EFLKumo

It's said Astra is based on a newly pretrained model. Personally I hope it solves the problem that GPT speaks weirdly (which can also be spotted on Claude models after Opus 4.8 but GPT's is more severe) because IMO the way GPT couldn't get how to write good code (obviously it's trined to write code which pass benchmarks, but never code which sound good, with pursuit towards simplification and code aesthetic in mind) is extremely similar with how it couldn't get how to speak like a human.

However, it seems like OpenAI didn't pay much attention on these perspectives and I didn't find if Astra could write a more elegant code, or communicate more naturally, etc., which made me somehow a little disappointed.

They indeed mentioned the code Astra delivered is closer to production grade but production-grade code is different from what I want since there can be a kind of messy code blowing up your whole architecture design with control flows nobody truly understands but just passes all tests perfectly. There is no difficulty in maintaining this kind of code because you only need to paste the problems into Codex. And we all know this sounds incorrect. I don't know if my appetite towards a good code (no matter how) is sound but I just imagined frontier labs to give more attention on this.

Note: fwiw Fable 5.1's release page says it's better at these perspectives of coding and per my experience, yes it is.

Sorry! I was just a bit excited writing the comment and ignored that :(

I've been confused a lot why there isn't a benchmark to measure a harness's performance rather than the model's one. Now there it is.

Claude Code supports the base URL env var so you could tell it to talk with any LLM API endpoint that receives the Anthropic style request format, e.g. DeepSeek.

Come on, think how fast Grok evolves after SoaceXAI acquired Cursor. I just believe if you can't get enough real data from practice then you can't train a good model. And for Mistral collecting data is a must step no matter what approach it takes.

Something maybe unfamiliar with you: not about coding but writing. I've asked it to write an argumentative essay, which is a part of "gaokao" (China's university entrance exam), and its work is *extremely* impressive. speaks and writes like a real senior high school student, and the opinions unfold progressively with deep hierarchy. I don't know how the Gemini team reaches this because this kind of Chinese capability literally outperforms at least 2/3 Chinese students, no to mention those who speak Chinese. After all, the model speaks like a real humankind if you prompt it well. That's AGI guys

It's displayed in my practice that LLMs master Rust even as weaker models like deepseek.

Making a XAML UI is fundamentally authoring a WinRT interface, I guess. And for cppwinrt, Microsoft's solution is like describing in so-called MIDL .idl files, compiler generating cpp stubs, copying these stubs and filling in implementations. After static reflection introduced in cpp idk if this process could become better, but Microsoft just left cppwinrt in maintenance mode, it's impossible I guess.

On the Rust side, IMO the windows-rs even has not thought about authoring new com interfaces, only consuming or impl-ing existing ones. In fact the experience of consuming windows apis in rust feels good if one would like to get rid of C++. Rust with NAPI or BoltFFI etc. offers an maintaining-friendly option for cross-platform app authors to interact with the OS more deeply. So in conclusion the situation right now is that windows apis just become not so unapproachable, while in-depth things keeping comfortable only with C# or .NET.

Exactly what I want to say. Thank you.

By using "ReAct", I just wanted to emphasize the "agentic" perspective of tool calling, which makes tool calling facing the real world and at risk sometimes. So I'm not downplaying the significance of tool callings.

Yes I'm a builder of an agent infra on PCs, so I can completely sense that the protective measures are weak and inadequate, sometimes seeming like an unsolvable problem. But according to the article, what Microsoft did was hard to tell in a polite way. If they had even a little security awareness, I could completely understand, but it's like they've vibe coded the entire permissions system of Cowork.