Viewing profile — spps11

I use ARQ heavily in my AI app's backend. I love the simplicity of the setup (just plug in Redis and you're good) and use it to manage long-running async LLM generation jobs. The c…

[dead]

[dead]

No I meant something else. As you said: us humans love clean abstractions. We love building on top of them. Now LLMs are trained on data produced by us. So I wonder if they would a…

pyspur is apache 2. it is free to self-host.

Yes, but I wonder how much of this trait is carried over to the LLMs from us.

got it, thanks for explaining. > with better AI models and tools like Cursor, we will move to a world where you can mold code ever more specific to your use case to make it more pe…

i feel this question correlates more with the generation of the SWE more than anything. expecting current gen SWEs to talk about network layer protocols while answering this is kin…

very cool! always wondered what that tower was haha, now i know!

Thanks for sharing, enjoyed reading it! I have a slightly tangential question: Do you have any insights into what exactly DeepSeek did by bypassing CUDA that made their run more ef…

When you say sequence length, does it only count the output tokens or are input tokens also included in that? Thanks for the post, it was an excellent read!

Is it unethical to short your own company's fake-coin?