vdomi

gottem

lmao, removing glm 5.3 flash... good thing i started blocking them on twitter, can't trust them anymore

> China is already basically in a depression You gotta expand on that, chief.

As much as I "hate" Anthropic, it did nothing wrong here. They could have used any closed or open model anyway

The price for Flash has stayed the same since April when v4 was released. I just checked it yesterday because I also thought DeepSeek increased their prices too much. The only time Flash was increased was briefly in August. But there's new peek pricing (double the price) during Chinese hours so yeah, it's a bit increased after all, but not much.

He says something and does something else. How is it unfair?

I would describe better as how much of my work I can delegate to the agent. Right now I'm delegating much more to Astra high than 6 months ago to Opus 4.6. Every dev has this feeling, it's weird to even argue what a better model/harness means.

Deepseek has claimed x6 profit on inference

HR stands for Human Resources, as in how the company manages ones of its resources, the humans. Is this not obvious at all?

I like how browser and websearch is handled in omp. But I only like these two features, it might be time for me to actually spend some time with pi