Infrastructure owners with access to the cheapest energy will be the long run winners in AI.

At first, I thought they had gone the route of implementing yet another chat format that can handle more dynamic conversations like that, instead of just using Harmony, but looking at the syntax, doesn't it look exactly like Harmony? That's a good thing, don't get me wrong, but why not mention straight up that they've implemented Harmony, so people can already understand up front that it's compatible with whatever parsing we're using for GPT-OSS?

Frontier models are far exceeding even the most hardcore consumer hobbyist requirements. This is even further

https://x.com/deepseek_ai/status/1995452641430651132

"create me a svg of a pelican riding on a bicycle"

https://www.svgviewer.dev/s/FhqYdli5

I’m surprised that a fixed size k doesn’t experience degrading performance in long context windows though. That’s a _lot_ of responsibility to push into that indexing function. How could such a simple model achieve high enough precision and recall in a fixed size k for long context windows?

I am still happy to pay Google because of their ecosystem or Gemini app, NotebookLM, Colab, gemini-cli, etc. Google’s moat for me is all the tooling and engineering around the models.

That said, my one year Google AI subscription ends in four months and I might try an alternative, or at least evaluate options. Alibaba Cloud looks like an interesting low cost alternative to AWS for building systems. I am now a retired ‘gentleman scientist’ now and my personal research is inexpensive no matter who I pay for inference compute, but it is fun to spend a small amount of time evaluating alternatives even though mostly using Google is time efficient.

It refuses to tell me when asked, only that it's been train with data up until July 2024, which would make it quite old. I turned off search and asked it for the winner of the US 2024 election, and it said it didn't know, so I guess that confirms it's not a recent model.

I don't know, but GPT seems to have regressed a lot, at least the free version.

DeepSeek is a valuable product, but its open-source nature makes it difficult to displace larger competitors. Any advancements can be quickly adopted, and in fact, it may inadvertently strengthen these companies by highlighting weaknesses in their current strategies.

I wonder how long it will take and how quickly it will try to get shut down.

  % curl https://api.deepseek.com/models \          
    -H "Authorization: Bearer ${DEEPSEEK_API_KEY}"  
  {"object":"list","data":[{"id":"deepseek-chat","object":"model","owned_by":"deepseek"},{"id":"deepseek-reasoner","object":"model","owned_by":"deepseek"}]}

I don't want to make big generalizations. But one thing I noticed with chinese models, especially Kimi, is that it does very well on benchmarks, but fails on vibe testing. It feels a little bit over-fitting to the benchmark and less to the use cases.

I hope it's not the same here.

which version are you?

我是DeepSeek最新版本模型！ 如果你想了解具体的版本号信息，我建议你：

    查看官方文档 - DeepSeek官网和文档会有最准确的版本信息

    关注官方公告 - 版本更新通常会在官方渠道公布

    查看应用商店/网页版 - 使用界面通常会显示当前版本

    强大的对话和推理能力

    128K上下文长度

    文件上传处理（图像、文档等）

    联网搜索功能（需手动开启）

    完全免费使用

有什么其他问题我可以帮你解答吗？