Nice! As a heads up, don't be tempted to replace the battery via a third party if the Samsung battery ever stops meeting expectations: https://news.ycombinator.com/item?id=47834810
For geometry, fixed-precision integers are better. But for computation and usability, floats are great. Scaling a 10 meter model in floats to 13% of the size is a trivial multiplication by 0.13f. With integers, this can get tricky. Can't first divide by 100 then multiply by 13 because you'd lose precision. Also can't multiply by 13 and then divide by 100 because you might overflow. Unless maybe venders would add hardware that computes that more accurately like they currently do for float, but honestly, float is good enough and the the potential benefits do not outweigh the disadvantages.
Float is also fantastic for depth values precisely because they have more precision towards the origin, basically quasi-logarithmic precision. Having double the precision at half the distance is A+. At least if you're writing software rasterizers and do linear depth. The story with depth buffer precision in GPU pipelines with normalized depth and and hyperbolic distribution is...sad.
Problem is, NVIDIA has so many quality of life features for developers. It's not easy getting especially smaller scale developers and academia to use other vendors that are 1) much more difficult to use while 2) also being slower and not as rich in features.
Personally I opted in to being NVIDIA-vendor-locked a couple of years ago because I just couldn't stand the insanely bonkers and pointless complexity of APIs like Vulkan. I used OpenGL before which supported all vendors, but because newer features weren't added to OpenGL I eventually had to make the switch.
I tried both Vulkan and CUDA, and after not getting shit done in Vulkan for a week I tried CUDA, and got the same stuff done in less than a day that I could not do in a whole week in Vulkan. At that moment I thought, screw it, I'm going to go NV-only now.
I did my thesis porting my supervisor's project from NeXTSTEP into Windows, was an OpenGL fanboy up to the whole Long Peaks disaster.
Additionally Vulkan has proven to be yet another extension mess (to the point now are actions try to steer it back on track), Khronos is like the C++ of API design, while expecting vendors to come up with the tools.
However, as great as CUDA, Metal and DirectX are to play around with, we might be stuck with Khronos APIs, if geopolitcs keep going as bad or worse, as they have been thus far.
Vulkan has abysmal UX though. At one point I had to chose between Vulkan and Cuda for future projects, and I ended up with Cuda because a feasibilty study I couldn't get to work in Vulkan for an entire week, easily worked in Cuda in less than a day.
Man, I love Kagi. Two years ago I would never have thought I'd ever pay for a search engine, but the option to block garbage domains like userbenchmark or sites with purely AI generated content is just too good.
If you go to duckduckgo.com/settings you can generate a URL with all of your saved settings. Loading it will configure all the settings it includes in your browser's local data. Blocked sites are included, I just checked.
It always takes me awhile to remember where this setting is buried in their menu. In case it helps someone else: https://kagi.com/settings/user_ranked . Besides blocking, they have ranking adjustment options on this page as well.
Security through obscurity is like a bike lock. It can be cracked with the right tools and effort, but massively improves security compared to leaving it out unlocked.
Anthropic models haven't been far ahead for a while. Quite a few months at least. Chinese models are roughly equal at 1/6th the cost. Minimax is roughly equal to Opus. Chinese providers also haven't had the issues with uptime and variable model quality. The gap with OpenAI also isn't huge and GLM is a noticeably more compliant model (unsurprisingly given the hubristic internal culture at Anthropic around safety).
CC is a better implementation and seems to be fairly economic with token usage. That is the really the only defining point and, I suspect, Anthropic are going to have a lot of trouble staying relevant with all the product issues.
They were far ahead for a brief period in November/December which is driving the hype cycle that now appears to be collapsing the company.
You have to test at least every month, things are moving quickly. Stepfun is releasing soon and seems to have an Opus-level model with more efficient architecture.
Minimax is nowhere near Opus in my tests, though for me at least oddly 4.6 felt worse than 4.5. I haven't use Minimax extensively, but I have an API driven test suite for a product and even Sonnet 4.6 outperforms it in my testing unless something changed in the last month.
One example is I have a multi-stage distillation/knowledge extraction script for taking a Discord channel and answering questions. I have a hardcoded 5k message test set where I set up 20 questions myself based on analyzing it.
In my harness Minimax wasn't even getting half of them right, whereas Sonnet was 100%. Granted this isn't code, but my usage on pi felt about the same.
> CC is a better implementation and seems to be fairly economic with token usage. That is the really the only defining point and, I suspect, Anthropic are going to have a lot of trouble staying relevant with all the product issues.
What are you using to drive the Chinese models in order to evaluate this? OpenCode?
Some of Claude Code's features, like remote sessions, are far more important than the underlying model for my productivity.
Yes, 100% agree. OpenHands has self-hosted, KiloCode and RooCode both have a cloud option. I don't think you are able to pass a session around with any of them. Codex seems to have comparable features afaik.
CC tool usage is also significantly ahead imo (doesn't negate the price but it is something). I have seen issues with heavy thinking models (like Minimax) and client implementations with poor tool usage (like Cline).
CC has had a period over the last six months of delivering significant value...but, of course, you can just use CC with OpenRouter.
I haven't noticed a huge difference with other models but I agree that is definitely a strength (and CC has better tooling for this). However, I do think there are practical limitations to agentic workflows because of the relatively poor output vs humans. You can generate lots of code, but most of it will be shit.
Agentic workflows do have a place in well-defined, structured tasks...but I don't think that is what most people are trying to do with it.
...and codex is at least 10x better than Claude. I don't even bother starting a new session when working on a feature, a single compaction is basically unnoticeable. You have to compact several times to start needing to remind the model about a rule or two.
Scanning your computer is an entirely different thing than scanning browser extensions. By maximizing the expectation via "Illegally searching your computer", the truth suddenly appears harmless.
reply