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

Anthropic publishes the 'system prompts' that make Claude tick

techcrunch.com

Post reply on HN
Print view View original

51–60 of 290 posts

Re: Anthropic publishes the 'system prompts' that make Claude tick

#51

Post by marcus0x62 »

blooalien wrote: post #49
lynx23 wrote: post #45

Earlier quoted context omitted.

I submit humans are no different. It can take years of seemingly good communication with a human til you finally realize they never really got your point of view. Language is ambigious and only a tool to communicate thoughts. The underlying essence, thought, is so much more complex that language is always just a rather weak approxmiation.

The difference is that large language models don't think at all. They just string language "tokens" together using fancy math and statistics and spew them out in response to the tokens they're given as "input". I realize that they're quite convincing about it, but they're still not doing at all what most people think they're doing.

How do people think?

Re: Anthropic publishes the 'system prompts' that make Claude tick

#52

Post by fenomas »

tomp wrote: post #10
fenomas wrote: post #7

Earlier quoted context omitted.

I've wondered about this - you'd naively think it would be easy to run the model through the system prompt, then snapshot its state as of that point, and then handle user prompts starting from the cached state. But when I've looked at implementations it seems that's not done. Can anyone eli5 why?

Tokens are mapped to keys, values and queries. Keys and values for past tokens are cached in modern systems, but the essence of the Transformer architecture is that each token can attend to every past token, so more tokens in a system prompt still consumes resources.

That makes sense, thanks!

Re: Anthropic publishes the 'system prompts' that make Claude tick

#53

Post by lynx23 »

blooalien wrote: post #49
lynx23 wrote: post #45

Earlier quoted context omitted.

I submit humans are no different. It can take years of seemingly good communication with a human til you finally realize they never really got your point of view. Language is ambigious and only a tool to communicate thoughts. The underlying essence, thought, is so much more complex that language is always just a rather weak approxmiation.

The difference is that large language models don't think at all. They just string language "tokens" together using fancy math and statistics and spew them out in response to the tokens they're given as "input". I realize that they're quite convincing about it, but they're still not doing at all what most people think they're doing.

I know a lot of people who, according to your definition, also actually dont think at all. They just string together words ...

Re: Anthropic publishes the 'system prompts' that make Claude tick

#54

Post by naveen99 »

tayo42 wrote: post #8
riku_iki wrote: post #5

its so long, so much waste of compute during inference. Wondering why they couldn't finetune it through some instructions.

has anything been done to like turn common phrases into a single token? like "can you please" maps to 3895 instead of something like "10 245 87 941" Or does it not matter since tokenization is already a kind of compression?

You can try cyp but ymmv

Re: Anthropic publishes the 'system prompts' that make Claude tick

#57

Post by dTal »

Terr_ wrote: post #27
cubefox wrote: post #15

Earlier quoted context omitted.

And "kinda" is an understatement. It understands you very well, perhaps even better than the average human would. (Average humans often don't understand jargon.)

> It understands you very well No, it creates output that intuitively feels like like it understands you very well, until you press it in ways that pop the illusion. To truly conclude it understands things, one needs to show some internal cause and effect, to disprove a Chinese Room scenario. https://en.wikipedia.org/wiki/Chinese_room

I think you have misunderstood Searle's Chinese Room argument. In Searle's formulation, the Room speaks Chinese perfectly, passes the Turing test, and can in no way be distinguished from a human who speaks Chinese - you cannot "pop the illusion". The only thing separating it from a literal "robot that speaks Chinese" is the insertion of an (irrelevant) human in the room, who does not speak Chinese and whose brain is not part of the symbol manipulation mechanisms. "Internal cause and effect" has nothing to do with it - rather, the argument speciously connects understanding on the part of the human with understanding on the part of the room (robot).

The Chinese Room thought experiment is not a distinct "scenario", simply an intuition pump of a common form among philosophical arguments which is "what if we made a functional analogue of a human brain that functions in a bizarre way, therefore ".

Re: Anthropic publishes the 'system prompts' that make Claude tick

#58

Post by ljlolel »

Terr_ wrote: post #29
zevv wrote: post #28

Earlier quoted context omitted.

It actually still scares the hell out of me that this is the way even the experts 'program' this technology, with all the ambiguities rising from the use of natural language.

LLM Prompt Engineering: Injecting your own arbitrary data into a what is ultimately an undifferentiated input stream of word-tokens from no particular source, hoping your sequence will be most influential in the dream-generator output, compared to a sequence placed there by another person, or a sequence that they indirectly caused the system to emit that then got injected back into itself. Then play whack-a-mole unti…

same as with asking humans to do something

Re: Anthropic publishes the 'system prompts' that make Claude tick

#59

Post by JumpCrisscross »

aden1ne wrote: post #42
nilsherzig wrote: post #39

Earlier quoted context omitted.

Sonnet 3.5 > I understand that you're telling me you're dyslexic and often have problems with search engines, but you think I will understand you. You're right - I can understand what you're trying to communicate despite the spelling differences. Is there something specific I can help you with today? I'm happy to assist in any way I can. Honestly it has a much nicer writing style than chatgpt. I really dislike openai…

This is one of the reasons why I'm paying for Claude and not for ChatGPT. ChatGPT really goes into uncanny valley for me.

> ChatGPT really goes into uncanny valley for me

Especially with the exclamation marks, it reads to me the way a stereotypical Silicon Valley bullshitter speaks.

Re: Anthropic publishes the 'system prompts' that make Claude tick

#60

Post by spywaregorilla »

spiderfarmer wrote: post #30
zevv wrote: post #28

Earlier quoted context omitted.

It actually still scares the hell out of me that this is the way even the experts 'program' this technology, with all the ambiguities rising from the use of natural language.

It still scares the hell out me that engineers think there’s a better alternative that covers all the use cases of a LLM. Look at how naive Siri’s engineers were, thinking they could scale that mess to a point where people all over the world would find it a helpful tool that improved the way they use a computer.

Do you have any evidence to suggest the engineers believed that?
Post reply on HN