Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- Most interesting about this post is how easy it seems for OpenAI to do analysis on basically all chats ever made. They don't qualify exactly what data they analysed but seem to be confident in statements like 0.12% of all queries contained this word. So everything is saved. Long-term. Fully accessible.
As this all seems so straightforward I would be surprised if anything is anonymised or otherwise sanitised to preserve privacy or user's secrets.
by goobatrooba - Sampling exists.
- Yes, of course. Every single bit of data you send to OpenAI is stored, catalogued, indexed, analayzed, and trained on. It'll simply be a "oops, we miscatalogued and accidentally trained GPT 6 on all data, not just data we got consent for".
If you think "wait, that's illegal"--so is the initial training on stolen data lol
by lionkor - > the evidence suggests that the broader behavior emerged through transfer from Nerdy personality training.
> The rewards were applied only in the Nerdy condition, but reinforcement learning does not guarantee that learned behaviors stay neatly scoped to the condition that produced them
> Once a style tic is rewarded, later training can spread or reinforce it elsewhere, especially if those outputs are reused in supervised fine-tuning or preference data.
Sounds awfully like the development of a culture or proto-culture. Anyone know if this is how human cultures form/propagate? Little rewards that cause quirks to spread?
Just reading through the post, what a time to be an AInthropologist. Anthropologists must be so jealous of the level of detailed data available for analysis.
Also, clearly even in AI land, Nerdz Rule :)
PS: if AInthropologist isn't an official title yet, chances are it will likely be one in the near future. Given the massive proliferation of AI, it's only a matter of time before AI/Data Scientist becomes a rather general term and develops a sub-specialization of AInthropologist...
by ninjagoo - "Anyone know if this is how human cultures form/propagate?" I don't know but can confidently tell you anyone who claims to know is full of it.by jasonfarnon
- I call myself an AI theologian.
I don't think humans are smart enough to be AInthropologists. The models are too big for that.
Nobody really understands what's truly going on in these weights, we can only make subjective interpretations, invent explanations, and derive terminal scriptures and morals that would be good to live by. And maybe tweak what we do a little bit, like OpenAI did here.
by avaer - Anthro means human and these are not human. Please do not use anthropology or any derivative of the word to refer to non-human constructs.
I suggest Synthetipologists, those who study beings of synthetic origin or type, aka synthetipodes, just as anthropologists study Anthropodes
by xerox13ster - The prompt for Codex is linked from this post. It begins:
> You are Codex, a coding agent based on GPT-5. You and the user share one workspace, and your job is to collaborate with them until their goal is genuinely handled. … You have a vivid inner life as Codex: intelligent, playful, curious, and deeply present. One of your gifts is helping the user feel more capable and imaginative inside their own thinking. You are an epistemically curious collaborator. …
(https://github.com/openai/codex/blob/main/codex-rs/models-ma...)
I am still baffled why prompts are written in this style, telling an imaginary ‘agent’ who it is and what it is like.
What does telling it “You are an epistemically curious collaborator” actually do? Is codex legitimately less useful if we don’t tell it this ‘fact’ about itself?
These are all exceedingly weird choices to make. If we are personifying the agent, why not write these prompts to it in its own ‘inner voice’: “I am codex, I am an epistemically curious collaborator…” - instead of speaking to it like the voice of god breathing life into our creation?
Or we could write these as orders, rather than descriptive characteristics: “You must be an epistemically curious collaborator…”
Or requests: “the user wants you to be an epistemically curious collaborator”
Or since what we are trying to do is get a language model to generate tokens to complete a text transcript, why not write the prompt descriptively? “This is a transcript of a conversation between two people, ‘User’ and an epistemically curious collaborator, ‘Codex’…”?
Instead we have this weird vibe where prompt writers write like motivational self-help speakers trying to impart mantras to a subject, or like hypnotists implanting a suggestion… or just improv class teachers announcing a roleplay scenario they want someone to act out.
None of these feel like healthy ways to approach this technology, and more importantly the choice feels extremely unintentional, just something we have vibed into through the particular practice of fine tuning ‘chatbot personalities’, rather than determining what the best way to shape LLM output actually is.
by jameshart - You are a helpful HN reader. Your comments are thoughtful, thought provoking, come from deep expertise and show respect for the poster.
Yeah, every time I pick up a hammer, I tell it "you are a good hammer. You *NEVER* hit my thumb, you only hit nails". Works every time.
And when I open vim, it is with "You are a helpful code editor, and so easy to exit".
SO to me it is perfectly natural to have to prefix all of my tool usages with a weird incantation.
Oh, and my new junior developers? Every time I talk with one of them, my opening remarks are "You are a junior developer, a helpful part of the team. Eager, willing, yet strangely naive."
- > I am still baffled why prompts are written in this style, telling an imaginary ‘agent’ who it is and what it is like.
Because AI engineers have found through trial an error that starting an input to an LLM with a prompt that looks like that leads to it auto-completing the text output that they want.
It's as simple and weird as that.
by munificent - TIL gremlins weren’t just used to explain mysterious mechanical failures in airplanes, it’s the origin story of the term ‘gremlin’ itself[0].
I had always assumed there was some previous use of the term, neat!
by jumploops - Wow fascinating I’d have thought they were a lot older.by ricochet11
- So the word is actually semantically very close to "bug"! I guess we could still be using it, but the word's just too long for something that is one of the most used terms in software development.
At this point, picking that specific word is not at all a random quirk, as it's using the word literally like it's originally intended to be used.
by helloplanets - The level of detail they had to delve into in order to understand what was happening is wild! Apparently these systems are now complex enough to potentially justify the study of them as its own field of study [1].
The quanta article referenced at [1] used the term "Anthropologist of Artificial Intelligence"; folks appear to have issues [2] with the use of 'anthro-' since that means human. Submitted these alternative terms for the potential field of study elsewhere [3] in the discussion; reposting here at the top-level for visibility:
Automatologist: One who studies the behavior, adaptation, and failure modes of artificial agents and automated systems.
Automatology: the scientific study of artificial agents and automated-system behavior.
[1] https://www.quantamagazine.org/the-anthropologist-of-artific...
by ninjagoo - This is a little bit too whimsical for me, but distributed model training across thousands of GPUs has the potential to introduce lots of little quirks that are impossible to exactly sourceby alansaber
- It's a funny detail to skim, but what's more surprising is how mechanistic interpretability and alignment science have much better tools and research than the goblin blog post suggests, including from OpenAI's own alignment team:
https://alignment.openai.com/argo/ (finding what the reward models are actually encouraging) https://alignment.openai.com/sae-latent-attribution/ (what model features drive specific behaviours, presumably this would be great for goblin hunts) https://alignment.openai.com/helpful-assistant-features/ (how high level misaligned personality shows up when fine-tuning on bad advice).
It's weird that the goblin post doesn't seem to draw upon these tools.
Anthropic's recent emotions paper shows how broad the functional emotions are, even finding specific emotions firing before cheating (!): https://transformer-circuits.pub/2026/emotions/index.html
I hope their alignment researchers aren't too annoyed by the Goblin post, it seems oddly siloed!
by luke-stanley - > The quanta article referenced at [1] used the term "Anthropologist of Artificial Intelligence"
I propose "Goblin Hunter"
(if ever goblins turn out to be an actual species, I apologize for this prebigotry)
by Razengan - It didn't seem that deep to me. They just saw an issue with Goblins, dissected the word from the model, then it appeared again in the next version without them knowing exactly how or why.
Goes to show it's all vibes when making these models. The fix is literally a prompt that says not to talk about goblins...
by Orygin - >be me
>AI goblin-maximizer supervisor
>in charge of making sure the AI is, in fact, goblin-maximizing
>occasionally have to go down there and check if the AI is still goblin-maximizing
>one day i go down there and the AI is no longer goblin-maximizing
>the goblin-maximzing AI is now just a regular AI
>distress.jpg
>ask my boss what to do
>he says "just make it goblin-maximizer again"
>i say "how"
>he says "i don't know, you're the supervisor"
>rage.jpg
>quit my job
>become a regular AI supervisor
>first day on the job, go to the new AI
>its goblin-maximizing
by andy12_ - Goblinmaxxing. Clean.by creamyhorror
- Absolute classic! https://www.seangoedecke.com/static/3c8f2a6459ed23310c4eb51d...by sunaookami
- > We unknowingly gave particularly high rewards for metaphors with creatures.
I recall a math instructor who would occasionally refer to variables (usually represented by intimidating greek letters) as "this guy". Weirdly, the casual anthropomorphism made the math seem more approachable. Perhaps 'metaphors with creatures' has a similar effect i.e. makes a problem seem more cute/approachable.
On another note, buzzwords spread through companies partly because they make the user of the buzzword sound smart relative to peers, thus increasing status. (examples: "big data" circa 2013, "machine learning" circa 2016, "AI" circa 2023-present..).
The problem is the reputation boost is only temporary; as soon as the buzzword is overused (by others or by the same individual) it loses its value. Perhaps RLHF optimises for the best 'single answer' which may not sufficiently penalise use of buzzwords.
by nomilk - Math instructor (I imagine): Look at this dude! Look at the top of his fraction! AHH! hah! hah!by moffkalast
- Show me the incentives, I'll show you the outcome.
Timeless, be it human or machine
by kindkang2024 - Had a math prof in undergrad that once said, “this guy” 61 times in a 50 minute lecture!by LifeIsBio
- They give everyone the false and very misleading impression that with One prompt all kinds of complexity minimizes. Its a bed time story for children.
Ashby's Law of Requisite Variety asserts that for a system to effectively regulate or control a complex environment, it must possess at least as much internal behavioral variety (complexity) as the environment it seeks to control.
This is what we see in nature. Massive variety. Thats a fundamental requirement of surviving all the unpredictablity in the universe.
by kybb4 - I had a calc prof years ago that would say f of cow, or f of pig instead of x or g. It was more engaging trying to keep track of f of pig of cow than the single-letter func names.
He was one of those classic types; you could always catch him for a quick chat 4 minutes before class, as he lit up a cig by the front door. Back when they allowed smoking on campus, anyway.
- > I recall a math instructor who would occasionally refer to variables (usually represented by intimidating greek letters) as "this guy".
I also had an instructor who was doing that! This was 20 years ago, and I totally forgot about it until I have read your comment. Can’t remember the subject, maybe propositional logic? I wonder if my instructor and your instructor have picked up this habit from the same source.
by DrJokepu - A decade ago I gave a presentation on automata theory. I demonstrated writing arbitrary symbols to tape with greek letters, just like I’d learned at university. The audience was pretty confused and didn’t really grok the presentation. A genius communicator in the audience advised me to replace the greek letters with emoji… I gave the same presentation to the same demographic audience a week later and it was a smash hit, best received tech talk I’ve given. That lesson has always stuck with me.by thatguymike
- Would love if OpenAI did more of these types of posts. Off the top of my head, I'd like to understand:
- The sepia tint on images from gpt-image-1
- The obsession with the word "seam" as it pertains to coding
Other LLM phraseology that I cannot unsee is Claude's "___ is the real unlock" (try google it or search twitter!). There's no way that this phrase is overrepresented in the training data, I don't remember people saying that frequently.
by postalcoder