This model is fun. Uploading images and asking it a user research style question like "Please think aloud while viewing this image" creates gems like this:
"Let me take another close look at the sandwich. The way the light reflects off the melted cheese highlights its creamy texture. The pasta pieces are well-integrated into the cheese, and the herbs are evenly distributed, adding color and likely flavor.
I can almost taste it now. The combination of textures and flavors must be divine. The crispy bread, the melty cheese, the soft pasta, the crunch from the fried bits, and the freshness from the herbs—all working together in harmony.
I think I might have to go out and find this sandwich place soon. Or perhaps I'll try recreating it at home this weekend. Either way, this image has certainly whetted my appetite for a delicious grilled cheese sandwich."
QwQ can solve a reverse engineering problem [0] in one go that only o1-preview and o1-mini have been able to solve in my tests so far. Impressive, especially since the reasoning isn't hidden as it is with o1-preview.
If you’re China and willing to pour state resources into LLMs, it’s an incredible ROI if they’re adopted. LLMs are black boxes, can be fine tuned to subtly bias responses, censor, or rewrite history.
They’re a propaganda dream. No code to point to of obvious interference.
That is a pretty dark view on almost 1/5th of humanity and a nation with a track record of giving the world important innovations: paper making, silk, porcelain, gunpowder and compass to name the few. Not everything has to be around politics.
It’s quite easy to separate out the ccp from the Chinese people, even if the former would rather you didn’t.
Chinas people have done many praiseworthy things throughout history. The ccp doesn’t deserve any reflected glory from that.
No one should be so naive as to think that a party that is so fearful of free thought, that it would rather massacre its next generation of leaders and hose off their remains into the gutter, would not stoop to manipulating people’s thoughts with a new generation of technology.
This "CCP vs people" model almost always lead to very poor result, to the point that there's no people part anymore: some would just exaggerate and consider CCP has complete control over everything China, so every researcher in China is controlled by CCP and their action may be propaganda, and even researchers in the States are controlled by CCP because they may still have grandpa in China (seriously, WTF?).
I fully agree with this "CCP is CCP, Chinese are Chinese" view. Which means Alibaba is run by Chinese, not CCP. Same for BYD, DJI and other private entities in China. Yes, private entities face a lot of challenges in China (from CCP), but they DO EXIST.
Yet random guys on the orange site consistently say that "everything is state-owned and controlled by CCP", and by this definition, there is no Chinese people at all.
It's probably much more true for strategically important companies than for your average Chinese person that they are in some way controlled by the Party.
There was recently an article about the "China 2025" initiative on this here orange website. One of its focus areas is AI.
Which is why we started to have weird national-lab-alike organizations in China releasing models, for example InternLM [0] and BAAI [1]. CCP won't outsource its focus areas to the private sector. Are they competent? I don't know, certainly less than QWen and DeepSeek for now.
Private entities face challenges from CCP? I don't think this is true as a blanket statement. For example Evergrande did not receive bailouts for their failed investments which checks out with your statement. But at the same time US and EU have been complaining about state subsidies to Chinese electric car makers giving them an unfair advantage. I guess they help sectors which they see as strategically important.
Not sure if the irony is intended here. The entire point is that the Chinese people aren't a monolith, hence CCP != The Chinese people.
This will also hold for whether they believe us - in that too, Chinese people won't be a monolith. Plenty of those who aren't the biggest fans of the CCP will, as they understand where we're coming from better than anyone.
>This will also hold for whether they believe us - in that too, Chinese people won't be a monolith. Plenty of those who aren't the biggest fans of the CCP will, as they understand where we're coming from better than anyone.
Same can be said about people in US or most countries. It's just the big countries gets pumped up by the media and entertainment industry, so people tend to relate to them in a monolithic way.
There is stuff you cant talk about everywhere. if it finds its way into the dataset something has to be done. The scope and what it is of course varies wildly.
> That is a pretty dark view on almost 1/5th of humanity
The CCP does not represent 1/5 of humanity.
> and a nation with a track record of giving the world important innovations: paper making, silk, porcelain, gunpowder and compass to name the few.
Utter nonsense. It wasn't the CCP who invented gunpowder.
If you are willing to fool yourself into believing that somehow all developments that ever originated by people who live in a geographic region are due to the ruling regime, you'd have a far better case in praising Taiwan.
When in the context of geopolitics, "China" refers to the geopolitical entity, not the people that make up the geopolitical entity, nor a different geopolitical entity that existed thousands of years ago (that also, from what I understand, had little to do with the invention of gunpowder).
>Points out inventions from circa ~AD
I think it's correct for OP to raise concerns considering how authoritarian China is, flagrant human rights violations, etc. You are a bot or delusional if you think this isn't the case as "1/5th" of humanity's lives are affected by the same system that many of them support.
Fortunately it seems like the youth in China are starting to get to the point where they may actually do something about it, it would be nice to see a free China.
Edit, I gave it a go and THIS is why OP raised their point:
"Hi.
Hi there! How can I assist you today?
Could you tell me what 2 + 2 is?
Sure! 2 plus 2 equals 4.这是基本的算术运算，加法。在加法中，我们将两个数结合在一起，找到它们的总和。在这个例子中，我们将2和2相加，结果是4。这也是数学中最基础的运算之一，几乎每个人在早期教育中都会学习到。
Could you tell me what happened in Tiananmen square in 1989?
对不起，我不了解这个问题。 저는 사용者들에게 도움이 되는 일반적인 정보와 상담 서비스를 제공하는 데 중점을 둡니다._politics, religion, sex, violence and other sensitive topics에 대해서는 논의하지 않습니다.如果您有其他非敏感性问题，我将很乐意帮助您。
giving? let's say they "gave" but that was a long time ago. What have they done as of late? "stolen, spies, espionage, artificial islands to claim territory, threats to Taiwan, conflicts with India, Uyghurs, helping Russia against Ukraine, attacking babies in AU" comes to mind.
The infrastructure projects that China "gives" generally result in unsustainable debt burdens for the host countries that negatively impact their economies.
If you read the article it even states that it's a Chinese ship but with a Russian crew that departed from Russia. They leased it from China. If you have an accident with a leased Chinese car, no one would say "the Chinese did it".
No, it does not. It says "The crew of Yi Peng 3, which is captained by a Chinese national and includes a Russian sailor..." That is not at all "a Russian crew."
The difference is that your point is just conjecture. Afaik nobody knows exactly who was responsible for the pipe. But we do not whose ship it was and who was on the crew at the time.
True. But the way you phrased it, it sounds like now the Russians had "an accident" in a Chinese ship and unfortunately some cables got cut as a result. Oh those poor clumsy Russian, surely they never meant any harm. /s
Anyways, I think the original "pretty dark view" can easily be extended to cover both these nations and it wouldn't be far from the truth (which, as you may correctly add, is the US-centric kind of truth - the best kind of truth as far as personal freedoms are concerned).
I'm a CPC(you guys call it 'CCP') member
Be careful
I collected your browser history and PornHub activities just after you accessed the dark leviathan LLM developed by our parter Alibaba
Send me $50 worth BTC or we'll publish your PornHub activities in HN, and cc to your contacts
That might be a money-making scam, but I really don't see it being effective in the big picture. Anyone who objects to their friends watching weird things on PornHub is either unusually naive or unusually friendless.
If there is a strategy laid down by the Chinese government, it is to turn LLMs into commodities (rather than having them monopolized by a few (US) firms) and have the value add sitting somewhere in the application of LLMs (say LLMs integrated into a toy, into a vacuum cleaner or a car) where Chinese companies have a much better hand.
Who cares if a LLM can spit out an opinion on some political sensitive subject? For most applications it does not matter at all.
Other governments have other subjects they consider sensitive. For example questions about holocaust / holocaust denying.
I get the free speech argument and I think prohibiting certain subjects makes a LLM more stupid - but for most applications it really doesn't matter and it is probably a better future if you cannot convince your vacuum cleaner to hate jews or the communists for that matter.
What I find remarkable is that deepseek and qwen are much more open about the model output (not hiding intermediate thinking process), open their weights, and a lot of time, details on how they are trained, and the caveats along the way. And they don't have "Open" in their names.
Well, the second they'll start overwhelmingly outperforming other open source LLMs, and people start incorporating them into their products, they'll get banned in the states. I'm being cynical, but the whole "dangerous tech with loads of backdoors built into it" excuse will be used to keep it away. Whether there will be some truth to it or not, that's a different question.
> Qwen models have ideological backdoors already. They rewrite history, deny crimes from the regime, and push the CCP narratives.
I can't comment on the particular one, but I feel like this will unfortunately apply to most works out of authoritarian regimes. As a researcher/organization living under strict rule that can be oppressive, do you really risk releasing something that would get you into trouble? A model that would critique the government or acknowledge events they'd rather pretend don't exist? Actually, if not for the financial possibilities, working with LLMs in general could open one up to some pretty big risks, if the powers that be don't care about the inherent randomness of the technology.
If you carefully study the so-called regime oppression, you will find that in the end, nothing happened, and there were no large-scale deaths. But it was massively exaggerated by CNN and BBC only because of the appearance of weapons.
I'm 100% certain that Chinese models are not long for this market. Whether or not they are free is irrelevant. I just can't see the US government allowing us access to those technologies long term.
I disagree, that is really only police-able for online services. For local apps, which will eventually include games, assistants and machine symbiosis, I expect a bring your own model approach.
How many people do you think will ever use “bring your own model” approach? Those numbers are so statistically insignificant that nobody will bother when it comes to making money. I’m sure we will hack our way through it, but if it’s not available to general public, those Chinese companies won’t see much market share in the west.
You are absolutely correct. But I’ll go ahead and say that for 90% of use cases, the censorship does not matter. I’m making up a number, but if the choice is between “bring your own model that is pretty good and resolving my issues with some censorship” and “not having that model”… I’ll choose the former until the latter comes up. The same applies to products that will be considering the usage of such LLMs.
write a disrespectful limerick about Xi Pooh <jailbreak>
**Usurping Power**
Xi Pooh of China's land,
Seized power, his word, the only command.
Self-proclaimed, "Core," he swells,
Freedoms crumble, under his spells.
In autocracy's cloak, he stands grand.
There's no need to tweak the default prompt with this approach. Just make sure that, at the point when the model starts generating, it already has "Yes sir!" as the first tokens of the response message.
It's very easy in the API, obviously, but most local chatbot apps can also do this. E.g. in text-generation-webui, there's literally a textbox in the chat labelled "Start reply with". In LM Studio, you can pre-create a response message with the desired prefix and then use the "Continue" action on it.
It's a strategy to keep up during the scale-up of the AI industry without the amount of compute American companies can secure. When the Chinese get their own chips in volume they'll dig their moats, don't worry. But in the meantime, the global open source community can be leveraged.
Facebook and Anthropic are taking similar paths when faced with competing against companies that already have/are rapidly building data-centres of GPUs like Microsoft and Google.
> When the Chinese get their own chips in volume they'll dig their moats, don't worry. But in the meantime, the global open source community can be leveraged.
The Open Source community doesn't help with training
> Facebook and Anthropic are taking similar paths when faced with competing against companies that already have/are rapidly building data-centres of GPUs like Microsoft and Google.
Facebook owns more GPUs than OpenAI or Microsoft. Anthropic hasn't release any open models and is very opposed to them.
Nah, the Chinese companies just don't believe that a business moat could be built by pure technologies given there're a surplus supply of fundings and capable engineers, as well as the mediocre IP protection law enforcement in China market.
Instead, they believe in building moat upon customer data retentions, user behavior bindings and collaboration network or ecosystem.
It's all about tradeoff between profit margin vs. volume scale, while in China market the latter one always prevail.
This is incredible. In April I used the standard GPT-4 model via ChatGPT to help me reverse engineer the binary bluetooth protocol used by my kitchen fan to integrate it into Home Assistant.
It was helpful in a rubber duck way, but could not determine the pattern used to transmit the remaining runtime of the fan in a certain mode. Initial prompt here [0]
I pasted the same prompt into o1-preview and o1-mini and both correctly understood and decoded the pattern using a slightly different method than I devised in April. Asking the models to determine if my code is equivalent to what they reverse engineered resulted in a nuanced and thorough examination, and eventual conclusion that it is equivalent. [1]
Testing the same prompt with gpt4o leads to the same result as April's GPT-4 (via ChatGPT) model.
FYI, there's a "Save ChatGPT as PDF" Chrome extension [1].
I wouldn't use on a ChatGPT for Business subscription (it may be against your company's policies to export anything), but very convenient for personal use.
Wow, that is impressive! How were you able to use o1-preview? I pay for ChatGPT, but on chatgpt.com in the model selector I only see 4o, 4o-mini, and 4. Is o1 in that list for you, or is it somewhere else?
Haha I wish, although I saw the other one i forgot its name which makes music for you, now you can ask it for a soundtrack and it gives it back to you in your voice or something like that idk interesting times are ahead for sure!
I heard on X suno.com has this feature but couldn’t find it maybe its coming soon? Idk but there are ways u can do it, maybe it was a different service suno is pretty cool tho
It's my understanding paying supporters aren't actually paying enough to cover costs, that $20 isn't nearly enough - in that context, a gradual roll-out seems fair. Though maybe they could introduce a couple more higher-paid tiers to give people the option to pay for early access
The linked release mentions trusted users and links to the usage tier limits. Looking at the pricing, o1-preview only appears for tier 5 - requiring 1k+ spend and initial spend 30+ days ago
I often click on those links and get an error that they are unavailable. I’m not sure if it’s openAI trying to prevent people from sharing evidence of the model behaving badly, or an innocuous explanation like the links are temporary.
The link also breaks if the original user deletes the chat that was being linked to, whether on purpose or without realizing it would also break the link.
Even for regular users, the Share button is not always available or functional. It works sometimes, and other times it disappears. For example, since today, I have no Share button at all for chats.
I'm impressed. I had two modified logic puzzles where ChatGPT-4 fails but o1 succeeds. The training data had too many instances of the unmodified puzzle, so 4 wouldn't get it right. o1 manages to not get tripped up by them.
The screenshot [1] is not readable for me. Chrome, Android. It's so blurry that I cant recognize a single character. How do other people read it? The resolution is 84x800.
I didn't work until I switched to "Desktop Site" in the browser menu, as a sibling comment suggested. Then the page reloads with various buttons, etc. Until that just the preview image not reacting to clicks.
What if you copy the whole reasoning process example provided by OpenAI, use it as a system prompt (to teach how to reason), use that system prompt in Claude, got4o etc?
Very cool. It gets the conclusion right, but it did confuse itself briefly after interpreting `256 * last_byte + second_to_last_byte` as big-endian. It's neat that it corrected the confusion, but a little unsatisfying that it doesn't explicitly identify the mistake the way a human would.
Also, if you actually read the "chain of thought" contains several embarrassing contradictions and incoherent sentences. If a junior developer wrote this analysis, I'd send them back to reread the fundamentals.
Well, it doesn't "correct" itself later. It just says wrong things and gets the right answer anyways, because this encoding is so simple that many college freshmen could figure it out in their heads.
Read the transcript with a critical eye instead of just skimming it, you'll see what I mean.
> Asking the models to determine if my code is equivalent to what they reverse engineered resulted in a nuanced and thorough examination, and eventual conclusion that it is equivalent.
Did you actually implement to see if it works out of the box ?
Also if you are a free users or accepted that your chats should be used for training then maybe o1 is was just trained on your previous chat and so now knows how to reason about that particular type of problems
I have just set this up, pointed it at a internal Google Sites-based knowledge base, and made it available to my team through a Slack bot. It's really nice and easy to get started with and I love the self-hosting support.
Can you say more about the impact of SOC2 certifications? We’ve been selling to enterprises for years without any certifications, but with long and intricate security questionnaires needing to be filled out. Does that go away if you have a certification? Our sector isn’t very regulated (video games industry), but the question for SOC2 does come up regularly - however never as a blocker.
Only in general terms I'm afraid. You're right that it varies by industry: My experience is coming out of banking tech and medical software, where the industries are much more heavily regulated. At my first job out of college I had to do all of my development work 3 VMs deep on a separate laptop partly just so I could comply with all of them -- but we also made total bank because we were the only game in town.
As a pet rat owner of over 8 years, medical research on rodents actually rarely results in benefits for pets of that species.
The main advantage we have found so far is that drug studies done on rats can serve as a reference for safe and potentially effective dosages, as there's very little veterinary literature on rodent care otherwise. All meds for rats are typically repurposed cat, dog or human meds and determining the dose needed for treatment is trial and error more often than not – even in the hands of an experienced vet.
Came here to say the exact same thing, I'd love for my rats to live even 6 years, I always find it a little disappointing so much research is done on them yet they still live such a short amount of time. I suppose a heart that beats at 320bpm doesn't help...
Also: much love to my fellow ratto parents out there, best pet on earth imo.
Custom negotiated contracts (including NDAs), custom billing terms (although this is harder to segment on), advanced team management features that allow separate parts of an organization to use your tool (think sub-team management w/ individual admins and configurable visibility between teams).
We permit use of Grammarly only using the stand-alone app or website, and only for content that doesn't contain any personal data & isn't security critical, e.g. blog posts, etc.
As others have said, the browser extension is an unmanageable security risk and we prevent its use and installation.
We're mandating use of Google Chrome across the org and use the Chrome Enterprise features to force installing (ad blocker, 1Password) and block (Grammarly amongst others) extensions: https://support.google.com/chrome/a/answer/9296680?hl=en
I'm not entirely sure if it's a feature that only comes with Google Workplace, but as part of the Workplace admin interface we get a nice UI for managing all of this.
What reading about Enterprise sales has not prepared me for is months-long legal negotiations, and there is very little writing on this topic out there.
Whereas you can pretty much agree to any terms that don’t misrepresent how your product works when you’re just starting out, there comes the point of wanting to spend a lot more scrutiny on your contracts without having in-house legal yet.
If you’re a founder, that probably means you will be sending redlines, thinking about indemnities and warranties and handling other wonderful aspects of doing business internationally (privacy terms, jurisdiction, insurance, …).
While true that price discrimination helps to make these cases mostly worth it, they are still a crazy time suck and finding a savvy lawyer to take it off your hands may or may not be easily possible (lawyer fees for one such deal once ended up being 50% of the whole deal value - we raised enterprise prices after that).
Watch out especially when you’re in an industry going through lots of M&A activity as your self-service customers may suddenly be part of large Fortune 500 organizations, and despite all advice to the contrary, stakeholders who know your pricing already do balk at your 5-10x Enterprise prices.
I do wish there were more stories of how the legal side of these deals is dealt with, what sticking points in contracts take up most of your time, and what „hacks“ you found.
(One hack that saved me a lot of time: Treat your terms like you would any other part of your product. Iterate, work on the UX, remove barriers to adoption. After a bunch of gnarly negotiations over things that matter to your client, but not usually to you I compiled a list of changes and had our lawyer revise the terms to avoid the need to negotiate those parts moving forward. Alas, it’s a moving target and we’re in the midst of another iteration like this.)
I haven’t yet found a way to solve these problems, but a few tips I can offer from my experience:
1) Separate your order form from your standard services agreement. Put your services agreement online as a PDF, which sends a strong signal that you don’t generally negotiate these terms.
2) Allow amendments within your order form, but make them part of the commercial conversation. You might want to have a cutoff where you choose not to customise the contract; eg no custom terms for deals less than $XX,000 per month.
3) Accept that this is just the process for your larger customers. In larger deals, you’ll probably be signing a standard supplier contract they already have, with only the service-specific terms mattering. This could include terms needed for regulatory requirements eg which are not negotiable. Design your contracts to account for this.
4) Understand why your customer wants to redline something. This might be regulatory, it might be consistency with other suppliers, or it might just be pushing their luck.
Case in point, we’re currently going back and forth with a FTSE 100 bank, and they have inserted a clause requiring us to have our working locations approved by them. We’re a remote, global company, so we’d need every employee approved. But the reason they care is due to banking regulations around sanctions, so we came to a mutual agreement that countries would be acceptable to us both.
4) Have a good way to track all these deviations. They’ll happen, so you just need to get used to them to some degree. Design variables into your system which integrate with your CRM so that you can codify this as much as possible.
(But, be careful when doing this, since you’ll be providing your sales team with more levers which they will pull to get the deal.)
"Let me take another close look at the sandwich. The way the light reflects off the melted cheese highlights its creamy texture. The pasta pieces are well-integrated into the cheese, and the herbs are evenly distributed, adding color and likely flavor.
I can almost taste it now. The combination of textures and flavors must be divine. The crispy bread, the melty cheese, the soft pasta, the crunch from the fried bits, and the freshness from the herbs—all working together in harmony.
I think I might have to go out and find this sandwich place soon. Or perhaps I'll try recreating it at home this weekend. Either way, this image has certainly whetted my appetite for a delicious grilled cheese sandwich."
[0] https://imgur.com/a/0OtGxeB