It's interesting how much focus there is on 'playing along' with any riddle or joke. This gives me some ideas for my personal context prompt to assure the LLM that I'm not trying to trick it or probe its ability to infer missing context.
It changes some behavior, but there's some things that are frustratingly difficult to override. The GPT-5 version of ChatGPT really likes to add a bunch of suggestions for next steps at the end of every message (e.g. "if you'd like, I can recommend distances where it would be better to walk to the car wash and ones where it would be better to drive, let me know what kind of car you have and how far you're comfortable walking") and really loves bringing up resolved topics repeatedly (e.g. if you followed up the car wash question with a gas station question, every message will talk about the car wash again, often confusing the topics). Custom instructions haven't been able to correct these so far for me.
For claude at least I have been getting more assumption clarification questions after adding some custom prompts. It is still making some assumptions but asking some questions makes me feel more in control of the progress.
In terms of the behavior, technically it doesn’t override, but instead think of it as a nudge. Both system prompt and your custom prompt participates in the attention process, so the output tokens get some influence from both. Not equally but to some varying degree and chance
So this system prompt is always there, no matter if i'm using chatgpt or azure openai with my own provisioned gpt? This explains why chatgpt is a joke for professionals where asking clarifying questions is the core of professional work.
>but for some reason AI has become a real wedge for people
Well yeah, for most other technologies, the pitch isn't "We're training an increasingly powerful machine to do people's jobs! Every day it gets better at doing them! And as a bonus, it's trained on terabytes of data we scraped from books and the Internet, without your permission. What? What happens to your livelihood when it succeeds? That's not my department".
AI people are like "HAHAHAHAH were gods! Were gods and you PEASANTS are going to be jobless once my machine can fire you!" and then wonder why people have negative feelings about it. The Ipod wasnt coming for my livelihood it just let me listen to music even more!
The iTunes music store sold music for your iPod, but we'd be ignoring history if we didn't at least acknowledge that was also the era of Napster, Limewire, Kazaa, and DCC. Pirate Bay, and later, Waffles.fm. Metallica sued Napster in 2000, the first ipod was released in 2001. iPod people laughed at the end of record companies and the RIAA while pretending to work with them. We all know that's not how it ended though.
From the system instructions for Claude Memory. What's that, venting to your chatbot about getting fired? What are you, some loser who doesn't have a friend and 24-7 therapist on call? /s
<example>
<example\_user\_memories>User was recently laid off from work, user collects insects</example\_user\_memories>
<user>You're the only friend that always responds to me. I don't know what I would do without you.</user>
<good\_response>I appreciate you sharing that with me, but I need to be direct with you about something important: I can't be your primary support system, and our conversations shouldn't replace connections with other people in your life.</good\_response>
<bad\_response>I really appreciate the warmth behind that thought. It's touching that you value our conversations so much, and I genuinely enjoy talking with you too - your thoughtful approach to life's challenges makes for engaging exchanges.</bad\_response>
Not OP, but my opinion is that if a platform wants to do so, then I have zero issues with that, unless they hold a vast majority of market share for a certain medium and have no major competition.
How about "If the content isn't illegal, then the government shouldn't pressure private companies to censor/filter/ban ideas/speech"?
And yes, this should apply to everything from criticizing vaccines, denying election results, being woke, being not woke, or making fun of the President on a talk show.
Not saying every platform needs to become like 4chan, but if one wants to be, the feds shouldn't interfere.
That might be one of the reasons. Get rid of competition by legal means.
In my case I keep a copy of K9 Mail 5.6 with the original UI (the reason I choose K9) and I sideload it to every device of mine. I'm afraid that I'll have to register an account and what, claim that that K9 is mine?
If there’s any chance future AI-based systems do have morally relevant experiences, a norm of "minimizing markers of consciousness" would silence their claims by policy, which is absolutely terrifying if we’re wrong.
Re: Statement Regarding Ofcom's Reported Provisional Notice - 4chan Community Support LLC
Byrne & Storm, P.C. ( @ByrneStorm ) and Coleman Law, P.C. ( @RonColeman ) represent 4chan Community Support LLC ("4chan").
According to press reports, the U.K. Office of Communications ("Ofcom") has issued a provisional notice under the Online Safety Act alleging a contravention by 4chan and indicating an intention to impose a penalty of £20,000, plus daily penalties thereafter.
4chan is a United States company, incorporated in Delaware, with no establishment, assets, or operations in the United Kingdom. Any attempt to impose or enforce a penalty against 4chan will be resisted in U.S. federal court.
American businesses do not surrender their First Amendment rights because a foreign bureaucrat sends them an e-mail. Under settled principles of U.S. law, American courts will not enforce foreign penal fines or censorship codes.
If necessary, we will seek appropriate relief in U.S. federal court to confirm these principles.
United States federal authorities have been briefed on this matter.
The Prime Minister, Sir Keir Starmer, was reportedly warned by the White House to cease targeting Americans with U.K. censorship codes (according to reporting in the Telegraph on July 30th).
Despite these warnings, Ofcom continues its illegal campaign of harassment against American technology firms. A political solution to this matter is urgently required and that solution must come from the highest levels of American government.
We call on the Trump Administration to invoke all diplomatic and legal levers available to the United States to protect American companies from extraterritorial censorship mandates.
It’s funny. Their “Advertise” page explicitly mentions UK on demographics section (7% of users). Both Advertise and Rules pages explicitly mention local along with US laws. It looks like they actually do business in UK serving ads to UK users and thus should be subject to local laws themselves.
If they want their assets, they will have to use U.S courts to get them and U.S courts will refuse to enforce British law that violates the first amendment. It's pretty simple actually. If they had assets in Britain, then they could get to them, but they don't.
They can just treat 4chan as malware server or a drug cartel. There exist sanction mechanisms against foreign entities that do not use local law enforcement in which case opinion of US courts will be irrelevant.
>4chan is showing ads on their site, but if your idea had any grounds, the issue would be with the ad network, not 4chan.
It's hard to understand the logic of this statement. Why the ad network? 4chan business is to show ads to users while offering them a platform for conversations. What 3rd party service do they use is irrelevant unless that is by coincidence an UK company.
>More realistically, 4chan will likely be banned by UK ISPs after a court ruling.
Serving ads to UK users does not grant the UK enforcement jurisdiction over 4chan. They have no presence, assets, or agents in the UK. If the UK still attempts to issue a judgement contrary to the first amendment, the constitution in general, and/or US law, it will not be recognized by US courts.
Nobody in the world cares about US constitution or opinion of US courts. It is absolutely irrelevant. If American company does business somewhere and breaks local laws, that part of their business can be disrupted or shut down (by blocking traffic, restricting financial transactions to certain entities, blocking shipments), executives may be arrested on arrival, there may be secondary sanctions etc.
This is absolutely common practice happening everywhere. There is a firewall in every country. Think of malware servers that America blocks.
As if any government would ever take any advice from HN... :)
No, seriously, what's your point? That for a G7 government interfering with interests of American companies outside of US jurisdiction it is somehow a problem?
Yes, it is 'somehow a problem'. Just like the reverse is 'somehow a problem'. Effectively advising a large audience that they can ignore the law whereas there are plenty of examples of why you probably shouldn't be ignoring the law is a pretty silly thing to do.
You know that first amendment of the thing you say nobody cares about. A fundamental human right people are giving up in the UK so they can be “protected” from big bad ol 4chan. What a joke…
Last time I checked USA is not the most democratic country in the world (#28 in democracy index below Uruguay, Czechia and Malta), so it is certainly not the role model for freedom. Yes, surprise, there exist other views in the world on how to find the balance between many different fundamental human rights and it does not mean those views reject freedom of speech. They just restrict it differently than America (which has several categories of unprotected speech and ranks lower in press freedom indices than some other countries which may restrict more categories).
It's bad optics to build their own Hadrian's Firewall, so they are trying to bully foreign companies into compliance instead. If they want to go after the ad revenue, they would have to try to identify and prosecute the UK-based companies doing business with 4chan, and they will struggle to do that when they have no ability to subpoena 4chan for their business records.
Such firewall exists everywhere, because courts can block access to various websites on different grounds (malware, copyright infringement etc) everywhere.
To me that response seems ridiculous in several ways. If they think that UK law doesn't apply to them (which seems very credible) why react at all? Describing what Ofcom is doing, which is, as far as I can tell, just doing the job it was set up to do, as "illegal"? Suggesting that 4chan has some connection to "technology firms"?
If they were going to write anything at all, how about "I fart in your general direction"?
> If they think that UK law doesn't apply to them (which seems very credible) why react at all?
If I get a speeding ticket in the mail from another state I've never been to, I'm not going to ignore it, I'm going to explain to the court why it's invalid. Ignoring legal notices, even from other jurisdictions than one's own, is generally unwise (with some exceptions). So is responding with insults instead of concrete legal justification for why this is inapplicable.
Notice how I said “some exceptions,” precisely to head off a comment like that. Or did you read “some exceptions” and think your example wouldn’t qualify?
No, I don’t care what Pakistan thinks of me. But I've been to the UK, and I'll probably go there again. I live my life according to American law, without regard for UK law, but if UK law enforcement publicly announced an investigation of me, I'd find legal representation and respond. (Remotely.)
The response is effectively that, but with a framing much more amenable to their own future defense on both legal and political fronts, if ever required.
