DeepSeek Introduces Vision

(chat.deepseek.com)

123 points | by RIshabh235 3 hours ago

18 comments

  • insumanth 0 minutes ago
    [delayed]
  • rcMgD2BwE72F 2 hours ago
    Points to https://chat.deepseek.com/sign_in for me, that's just a login screen. Anything page with some info?
  • jiehong 1 hour ago
    For those not trying, this allows Deepseek to understand a picture (instead of just extracting text from it), and it can describe what's in the picture, but this is not an image generation system, so you can't ask it to modify an image.

    Personally, I'm a bit surprised the DS chat app still doesn't offer its own text to speech and speech to text features (I know DS doesn't have any ASR model for example, but there are quite a few in the open).

    • paulluuk 1 hour ago
      Can you explain what the benefits are of actually "talking" with the bot instead of typing and reading?

      As someone who would rather send a slack message to a coworker rather than actually walking over and talk to them, the idea of having to talk with my laptop is not appealing at all, haha.

      • itake 6 minutes ago
        I am someone that prefers a slack message to a coworker than talking to them and I use AI.

        My current flow is: Google Eloquent to capture 127WPM (my typing is best case is 65wpm). This lets me get the thoughts out without thinking too much about structure or flow, the same way I would brain-dump type it.

        Next I use AI to compress, summarize, and restructure to create a clear coherent message for my peer to read (which is way faster for them).

        When communicating with AI, its the same thing, except I skip the second step since AI does a good job at understanding my ramblings.

        ----

        It drives me crazy that some cultures only send voice messages to each other. It drives me crazy they can't be respectful of my time and use STT+AI to convert their 90 second monologue to a few written sentences.

      • arcanemachiner 11 minutes ago
        Much faster and better flow. Don't knock it til you've tried it.
      • throawayonthe 22 minutes ago
        it's very confusing. maaaybe if the stt is good and fast enough, speaking may be faster? english speakers can probably hit 150-180 wpm but seems like a hassle
      • stranded22 25 minutes ago
        Accessibility.
  • bjoli 2 hours ago
    What has been going on with deepseek recently? I have gotten lots of replies in Chinese and even more frequently, reasoning in Chinese as well.

    Is it a new silent update?

    • Shank 2 hours ago
      Well, it is a Chinese model, maybe it thinks better in Chinese?
      • bogdan 1 hour ago
        Hànzì can use 30%-40% fewer tokens than English. So, yes, it probably thinks better in Chinese.
        • Razengan 42 minutes ago
          If so, would other models like ChatGPT benefit from translating the user's prompt to Chinese/Japanese and thinking in Hanzi/Kanji and then converting the response back to the user's language before displaying it?
          • cocoflunchy 35 minutes ago
            I believe that most reasoning models actually think in their own "language" which is not really understandable by humans. The thinking traces that are shown in the UI are actually summaries generated by a smaller model in plain english (or user language). Sometimes this leaks through and you see some chinese/japanese characters in e.g. Claude's reasoning.
            • dryarzeg 2 minutes ago
              As far as I'm aware, it's not true for models like DeepSeek or other Chinese open-weight models (at least those that I have seen); their reasoning traces are fully composed from some human language, be it English, Chinese or another one; by the way, most of them can adapt their reasoning based on user language, for example, if user speaks English the reasoning more likely will be in English.

              I think that for DeepSeek problem (thinking and replying in Chinese) everything is kinda simpler: in their official chat, they're probably using some kind of system prompt which is (probably) written in Chinese, so that's why model may prefer Chinese in it's output.

            • seydor 20 minutes ago
              > summaries generated

              Or hallucinated

          • bogdan 34 minutes ago
            There are other even more efficient ways of doing this, i.e. using images instead of raw text https://xcancel.com/karpathy/status/1980397031542989305?lang...
          • grogg 33 minutes ago
            Yeah, it’s why the Caveman skill includes a Wenyan mode.

            https://github.com/JuliusBrussee/caveman

    • serf 1 hour ago
      This happens to me a lot when I ask a qwen3.6 model to respond to a question in JSON. No clue why.
    • surgical_fire 1 hour ago
      I use DeepSeek daily, never happened to me.

      I use the API however, not the chat interface.

    • abyssin 2 hours ago
      It doesn’t seem that recent to me, at least been like that for six months.
    • RIshabh235 2 hours ago
      yes, kind of silent update plus they might have better chinese datasets and user data for their training, that might be leading to chinese preference.
    • alfiedotwtf 1 hour ago
      Are you running out of context? I’ve found that tooling and giberish most of the time happens when I’m butting up against the high watermark of my context window. One other thing it could be, I’ve read that lower quanta like Q1 and Q2 for smaller models can leak Chinese
    • epolanski 2 hours ago
      It never happened to me with Deepseek, but it happened multiple times with Kimi 2.6.

      It also happened a handful of times with Anthropic models.

  • throwaw12 1 hour ago
    I wish they published a post where we read about capabilities, quality, accuracy and other parameters
  • tornikeo 1 hour ago
    I really need this as an API.

    Turns out, to use Claude Agents SDK, you need to have a vision enabled API. If Deepseek API could see, it can fully drive Claude Code and Claude Agents SDK. A project I'm working on relies on a Claude-in-CloudflareWorker setup and I've been relying on Qwen and gemini flash lite, both more expensive than Deepseek.

    Can't wait to have it available on deepseek.

    • 5701652400 6 minutes ago
      same here. I am using Gemini 2.5 Flash as VSCode "vision proivder" for Deepseek V4 Pro, but it is expensive and not accurate. can't wait for native Deepseek vision.
    • petesergeant 1 hour ago
      Have you looked at MiniMax or MiMo? Available today via OpenRouter, and it’ll make the path to porting to DeepSeek a line change https://openrouter.ai/collections/vision-models
  • arjie 2 hours ago
    If they'd do one of those little extraneous additions like Qwen does, so that I can have DS4 Flash with Vision that would be great. I've got to run a separate model entirely so that I can get vision and I'd prefer to just put it all in one space.
    • RIshabh235 59 minutes ago
      Maybe they will do now as they got huge funding.
  • alexwwang 34 minutes ago
    Does the api support vision yet?
    • RIshabh235 25 minutes ago
      No announcements about it yet.
      • alexwwang 22 minutes ago
        That makes sense. I haven’t found it work in api yet.
  • earth2mars 2 hours ago
    And it's really good and fast. Have tested with bunch of odd photos on what is happening. Overall the training set seems large enough to know what's what and where
    • RIshabh235 2 hours ago
      yes and I hope their rate of shipping increases after recent funding.
  • crvdgc 2 hours ago
    Vision has been in A/B testing for a while now (at least in China). Is there an official announcement that this will be available for everyone?
    • RIshabh235 2 hours ago
      I haven't seen any official announcement yet, works for me though.
  • innis226 2 hours ago
    Nice, is this available in the API now as well?
    • naseemali925 2 hours ago
      I am also waiting on the vision support in API. Its the only thing blocking me from buying their subscription.
      • dakolli 1 hour ago
        What subscription?
        • naseemali925 28 minutes ago
          I mean't topup. They don't have subsciptions.
    • RIshabh235 2 hours ago
      Not in the api yet.
  • thiago_fm 4 minutes ago
    Just wait until they release their coding model. Once they do an Opus-level coding model, the sandcastle of the AI economy in the US will fall
  • tw1984 46 minutes ago
    what is more interesting to me is why it takes so long for them to support vision.

    does it implies that Liang believes vision/voice is less important on its way to AGI?

    • RIshabh235 13 minutes ago
      Might be compute bottleneck due to the US chips act and migrating to Huawei ecosystem.
  • hklohani 1 hour ago
    [flagged]
  • ValveFan6666 2 hours ago
    [dead]
  • andrewstuart 2 hours ago
    OpenAI and Anthropic need to get this free foreign competition banned.
    • 0xpgm 21 minutes ago
      Is that before or after the OpenAI and Anthropic pay off all the people and companies who's copyrights were violated when they used their works for free to train their models?

      At least DeepSeek freely gives back the benefits.

    • epolanski 2 hours ago
      Care to expand on why? Or did you forgot the /s at the end?
      • dudisubekti 1 hour ago
        I feel like '/s' has ruined irony on the internet. Irony is at its best if left ambiguous, lol.
        • cromka 1 hour ago
          Nah, they're serious actually!
        • Weryj 1 hour ago
          Wait, did that need a /s?
      • ReptileMan 1 hour ago
        If everything goes to plan everyone involved with big US models will be trillionaire and everyone else will poor and unemployed. If there are open and cheap to run Chinese models (and please god silicon) the financial house of cards that we have build will fall, people involved with big US models will be poor and unemployed, and everyone else will be slightly less poor and unemployed than in the first scenario.

        What is good for Dario is good for America.

      • andrewstuart 1 hour ago
        Why do you think it’s free?

        Any ideas, theories where they get their payoff?

        • cromka 1 hour ago
          Yes, subscription options they sell on deepseek.com