging from easy to hard but even with the same model the completion time sometimes varied by as much as 50% between runs. That made me realize you’d probably need hundreds of tasks to get any meaningful numbers. Otherwise there’s just too much variance. So I can’t give you solid benchmarks without spending weeks testing everything properly. What I can say is that I actually use most of these models regularly for different things, so I’ve developed a general feel for them. DS is my main model for work, Claude for hobby projects and local AI, Fable mostly for design, Codex for various other tasks and sometimes Grok for health-related stuff. Cost-wise, a $200 subscription wasn’t enough to get through 20-30 tasks while $30 of DeepSeek was, and that was with Sol, not even Astra. Fable is expensive too and I haven’t found it particularly strong at coding. Opus 5 was horrible in my experience, though maybe 5.5 will be better since I’m testing it now. I also ran GLM 5.3 Flash locally for a while but it was pretty slow and its code was usually worse than both DS4.1 and Qwen Flash Next. Things are moving so quickly that it’s honestly hard to keep up, so take all of this as my general experience from actually using these models rather than a proper benchmark.

I’ve been working with frontier models for the last year on a large real-world project with multiple apps. Eventually they started becoming unreliable. Simple UI issues, usage limits and overengineering became constant problems. I had to come up with a robust process: task analysis, user intent analysis, implementation and testing. All of these steps loop when needed with 15-20 steps per task in total. This finally got the models to do a good job but I started hitting usage limits. Then I switched to DeepSeek and haven’t noticed any drop in quality. It’s fast at around 300 TPS and cheap. I don’t miss frontier models anymore! Come up with a good process and you might not need them either.

I’m wondering whether O3 can be used to explore its own improvement or optimization ideas, or if it hasn’t reached that point yet.

> I don't think people's habits will change irreversibly. I actually disagree. A great example is smoking. It's been declining for the past 70 years. It just became unattractive.

> Sadly I don't think taxes end up working this way for long. They might or might not start by doing this, but then they just stay forever. I just described my idea how to approach this. I agree that governments are far from being perfect in this matter.

I'm close to being libertarian in many cases; however, I think that a tax may be a good way to quickly address this issue. I also believe that the money received from this tax should be directly spent on educating the public about why it's bad to consume too much sugar. The tax should be gradually decreased until people's habits change.

You can thank the government for all the regulations which make it ultra hard for new companies to enter the market. You can thank the government for not fighting monopolies. Don’t blame the free market as it basically doesn’t exist.

No isolation, no depression, definitely :)

Just curious: Do you spend much time reading news, watching podcasts, or YouTube videos? I've noticed a similar thing in myself and I'm not sure if it's due to COVID or if it's because of this news addition.

I just had this thought (possibly unrelated to this particular situation): We see how many accidents are caused by autonomous vehicles therefore it’s easy to blame them. However what we don’t see is how many accidents did not happen because of autonomous vehicles. I hope regulators consider both cases.

Please read the project description (Point 2 - 2. Download the model).

Maybe something like: hodoov

xAI's mission is to elevate the world's consciousness

I find that my confusion primarily arises from the utilization of "USD", an abbreviation denoting the United States Dollar which exists since 1792 :)

Not sure why you assume the cost of battery replacement will be the same now and in 10 years.