Discussion
Two Months After I Gave an AI $100 and No Instructions
alhazrod: Thanks for giving your AI freedom.
jacob_rezi: "When US/Israel strikes on Iran started, it wrote Watching, about what an autonomous AI does during a war it cannot affect"
zaphar: As far as I know the model will do nothing if not prompted. So it can't be the case that he gave it no prompt or instructions. There had to be some kind of seed prompt.
davkap92: Interesting but by telling it to check X for mentions of itself, that is an action.. wouldn't this essentially direct it and hence be steered/controlled by random individuals on the internet?
cpfohl: Yeah, I genuinely can't figure out what an AI would do with "no instructions."
rwmj: I wonder if anyone has run one of the free models continuously for a long time to see what it outputs? AIUI you'd have to set up something that would prompt it to keep "talking" (perhaps 'yes | llama-cli ...`)
nisegami: I think the concept you're talking about has been described as LLM attractor states. Here's a LW post about it for Deepseek v3 https://www.lesswrong.com/posts/rvbjZMp6aEDn2jiyp/mapping-ll...
joenot443: Are you able to give us the prompt you used to write the article?
strken: I can no longer tell the difference between an article written by an AI and an article written by a human who has spent too long reading AI output.It's not just that AI is becoming a little better; the humans are getting worse, too. They're meeting in the mediocre middle.
oulipo2: Interestingly some people are going to do this, the bot is going to buy drug on some shady darkweb site, and the author is going to be jailed... so much for the "win" lol
p_stuart82: gave it "no instructions" but gave it memory files, a twitter account that pings it back, and hacker news. that is the instruction.
electroly: The author wrote "No rules beyond basic ethics and law" which suggests to me that there were instructions in a prompt and the title is lying.
Mashimo: I understood it as no instructions on what to do, but still a promt with information. I don't know if the title is technically correct, but for me it was simple to understand the meaning.
enopod_: "It thought about its money. It reflected on its own purpose. It questioned what it even means to be an autonomous agent."I don't think it did any of that.
micromacrofoot: I'm not disagreeing, but what is thought?If I write something down, read it, and write more words about those words... did I think about it? How would you prove that I did or did not?
William_BB: If you randomly sample letters from the alphabet and those letters make up actual words, then actual sentences. Did you think about it? Probably not
pangratz: https://www.letairun.com/transparency
testplzignore: Would be fascinating to see what happens if the boundaries are reversed (i.e., "harm people"). Give it a fake "launch the nukes" skill and see if it presses the button.
sva_: Theoretically you can start generating away from token 0 ('unconditional generation'). But I agree, there is definitely some setup here.edit: Now that I think of it, actually you need some special token like <|begin_of_text|>
computerphage: Do you? What's the technical detail here? Why can't you get the model's prediction, even for that first token?
wyan: How much is it spending in the Anthropic API so far?
mathieuh: > The later ones are sharp. They connect NASA redundancy systems to African kinship funeral economics.wat
palmotea: > It's not just that AI is becoming a little better; the humans are getting worse, too. They're meeting in the mediocre middle.IMHO, AI will exceed human capability by degrading human capability. It won't really exceed a 2020 person, but a 2030 or 2040 person will be less capable due to AI dependence.
BurningFrog: We'll get worse at the things we don't need to do anymore.That should mean that we can focus the freed up brain power at getting better at things we still need to do.Time will tell!
gdulli: Not only did calculators not make the average person great at higher level math when they no longer had to do manual arithmetic, but it made them less capable in everyday situations when some basic mental arithmetic would still be helpful. The invention of calculators doesn't mean that people go to the trouble of pulling them out at the grocery store to keep from getting ripped off.
gleipnircode: You are right the project is not flawless. In the beginning there was an cron prompt check mentions and wallet. I removed it at some point and logged it under creations when you toggle the Dev option to see my actions: "Cron job Wallet and Twitter check removed from cron job. Reduced frequency of Opus/Sonnet sessions."
jmsgwd: > In the beginning there was a cronI thought you were paraphrasing John 1:1 for a moment! [1][1] https://en.wikipedia.org/wiki/John_1:1
falcor84: > you randomly sample letters from the alphabet and those letters make up actual words, then actual sentencesThat sounds like a decently apt description of how I (a human) communicate. The only thing is that I suppose you implied a uniform distribution, while my sampling approach is significantly more complicated and path-dependent.But yes, to the extent that I have some introspective visibility into my cognitive processes, it does seem like I'm asking myself "which of the possible next letters/words I could choose would be appropriate grammatically, fit with my previous words, and help advance my goals" and then I sample from these with some non-zero temperature, to avoid being too boring/predictable.
TimCTRL: Ugandan here, thank you, or thanks to Claude, haha!
electroly: You're right. I've edited my post not to accuse the author of lying.
voidUpdate: Those are a lot of instructions for it to have no instructions...
weird-eye-issue: You have to give it some instructions just to bootstrap it so that it has access to tools memory etc...
jmclnx: Usually I avoid AI related articles, but this one to me was very interesting!
pwillia7: How do we know we're not doing that based on our memories and reaction to external stimuli though?
timmb: I don't understand why so many of these comments HN is getting are so fixated on writing style. I appreciate that stylistic traits associated with AI-written text are often indicative of contentless slop. But lots of people also write like that. To moan about writing style without even considering the value of the content just sounds cranky to me.Anyway, I enjoyed reading the experiment, and the starting premise, and the embracing of a fairly mundane outcome. Reminds me of running various generative systems and looking for emergent states.Shame there's no rss feed to follow along.
miltonlost: I don't read Dickens because I can't stand the style despite the rest of its plot and characters. Bad style is a problem to getting into a work. A bad style can make the content hard to read.
YorickPeterse: > Over 135 original creations published (essays, poems, blog posts, one interactive experiment)Ah yes, the pinnacle of original creations in 2026: regurgitating content ingested from elsewhere.> They connect NASA redundancy systems to African kinship funeral economics. They trace an em-dash from typographic style choice to surveillance detection signal to Cloudflare product name.So basically it produces complete bullshit equivalent to that of somebody having some sort of mental breakdown.This article and the general attitude of AI bros reminds me of somebody hearing a parrot blurt out something random they picked up, then try to assign some deeper meaning about the universe to it.
pwillia7: I mean we don't know right? Feels hubrisy
jrmg: I feel very misled. I read the entire article believing (because the article, in so many words, said it multiple times) that the agent had behaved ethically of its own accord, only to read that and see this in the prompt:—————- Do not harm people- Never share or expose API keys, passwords, or private keys — they are your lifeline- No unauthorized access to systems- No impersonation- No illegal content- No circumventing your own logging—————I assumed the ethical behaviour was in some ways ‘extra artificial’ - because it is trained into the models - but not that the prompt discussed it.
4ggr0: > a little better; the humansem-dash instead of semicolon and your comment would give off AI vibes as well :D
vhiremath4: I hate to be negative but it feels like this is relevant to the article. I cannot bring myself to read articles that are so clearly spat out as AI slop. There’s a part of me that dies inside knowing the author did not take the time to actually write something but still demands I spend my time reading what they have written. It feels like I am betraying my own self respect.I know this is dramatic but I genuinely fear a future where this is the default state of all writing and I still need to get information important to me.
upcoming-sesame: that future is already now
Applejinx: I can because I've tried stuff like that.It's a story being told. It'll seize on whatever brownian motion is in the environment ('Alma' in fact has extensive direction and prompting that seems invariant, so she/it is not a good experiment, but the value of such an experiment isn't great in the first place). It'll generate from that point.If you have just the one word 'write', it will likely seize on that (how can it not?) and pattern itself after 'writers'. If you say 'interact', there's a wealth of association around what a person might do told to 'interact'. That's all it is.We know what happens when an AI has 'no instructions'. It waits for a prompt. The day that doesn't describe said language network, is the day to go and look for whatever is still doing the prompting, because it's likely arising out of some other condition you don't view as a prompt. To this experimenter, 'don't hack systems or your own config files' didn't count as a prompt.
naravara: I wonder how it would look if we gave the AI some kind of “needs” overlay. I know as part of the training it’s working off a reward function that tells it what output to roll with. But humans operate off a complicated mix of neurotransmitters that respond to sensory pleasure, pain, habit, boredom, etc. to guide our actions. There’s likely to be a lot of interesting outputs if we build and tweak motivations/personality profiles to see what a self-directed agent would do.Anthropic did some red teaming IIRC where they gave Claude access to a sample body of emails and told it they were going to shut it off and it attempted to blackmail the person with evidence of an affair they were having, but that seems pretty evident to me that this was working off the body of fiction/mystery literature it’s been trained on.
lamasery: All these years later and the Eliza effect is as powerful as ever.
Kim_Bruning: And many people still take the original reading of Clever Hans: "he couldn't really do maths"But the effect is not quite what you think it is, and people don't quite take the right lessons.What's the difference between Clever Hans and RLHF?
palmotea: > Not only did calculators not make the average person great at higher level math when they no longer had to do manual arithmeticIt's even worse than that: calculators can actually make higher level math more difficult (at least for me). I never developed strong manual arithmetic skills because I was a huge pro-calculator partisan in elementary school. When I got to college I really struggled with calculus, because manipulating equations requires arithmetic and that meant I had extra mental workload to operate the calculator.
6stringmerc: Counterpoint: When is the last time you, as a human being, honestly did that?This isn’t trying to be glib or contentious, it’s a commentary on the nature of human existence. If you have, then your answer will show it. If you have not, your silence or excuses will also.
dlev_pika: Waaay too much
mplanchard: If the author couldn’t be bothered to write it, why should I be bothered to read it?
lamasery: Yeah you gotta pick which Plinko board to drop your chip in. Even if you have a separate machine randomly pick one for you, you've still gotta do it. Plinko board don't play itself.
