Let me translate it for you. Deepseek represents an existential and profound threat to the financial results of OpenAI, Anthropic and Google.
U.S. House Panel Says China's DeepSeek AI Is a 'Profound Threat' to National Security
Submitted 5 days ago by schizoidman@lemm.ee to technology@lemmy.world
Comments
filister@lemmy.world 4 days ago
cabron_offsets@lemmy.world 5 days ago
The fucking president and the republican traitor filth are the threat to national security. I cannot wish enough ill upon them.
MelodiousFunk@slrpnk.net 5 days ago
I cannot wish enough ill upon them.
Not with that attitude. C’mon, keep trying like the rest of us.
forrgott@lemm.ee 5 days ago
“National security” has always been a euphemism for anything that threatened the status of the American oligarchy.
alwayshasbeen.jpg
taladar@sh.itjust.works 4 days ago
That is especially true since the US is at the ass end of nowhere so actual threats to its national security are incredibly rare.
futatorius@lemm.ee 4 days ago
That category also includes a number of things that will lead to the deaths of large parts of the US population.
forrgott@lemm.ee 4 days ago
Ooh. Whataboutism. So original!
Actually, no.
nuko147@lemm.ee 4 days ago
It is a bit funny to call it a threat to national security, when you think that they have TRUMP AS A PRESIDENT.
Xanthobilly@lemmy.world 5 days ago
Here, allow me to translate: National Security = $$$ from donors.
TropicalDingdong@lemmy.world 5 days ago
ComradeRachel@lemmy.blahaj.zone 5 days ago
It’s a profound threat to OpenAI here in the USA lol
bobs_monkey@lemm.ee 5 days ago
"Open"AI
BetaDoggo_@lemmy.world 5 days ago
“Free market” fans when free market
Nobilmantis@feddit.it 4 days ago
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. 🚀🤖
pineapplelover@lemm.ee 4 days 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.
turnip@sh.itjust.works 4 days ago
Deepseek just trained on existing models and used assembly language. It was a tiny company, they just did some optimization.
dubyakay@lemmy.ca 4 days ago
Could be a local model.
lemmy_acct_id_8647@lemmy.world 1 day 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
ashar@infosec.pub 4 days ago
That level of sarcastic irony is a national security threat to the US
Jaysyn@lemmy.world 5 days ago
Nothing more than techbro protectionism.
Arkouda@lemmy.ca 5 days ago
Sounds exactly like what an AI bent on world domination would say.
Octagon9561@lemmy.ml 5 days ago
Good, I’ll gladly use anything that’s a “profound threat” to US “national security”.
_cryptagion@lemmy.dbzer0.com 5 days ago
Maybe Trump will ban it like Tiktok.
Oh wait.
BrianTheeBiscuiteer@lemmy.world 5 days ago
So are tariffs. How can our nation be secure if we’re cut off from vital resources?
HorreC@lemmy.world 5 days ago
As much as grok is, in fact more now that it has all the US populations information in it.
MonkderVierte@lemmy.ml 5 days ago
The whole administration is currently a threat to national security. Nation being the people, that is.
TommySoda@lemmy.world 5 days ago
I nooo if only we didn’t defund all of our cybersecurity! Who could have seen this coming?!
turnip@sh.itjust.works 5 days ago
Why is cyber security relevant?
TommySoda@lemmy.world 5 days ago
Yeah, I guess that’s a good point. In my brain that made more sense but now I realize it makes no sense at all.
jabathekek@sopuli.xyz 5 days ago
Squizzy@lemmy.world 2 days ago
Good
just_another_person@lemmy.world 5 days ago
LOLZK!
cupcakezealot@lemmy.blahaj.zone 4 days ago
i mean can’t see how this is enforceable when they said the same thing about tiktok but the dumbass in chief keeps kicking the can down the road.
futatorius@lemm.ee 4 days ago
So what’s the great challenge with blocking it phoning home, or even better, subtly fucking with the data it sends back?
PunkRockSportsFan@fanaticus.social 5 days ago
GitHub has the code. Everyone should fork it to everywhere so they cannot delete it
bobs_monkey@lemm.ee 5 days ago
They’re just pissy that it outperforms their proprietary pieces of shit, thus the psyop campaign.
DarkWinterNights@lemmy.world 5 days ago
Even with Internet connection, LLMs only infer. The software you run it on (or online) is a different story, and it’s literally already the case with everything else for decades (although it is getting worse).
We weren’t upset enough when Google started scraping everyone’s emails, or how Meta/Amazon/Google/Microsoft/ByteDance track all your Internet activity right now via browser fingerprinting.
PunkRockSportsFan@fanaticus.social 5 days ago
Time to ditch browsers lol
Cethin@lemmy.zip 4 days ago
Presumably this is referring to using the online portal to use it. I don’t trust any of those, Chinese or otherwise. I run it locally.
LMStudio is the current software I use to manage LLMs, and I really like it. There’s a user-made app for Android that let’s you use it if you’re on the same network (or if you set it up to use on the internet) There are other options though.