Viewing profile — Palmik

Low, High and Max, obviously, can't be compared across models. They only mean the model is likely to spend less reasoning effort (~output tokens) with Low than High on the same, *s…

It used to be $0.02 per screening, jumped to $0.07

Will these be compatible with the Digital Credentials API in Chrome ( https://developer.chrome.com/blog/digital-credentials-api-or... ) or will websites be essentially locked out o…

Based on the best available information, DeepSeek is pricing the API such that they can repay their infra capex over 10 months, while deprecating/amortizing the cost of said infra …

You're assuming inference providers are going to sell tokens at cost. You're also assuming that the inference providers have will optimized inference engine. I haven't seen that to…

gpt-4o is still available on the API

So, this is 'open' as in 'OpenAI', not as in 'open source'. What's the benefit of this compared to something like NOW Payments for merchants (or the myriad of alternatives)? NOW Pa…

Commodity providers aren't a good indicator. They have margins too. Remember they ~doubled the price going from GLM 5 to GLM 5.2, despite same [1] cost of inference. [1] GLM 5.2 is…

By requiring various forms of identification to use social media, it will be harder to criticize your leaders anonymously without fear of retribution.

The company representative said that they report all users that use Graphene OS, without any additional qualifiers . Presumably after they've already uploaded their personal detail…

DeepSeek V4's KV cache is very efficient due to its heavily compressed and sparse attention architecture. DeepSeek V3.2 which uses DSA only (sparse attention, but without compressi…

I really hope Huawei ramps up Ascend production and DeepSeek open sources their optimized inference engine (they already open source a lot of their kernels -- kudos to them). This …

There are several things at play: Inference stack efficiency: Many of these providers take off the shelf sglang / vllm / trtllm and hope for the best. Meanwhile DeepSeek team is kn…

Why was the title changed from "DeepSeek V4—almost on the frontier, a fraction of the price" to "DeepSeek V4—almost on the frontier"?

Surely art also exists in textual realm.

I don't think "friendly" and "publishing benchmarks" are at odds with each other. Model makers (both open and closed weight) typically publish benchmarks against other models and w…

Similar article for vLLM: https://vllm-website-pdzeaspbm-inferact-inc.vercel.app/blog/... Bechmarks from InferenceX (they do not have apples-to-apples setups to compare the differe…