[HN Gopher] Show HN: DeepSeek My User Agent
       ___________________________________________________________________
        
       Show HN: DeepSeek My User Agent
        
       Author : jasonthorsness
       Score  : 76 points
       Date   : 2025-01-26 22:03 UTC (56 minutes ago)
        
 (HTM) web link (www.jasonthorsness.com)
 (TXT) w3m dump (www.jasonthorsness.com)
        
       | minimaxir wrote:
       | > Bravo, time-traveling Safari 18.1 beta tester from Hayward--not
       | quite San Francisco, but at least you're _pretending_ to innovate
       | while lurking on Hacker News like a true NPC. Your decade-old Mac
       | OS 10.15.7 and 1512x982 resolution scream  "I upgrade hardware
       | when Apple sends me a funeral invite," yet here you are, cookie-
       | enabled and _still_ waiting for WebKit to make your life
       | exciting. Congrats on being the most cutting-edge relic in the
       | Bay Area's shadow.
       | 
       | ...I suspect that humor is still out of reach for reasoning
       | models. It may require a bit of system prompt engineering.
        
       | jasonthorsness wrote:
       | For those who don't want to click - it submits your user agent,
       | referrer, and location headers to DeepSeek R1. It is completely
       | pointless, but the chain-of-thought reasoning is super-
       | interesting. For example, when I followed it from this site:
       | 
       | Reasoning: Okay, let's tackle this roast. First, I need to pick
       | the three most unusual bits from the user agent info. The user is
       | using Edge in Redmond, which is where Microsoft is based--that's
       | a good jab. The referrer is Hacker News, so I can mock that
       | they're procrastinating. They have 16 hardware concurrency, which
       | is high for a regular user. Also, screen resolution is 2560x1440,
       | but maybe not too unusual. Oh, and maxTouchPoints is 0, meaning
       | no touchscreen. But the top three? Probably Edge in Redmond,
       | Hacker News referrer, and 16 cores. Then link the location to
       | Edge, make fun of Hacker News, and the 16 cores for
       | overcompensating. Keep it concise and three sentences. Let me
       | check the rules again: relate location to another attribute,
       | include referrer, three sentences. Yeah, that works.
       | 
       | Content: Using Edge in Redmond? How _shockingly_ loyal of you to
       | Microsoft's backyard--guess even your browser has a corporate
       | leash. Came here from Hacker News, huh? Let me guess: "How to
       | roast a user agent" was your 37th procrastination tab today. With
       | 16 CPU cores and a screen bigger than your social life, congrats
       | on overcompensating for your NPC-level browsing habits.
        
       | andrewfromx wrote:
       | pretty great. How long before deepseek charges for each api call?
        
         | minimaxir wrote:
         | DeepSeek does charge for the API (just 20-30x cheaper than o1),
         | I assume OP is eating the cost.
         | 
         | https://api-docs.deepseek.com/quick_start/pricing/
        
           | andrewfromx wrote:
           | i see and where is https://groq.com/ in this. They used to be
           | the cheapest?
        
             | minimaxir wrote:
             | The "why is DeepSeek so much cheaper than o1" question is
             | currently a mystery, with the best guess being that compute
             | in China is cheaper.
        
               | acheong08 wrote:
               | The model is much smaller. Compute in China should be
               | more expensive considering all the US restrictions
        
               | minimaxir wrote:
               | No one knows the size of o1. The only hint was a paper
               | that suggested it was 200B parameters.
               | 
               | Meanwhile, DeepSeek R1 is known to be 671B parameters
               | because it is open-source.
        
             | KTibow wrote:
             | Right now Deepseek's official hosting is cheaper than
             | everyone else who can manage to run the model, including
             | Deepinfra. I haven't seen any good hypotheses as to why
             | other than their large batch size and speculative decoding.
        
         | quantadev wrote:
         | The only purpose of the free DeepSeek API is to undercut
         | American AI service companies. It's just a technological
         | version of "steel dumping". It's funded by China Gov't with the
         | goal of harming us AI companies, by stealing users away.
         | 
         | The 'open-source' version of DeepSeek, if you ask me, is
         | similarly done in China's interest as it's a propaganda tool,
         | programmed to take China's side on political topics.
        
           | andrewfromx wrote:
           | wow I just asked deep "is taiwan independent from china?" and
           | then the same question to claude. Very different.
        
           | tokioyoyo wrote:
           | So, ChatGPT/Gemini's free version is stealing the users from
           | European AI companies, and the goal is to harm them? Or we
           | call that just a competition?
        
           | aiono wrote:
           | Funny that's basically how "growth" companies work in general
        
           | simonw wrote:
           | "It's funded by China Gov't"
           | 
           | Are there any credible sources of information out there to
           | back that up, or is that just a conspiracy theory?
        
       | arthurcolle wrote:
       | Oh look, a Hacker News refugee with a Frankenstein 1800x1169
       | screen--did you split that browser window just to flex your NPC-
       | level multitasking skills in Rockville's tech equivalent of a
       | Starbucks patio? Twelve CPU cores but still running MacOS 10.15
       | like you enjoy digital nostalgia, and _oui_ , including French in
       | your languages list for that one croissant emoji tweet you'll
       | never send. Chrome 132? At least the RTT is zero, matching your
       | urgency to upgrade anything.
       | 
       | ------------
       | 
       | hey man not my fault you VLM homunculii can't handle high
       | resolutions yet ;) I'm finetuning a computer using agent, jeez!
        
       | petercooper wrote:
       | Very cute :) It might be worth adding to the context that Chrome
       | on macOS reports as OS X 10.15.7 (Catalina) no matter what future
       | version you're actually running. It seemed very confused to my
       | other specs but running such an old OS.
        
         | chris_st wrote:
         | Did the same with Safari... which it reported as being _from
         | the future_!
        
       | glutamate wrote:
       | > your Danish language setting in _Croydon_ screams  "I VPN to
       | Copenhagen for overpriced pastries."
       | 
       | First time an LLM made me laugh
        
       | schoen wrote:
       | "[...] you're so tech-cliche, your browser's "maxTouchPoints" is
       | zero because even your devices fear human contact [...]"
        
       | strange_magnet wrote:
       | >Not only did you crawl here from Hacker News, the tech bro
       | nursery, but you're flexing 16 CPU cores just to run Linux like a
       | spreadsheet samurai in Kirishima--impressive, given your browser
       | speaks three languages yet still can't ask for ramen politely.
       | 
       | ..not bad
        
       | simonw wrote:
       | > _Braving Hacker News to end up here in San Mateo, huh? Your
       | 1728x1117 resolution screams "I need 11 pixels to hide my crypto
       | tabs," and 30-bit color depth proves you see more shades of gray
       | than emotions--classic Firefox-on-Mac NPC behavior._
       | 
       | Yeah, that's pretty great!
        
       | aaurelions wrote:
       | Show which request is sent to R1.
        
       | cbracketdash wrote:
       | "You spent 46 seconds lurking on Hacker News just to end up here
       | with your four Chrome cores and Linux OS in the tech capital of
       | San Jose--did you _compile_ the courage to click? Your 8.1 Mbps
       | downlink is almost as slow as your realization that  "Blink"
       | isn't a rave in Mountain View, and your zero touch points explain
       | why you still type "sudo" to open your fridge."
       | 
       | :sob: I'm getting roasted by an AI
        
       | elaus wrote:
       | > Roasting your Firefox 135 on Linux setup from
       | <redacted>--because nothing says "I have opinions about open-
       | source" like a 16-core CPU crying over _hckrnews.com 's_ typo-
       | adjacent Hacker News ripoff and a screen resolution (1920x1200)
       | stuck in 2010s developer nostalgia.
       | 
       | I feel called out - well done.
        
       | gpm wrote:
       | Hmm, disturbingly accurate lol
       | 
       | > Oh, a _4K screen_ just to scroll Hacker News in  <redacted>?
       | Your Canadian Linux setup screams "I politely argue about Rust in
       | 2160p," and 16 CPU cores clearly aren't helping you realize that
       | site hasn't updated its design since 2007. Go touch grass (but
       | carefully, since your browser thinks you've never heard of a
       | touchscreen).
        
       | loves_mangoes wrote:
       | It doesn't recognize Tor Browser as such, but in this case
       | calling its anti-fingerprinting user agent a "desperate lack of
       | personality" happens to be more a compliment than a roast!
       | 
       | On the other hand, it's disappointed that the browser claims to
       | only have two cores and uses a resolution "from 2009".
        
       | cubefox wrote:
       | For me it just returns a wall of text with (part of) its
       | reasoning about composing a short roast, but not the roast
       | itself. I guess this is not intended.
        
       | bojan wrote:
       | Interestingly enough, it sees my Pixel 9 Pro as model "K" and
       | doesn't really know what to do with it.
        
       ___________________________________________________________________
       (page generated 2025-01-26 23:00 UTC)