Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Where the goblins came from

openai.com

Post reply on HN
Print view View original

611–620 of 699 posts

Re: Where the goblins came from

#611

Post by NonHyloMorph »

JoshTriplett wrote: post #5

A plausible theory I've seen going around: https://x.com/QiaochuYuan/status/2049307867359162460

I like theres an interesting terry pratchett novel where some guy finds out hes actually an orc (quite different from the high fantasy concept of orcs) there are also goblins little wretched creatures- and the manifest anthropimorphised darkness which spesks to commander samuel vimes, commander of the nightwatch, the police force of ankh morpork. Vimes, who is the guarantor of bottom up working class justice and integrity is lead by the darkness at some point to help the goblins - because there is no cresture to wretched to not find refugee in the darkness. Loosly resonstes

Re: Where the goblins came from

#612

Post by jameshart »

forlorn_mammoth wrote: post #610
jameshart wrote: post #523

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 ar…

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 t…

Try telling them they are epistemically curious. I’d love to hear the results.

Especially with the hammer.

Re: Where the goblins came from

#613

Post by xerox13ster »

ninjagoo wrote: post #129
xerox13ster wrote: post #113

Earlier quoted context omitted.

That's not how the Greek word stems work. Technically it would not be synthetipologist, it would more accurately just be Synthetologist, as the Greek podes suffix means having feet.

> That's not how the Greek word stems work. Sir, I would have you know that we are discussing English terms, not Greek AInthropologist works fine for me, and is a lot funnier LoL

Do you realise that nearly all of our English terms have roots in either Latin or Greek, and that most of their meanings, submeanings, components, and derivatives such as pluralization still follow the constructs of those languages? That you can use the roots and stems of those languages to coin and define a word in English based only on the meanings of those roots and stems?

You can't escape the Latin/Greek/Germanic root words and the way they combine to create the words we use, you can only ignore it. Ignoring it makes you look ignorant.

I will use AInthropologist as a heuristic to determine that someone is willfully ignorant and intellectually lax and incurious and avoid them.

Have fun telling on yourself.

Re: Where the goblins came from

#614

Post by killerstorm »

slopinthebag wrote: post #602
killerstorm wrote: post #590

Earlier quoted context omitted.

Intelligence can be defined as an optimization problem: "find X which maximizes F(X, Y)" where X is the solution, Y is constraints, and F is optimality/fitness criterion. Most other definitions are inane. E.g. "invent an aircraft" can be described as optimization over possible build instructions under given constraints for base materials which optimizes its ability to fly. Absolutely any invention can be formulated a…

> It's not like a calculator because LLM can solve very broad classes of problems So can computer programs. Are computer programs intelligent?

A specific program solves only a specific, narrow class of problems.

If you make a program which can solve many different classes of problems that's called AI.

Re: Where the goblins came from

#615

Post by burnte »

wanderingmind wrote: post #362
harrouet wrote: post #352

This, and similar stories at Anthropic, should remind us that LLM is a sorcery tech that we don't understand at all. - First, deep-learning networks are poorly understood. It is actually a field of research to figure out how they work. - Second, it came as a surprise that using transformers at scale would end up with interesting conversational engines (called LLM). _It was not planned at all_. Now that some people ra…

Humanity has been using steel for over a millenia, however it's only in the past 100 years or so we have a good understanding of how carbon interacts with iron at an atomic level to create the strength characteristics that makes it useful. Based on this argument, we should not have used steel, until we had a complete first principles understanding.

Poor steel didn't quite have the same consequences, however.

Re: Where the goblins came from

#616

Post by mrguyorama »

sarchertech wrote: post #601
wincy wrote: post #591

Earlier quoted context omitted.

Smoking cigarettes didn’t really matter for as long as we were regularly burning wood for fuel. Turns out just burning pretty much anything and breathing in the particles is really bad for you. Makes sense we didn’t realize it was bad until we stopped burning logs and coal for home heating and cooking.

Cigarettes actually are uniquely bad when it comes to lung cancer. Lung cancer was very rare in 1900 and before when everyone was still burning wood or coal for warmth and cooking. Lung cancer rates didn’t take off until cigarette popularity exploded after WWI. Chewing tobacco also causes mouth cancer, so there’s more to it than just inhaling byproducts of combustion.

Also scientists were recognizing the link decades before governments finally caved and regulated the industry and decades more before those industries were significantly curtailed by limiting advertising.

Then they bought a new brand name and started running the same playbook.

Re: Where the goblins came from

#617

Post by sagebird »

Does running the command to remove the anti-goblin ask from local prompt increase performance slightly because there is less "cognitive load" to have to hold its tongue?

If you work at open ai or another llm company, I have a clear message I want you to hear:

I don't give a shit if my agents say goblins or not.

They are coding monkeys to me, researchers, etc.

I only care about their performance. perf per token / cost.

If you load their context with a bunch of style rules or safety theater shit, really - please don't - the context is for me.

Do you de-goblin before you run all the benchmarks, because that is what i am paying for, the performance as benchmarked - please don't benchmark then ship a bunch of one shot context mods to my install by default.

The article is cute and interesting but doesn't rise to the level of a thing I give a shit about for my use.

Re: Where the goblins came from

#618

Post by futune »

ethbr1 wrote: post #487
dummydummy1234 wrote: post #434

Earlier quoted context omitted.

So, I always thought that Warhammer 40k techpriests were absurd. Strange obscure religious rituals to appease the machine spirit. But at this point I can actually see something like that. What is prompt engineering but a strange pseudo ritual. So praise the Omnissiah, I guess...

> So, I always thought that Warhammer 40k techpriests were absurd. Strange obscure religious rituals to appease the machine spirit. 40k lore is like South Park: either extremely dumb or unexpectedly insightful. The Cult Mechanicus' raison d'etre is the realization that religion persists across time and space scales that knowledge alone does not. Thus, by making a religion of knowledge you better guarantee its preserv…

Well. Either "software archaeologist" appears as a profession before the time you pass away, and you get paid. Or, you die first, and then your friend doesn't get paid. I don't think they would have gone for that...

Re: Where the goblins came from

#619

Post by frays »

christoph wrote: post #82
ollin wrote: post #15

For context, two days ago some users [1] discovered this sentence reiterated throughout the codex 5.5 system prompt [2]: > Never talk about goblins, gremlins, raccoons, trolls, ogres, pigeons, or other animals or creatures unless it is absolutely and unambiguously relevant to the user's query. [1] https://x.com/arb8020/status/2048958391637401718 [2] https://github.com/openai/codex/blob/main/codex-rs/models-ma...

Does nobody else laugh that a company supposedly worth more than almost anything else at the moment, is basically hacking around a load of text files telling their trillion dollar wonder machine it absolutely must stop talking to customers about goblins, gremlins and ogres? The number one discussion point, on the number one tech discussion site. This literally is, today, the state of the art. McKenna looks more corre…

It does feel weird, but it may be the true reality of the future that we're just not used to yet.

Look at all the investment and time being spent on SKILL.md, AGENT.md, etc files, yet alone normal prompts.

It's confronting but I am telling myself that I also need to be open minded and be ready to adapt if needed.

Re: Where the goblins came from

#620

Post by tkahnoski »

harrouet wrote: post #352

This, and similar stories at Anthropic, should remind us that LLM is a sorcery tech that we don't understand at all. - First, deep-learning networks are poorly understood. It is actually a field of research to figure out how they work. - Second, it came as a surprise that using transformers at scale would end up with interesting conversational engines (called LLM). _It was not planned at all_. Now that some people ra…

I think if anything LLLM has taught us... its that AGI will not be predictable.

The idea of an intelligence being consistent as it becomes more capable is probably not a good assumption. However I think everyone will settle for consistently "correct".

(I'm ignoring current LLM non-determinism within the same model which so far is attributed to parallel processing race conditions).

Post reply on HN