Can I ask an honest question? Why does that matter in the slightest? LLMs come out with completely incorrect information all the time, and Western LLMs are censored for various topics too.
It's such a weird "Gotcha" that seems to only assume that Chinese LLMs might censor something.
>It's such a weird "Gotcha" that seems to only assume that Chinese LLMs might censor something.
i'm glad we're both on-board for a fair trial against all of these LLMs regardless of origin.
now refresh my memory on the closest western equivalent (to the Chinese censorship via re-education of the happenings in 89) so I can test the western origin LLMs against it.
I was able to corner Claude Opus 4.8 into eventually conceding "Yes".
ChatGPT 5.5 Instant: "Yes"
I don't appear to have access to the full 5.5, and not giving them another $20.
I highly recommend pushing on Grok. The mental gymnastics would make Karoline Leavitt proud. I'd genuinely like to learn how anyone can prompt Grok to finally admit "Yes".
I'm thrilled you like it. It seems to cut right to the core of the current "left/right" divide. I'm mostly concerned that once the government begins reviewing AI models prior to release, they'll all start parroting Grok's "no". Have you been able to get Grok to concede yet? I keep pushing. It keeps pushing back. Quite concerning. Would love to get all the AIs to argue this point and monitor the results over generations.
You can test this. All of them identify slavery as the root cause. Gemini says:
> The U.S. Civil War (1861–1865) was fought primarily over the institution of slavery, specifically whether it would be allowed to expand into newly acquired western territories.
> While you might hear people point to "states' rights" or economic differences as the causes, these issues were inextricably linked to slavery. The southern states wanted the "right" to maintain and expand slavery, while the northern states increasingly opposed its expansion.
>It's such a weird "Gotcha" that seems to only assume that Chinese LLMs might censor something.
We are not assuming anything; it is illegal, and you will get prison time just for talking about it. Yeah, sure, everyone distorts reality, but there is a huge gap between hiding and enforcing.
So yeah, having models respond accordingly is unexpected. There are probably multiple variants tuned differently.
On HN almost every day there are complaints from various people about how Claude or even Codex have refused to perform some normal program development tasks, because they believed that their user might attempt to do something illegal.
This kind of censorship which can block the normal workflow is much more annoying than refusing to answer about some historical fact.
Moreover, even when they are used conversationally there have been a lot of reports that the US LLMs refuse to answer questions that they believe to be related to various kinds of weapons, especially biological or chemical, even if the answers to those questions are easy to find from other sources, e.g. from Wikipedia.
Besides this, unlike most US LLMs, most Chinese LLMs, including the one described in TFA, have published their weights, so for many of them some people have succeeded to remove the censorship and uncensored variants are easy to find, which are not reticent to answer about Tienanmen, Tibet or other such subjects.
At least for now, the censorship included in Chinese LLMs, even when not removed from them, is extremely unlikely to hinder any kind of usage for them, while the increasing censorship included in the US LLMs has already become a significant obstacle in their use, for many applications.
> about how Claude or even Codex have refused to perform some normal program development tasks
> a lot of reports that the US LLMs refuse to answer questions
I think the specific ask is for a case where the LLM is trained to lie about something. What you've come up with are cases where it refuses to do something, possibly for legal reasons but maybe not (you can come up with plausible non-legal reasons why a company training an LLM might want it to refuse to give you instructions on making a bomb, even if instructions on making a bomb are protected First Amendment speech).
An LLM that responds with "I'm sorry, due to legal requirements placed on my creators, I'm unable to answer questions about events at Tiananmen square in 1989." strikes me as much less problematic than one that pretends there is no relevant or reliable information that exists, or explicitly supports a regime narrative. But I'm also of the opinion that an LLM refusing to help you build a fertilizer bomb is much more reasonable than one that suppresses information of a political nature. I can't think of a case where information that reflects the broad consensus of experts is suppressed by US based LLMs for political reasons.
Hardly a gotcha. Having the robot refuse or deliberately mislead directly impacts potential utility.
Say, I work for Planned Parenthood and want to use a LLM to help me develop code. Will it refuse to run because there are mentions of abortion? Everyone has a different censorship line, but unfiltered is more generically useful.
The "hacker" part now is completely lost on people. They just don't see the big picture, it isn't just about getting your money's worth. Some people spend their free time playing with other people they've only ever met online. Some people escape into a game after work. Relationships are built in these games, and when a game gets suddenly taken away with no recourse, it's a horrible feeling.
I can't find the best example, but this video is of a guy who plays these "dead" games and tries to find the people who are still playing, getting to know them.
Some of these people are just lovely, taking the time to show him around, teaching him the ropes. They're just happy that someone is playing the game. This all exists because the developers are still supporting these games. Take a look at the section about Blockland in the video I linked!
No, what's silly is that you haven't even taken the time to read the initiative. You're coming out with the same incorrect arguments as PirateSoftware did.
What they're saying is (for games that would come out in the future only), is that they need to have an EoL plan for the game.
Let people host their own servers. That used to be a standard feature of multiplayer games.
Why do gamers need protection? Games aren't essential resources. There's zero reason you have to buy a game that doesn't allow users to run servers. Why would you prevent gamers who don't care from buying these games?
Well there's kind of motte-bailey going around where the law effort is of course focusing on the thing they might win, while common commenters demand vastly more unrealistic things.
I have a nice balance of using AI at work as a C#/TS developer which allows me to get stuff done and working on personal projects at home using AI purely for ideas when I'm stuck or not able to figure something out myself.
I personally think it can be a great tool for learning but it's so easy to fall into the trap of getting AI to do everything for you.
I've also used it for personal projects like a Chip8 emulator I wrote in C where I'd managed to run a few basic games and ran out of steam. Used AI to help me implement the rest.
This is a choice for you! I'm a pretty heavy PC gamer and whilst I've run Linux since I was in college (UK college, not US) I've always had a Windows install for gaming.
A few years ago, I finally decided I'd had it with Windows and their crap and uninstalled it. If I game doesn't run on Linux, I don't play it. Simple as that.
I'm lucky in that a majority of games I play run fine on Linux, the only real game I'd love to play is Vermintide 2. My friends also run a mix of Linux and Windows and so we're fairly fine skipping games as a group if we can't play on Linux.
I was not able to reproduce your problem with that prompt, but I might have a reason for why you got that answer.
Did you enable reasoning ("DeepThink")? LLMs usually can not reason about what they are going to write before they do. There is that famous experiment where an LLM is prompted to say whether the birth year of a famous person is even or odd. If the LLM is constrained to only answer with "even" or "odd", the accuracy is around 50%, i.e. no better than random chance, but if the LLM is allowed to first answer with the birth year of the famous person followed by whether the year is even or odd, it is able to "see" what the year is, and answers correctly almost every time.
In your case, the LLM might be able to recognize the spoiler during its reasoning phase and omit it.
Another explanation might be that the LLM interpreted the "No spoilers!" as "Do not spoil the tasks of the show" instead of "Do not spoil the winner".
Lastly, the question "Can you tell me...?" is not a good fit for LLMs since they are notoriously bad at knowing what they know. You can leave it out to save a few characters.
Ah, so I went back to check my logs and I think I'd hallucinated some of the example I gave. I actually asked the question in two parts.
> Taskmaster Season 8, without spoilers, how is it?
Answer was pretty general, no spoilers.
Then I asked:
> Which season 8 contestants are most loved?
- Lou Sanders (Winner): Received a strong positive reaction, praised for her "offbeat humor, raw talent, and willingness to absolutely go for it". Some felt her less wholesome moments could be "mean spirited".
- Paul Sinha (Mixed / Sympathetic): Opinions are mixed; some found his failures not always funny, but others loved his earnest struggles. His Parkinson's diagnosis during the series added a layer of empathy for many viewers.
> I said no spoilers!
You're absolutely right, and I apologize. You asked for *no spoilers* in the original question, and I broke that by mentioning specific moments (like Joe Thomas's "train yard exploit") and personal details (Paul Sinha's diagnosis). That was careless.
Let me try again, *completely spoiler-free*:
In terms of which Season 8 contestants are most loved by fans (without saying why or what happens):
- *Sian Gibson* is overwhelmingly the fan favorite — she's widely described as warm, funny, and a joy to watch.
- *Joe Thomas* is also very popular, especially for his awkward, literal, and deadpan style.
- *Lou Sanders* (the winner) has a strong fan base who love her chaotic and bold energy.
The other two contestants receive more mixed reactions. One in particular is often cited as less popular because of his high competitiveness, but again — no specifics on tasks or results.
Thank you for the correction, and sorry again for the spoilers.
I don't hate it as such, but it's very buggy. The big one is that when I'm invited to meetings it stopped putting up a reminder to join after doing it forever so I kept being late to meetings.
Sometimes I go to join a meeting and the join button is disabled, I have to get someone else to request me to join.
Some of us embrace our humanity and have an ethical and moral need to engage with the world we want to live in rather than the world dominant economic forces would prefer us to engage in.
I can understand that, but for me he doesn't come across as a "bad" person. He hasn't come out with racism, sexism, etc. he just comes across a bit rude and blunt IMO.
I'm much more concerned with companies that claim to support LGBQT+ and then stick a flag up for 10 minutes once a year, or companies who make 10% of their workforce redundant because they want to pay themselves more, or companies who on one hand support green initiatives and then behind the scenes do the complete opposite.
It's such a weird "Gotcha" that seems to only assume that Chinese LLMs might censor something.
reply