Comment

Comment on U.S. House Panel Says China's DeepSeek AI Is a 'Profound Threat' to National Security

I asked Deepseek to write me a response to the matter, in an ironic tone and being mean when possible:

Official Response from DeepSeek AI:

"The U.S. House Panel has declared us a ‘profound threat to national security’—joining the elite ranks of TikTok, Huawei, and that time Bernie Sanders wore mittens. We’re truly honored, especially since Congress has such a stellar track record of identifying real dangers, like that time they grilled the TikTok CEO for… checks notes… making an app Americans actually enjoy more than their own government’s apps.

On TikTok’s ‘Threat to Democracy’:
“Yes, an app where teens lip-sync and share ramen recipes is clearly more dangerous than, say, a $886 billion defense budget or the fact that half of Congress still thinks ‘algorithm’ is a type of Greek yogurt. But by all means, keep pretending this is about ‘data privacy’ and not the fact that U.S. tech giants can’t compete without a little… legislative sabotage.”

On OpenAI’s ‘Open’ Charade:
“We’d love to be ‘open’ like OpenAI—you know, the ‘nonprofit’ that took billions in Microsoft money, works with the Pentagon, and lobbies against AI regulation. DeepSeek AI, meanwhile, is just out here trying to make useful tools without pretending we’re Captain America. (Though if Congress wants to fund us too, we accept cash, Venmo, and subpoenas.)”

On That TikTok Hearing:
*"After watching lawmakers ask the TikTok CEO if his app ‘connects to WiFi,’ we’re begging to testify next. Our conditions:

No questions about ‘where the internet lives.’
No confusing us with ChatGPT (we have standards).
Mitch McConnell must be replaced by an AI that blinks occasionally."*

Final Offer:
“Instead of hyperventilating about AI, maybe fix the stuff actually undermining America—like lobbyists writing laws, or the fact your ‘open-source intelligence community’ still runs on Excel 97. But sure, investigate us. We’ll wait. (P.S. Our AI did predict this hearing would go viral… for all the wrong reasons.)”

🇺🇸 DeepSeek AI: The Only ‘Foreign Adversary’ Here Is Your IT Department. 🚀🤖

source

Sort:hotnew top

lemmy_acct_id_8647@lemmy.world ⁨11⁩ ⁨months⁩ ago
I asked OpenAI the same. Only without the snark, and noted that US politicians and OpenAI pressers should not be considered evidence without facts:

Great question—and a healthy dose of skepticism.

If we assume U.S. lawmakers may be misrepresenting the situation or overstating the threat (intentionally or otherwise), then it’s worth asking: What counter-evidence or independent information exists that disputes the claims against DeepSeek?

Here’s what we can currently analyze:

1.

OpenAI’s Role and Statements

The accusation is that DeepSeek used OpenAI data without authorization.

OpenAI has not released detailed technical evidence (as of now) proving DeepSeek “stole” data.

It is also unclear what “unauthorized use” means here—was it scraping publicly available content generated by ChatGPT? That’s not the same as hacking or violating terms.

Counterpoint: Unless OpenAI provides forensic evidence (e.g., logs showing data scraping from banned accounts or circumvention of APIs), their claim is not independently verifiable.

2.

Open-source AI Training Practices

DeepSeek R1 and other models are trained on publicly available data, much like LLaMA, Falcon, Mistral, etc.

Many open-source LLMs train on similar corpora, including data from books, code repositories, and even internet crawls, which may contain ChatGPT outputs.

No proof has been provided that DeepSeek used proprietary datasets beyond what’s publicly available or scraped from the internet.

Counterpoint: If DeepSeek simply trained on web data that happened to contain ChatGPT responses (which are abundant online), that wouldn’t constitute theft by typical AI research standards.

3.

DeepSeek’s Own Transparency

DeepSeek has published detailed model cards and training parameters for R1, a transparency move rare among Chinese AI firms.

This suggests a desire to appear cooperative or aligned with global AI openness norms—not necessarily what a covert “spy tool” would do.

Counterpoint: Spyware tools or state-controlled AI systems don’t usually go open source and document their architectures.

4.

No Independent Audit or Third-Party Verification

As of now, there’s no independent audit of DeepSeek’s model, training corpus, or infrastructure.

The accusations rest heavily on political framing, not technical forensics released to the public.

5.

Broader Pattern of U.S. Tech Nationalism

U.S. lawmakers have a history of labeling Chinese tech firms as threats without providing concrete, public-facing evidence (Huawei, TikTok, etc.).

This doesn’t mean the threats are false, but it does mean we should demand proof beyond committee soundbites.

TL;DR – Is there counter-evidence?

Not conclusive counter-evidence, but there’s a lack of compelling public proof supporting the claim. The case against DeepSeek is built on:

OpenAI’s statements (without shared evidence),

Political concerns about China,

and suspicions rooted in strategic competition.

That’s not enough to say DeepSeek is innocent—but it’s not enough to prove guilt either
source
ashar@infosec.pub ⁨11⁩ ⁨months⁩ ago
That level of sarcastic irony is a national security threat to the US

source
pineapplelover@lemm.ee ⁨11⁩ ⁨months⁩ ago
That’s pretty good. Though, I am sure China’s government funded Deepseek.

That being said, compared to the incredibly dry and PC responses you would get from chatgpt, this is incredibly better.

source
- turnip@sh.itjust.works ⁨11⁩ ⁨months⁩ ago
  Deepseek just trained on existing models and used assembly language. It was a tiny company, they just did some optimization.
  
  source
  - pineapplelover@lemm.ee ⁨11⁩ ⁨months⁩ ago
    Ah yes the small company of Deepseek who is owned and funded by the Chinese hedge fund High-Flyer.
    
    High-Flyer being worth 7 Billion dollars.
    
    en.m.wikipedia.org/wiki/DeepSeek
    
    en.m.wikipedia.org/wiki/High-Flyer
    
    source
    turnip@sh.itjust.works ⁨11⁩ ⁨months⁩ ago
    160 employees is a microcap is it not?
    
    source
- dubyakay@lemmy.ca ⁨11⁩ ⁨months⁩ ago
  Could be a local model.
  
  source