Viewing profile — tarruda

I don't have experience with opencode, so I couldn't tell you. Codex is really good in my experience, especially due to its native sandboxing. Deepseek seems really well versed in …

One of the best things about this version is that it is trained in the codex harness. It feels just as good as OpenAI models in using codex tools, but extremely cheap and with 1M c…

It is not that they don't release open weights, but some users report that they are significantly inferior to the closed versions.

> You can't. Not if you're in the minority Is that a bad thing?

> It would be fundamentally wrong for you to ask what's the value of solving the Erdős–Hajnal conjecture; the value is that it's solved. I suspect the value is in showing the poten…

Assuming steady 1 tok/second generation (which seems to be the case for M5 Max macbook), wait 1 day for a 86400 token response. In some configurations it can be as slow as 0.1 tok/…

Recently tried the pelican test on GPT-OSS which was probably one of the best local models of 2025. So cool to see how models have improved in the SVG pelican!

> given they are pretty close in size One thing that might not be obvious about about DSV4 is how much innovation the Deepseek team implemented in its architecture. When llama.cpp …

Hopefully this distillation will lead Alibaba to release more powerful open weights LLMs, contributing to the democratization of AI.

Vibe thinker also beats Opus 4.5

If your framework desktop is the 128G Strix Halo, I recommend giving Qwen 3.5 122B-A10B a shot. This Q5_K_M quant should be near lossless and fit with full 256K context in about 10…

I don't feel like AI coding has ruined my skills, and I could go back to manual coding any time. However, I cannot build a good mental model of a software component that I didn't w…

What I find fascinating is the idea that there might be a set of "secret" tweaks that when applied to those weights (or even smaller models) could result in an intelligence simulat…

Not as much as Qwen, since apparently 3.6 35B surpassed Opus 4.7 https://x.com/simonw/status/2044830134885306701

I don't think there's any incentive for Nvidia to make this a Windows-only device, so most likely it will be fully supported on Linux, just like their GPUs are.

> This also means that, according to our plans, Zig will have to propagate "stackless-ness" upwards in the call chain while analyzing the code (thus making Future.await not special…

> there's an accepted proposal to bring them back, in which case any function that calls await, or that otherwise has a suspension point, would have to be transformed into a stackl…

Fixed it. thanks!

> especially with the new IO mechanism which allows supper efficient code that looks good whether it's implemented single-threaded, multi-threaded or just via an event loop! I had …

The official Q4_K_S gguf is quite good and has very good 35 tps generation on a M1 mac studio. Should be much faster on recent Macs, especially M5.

> One of the most prominent improvements in Opus 4.8 is its honesty. Does that mean it no longer deletes or changes tests to make it pass?

> safer bet as a dependency. The recent 1 million line vibe coded PR suggests it is not so reliable as a dependency.

> That's impressive getting a 397B down to It is higher than 110GB. MacOS allows up to 125G of the RAM to be shared with GPU, so it is certainly less than that! > HF link is broken…

> I'm questioning ROI If by ROI you mean saving more money than using paid APIs, then I don't think it is worth it. All you gain is full sovereignty over your AI usage.