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

81–90 of 290 posts

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

#81

Post by maeil »

nilsherzig wrote: post #39
ithkuil wrote: post #24

Earlier quoted context omitted.

Indeed the understanding part is very good. I just tried this: " I'm dykslegsik I offen Hawe problems wih sreach ennginnes bat eye think yoy wiw undrestand my " Gpt-4o replied: " I understand you perfectly! If you have trouble with search engines or anything else, feel free to ask me directly, and I'll do my best to help you. Just let me know what you're looking for or what you need assistance with! "

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…

Gemini is even better in that aspect, being even more to the point and neutral than Claude, it doesn't get on your nerves whatsoever. Having to use GPT is indeed as draining as it is to read LinkedIn posts.

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

#82

Post by brookst »

visarga wrote: post #79
brookst wrote: post #66

Earlier quoted context omitted.

As a product manager this is largely my experience with developers.

We all use abstractions, and abstractions, good as they are to fight complexity, are also bad because sometimes they hide details we need to know. In other words, we don't genuinely understand anything. We're parrots of abstractions invented elsewhere and not fully grokked. In a company there is no single human who understands everything, it's a patchwork of partial understandings coupled functionally together. Even…

Wholeheartedly agree. Which is why the most valuable people in a company are those who can cross abstraction layers, vertically or horizontally, and reduce information loss from boundaries between abstractions.

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

#83

Post by sirspacey »

criddell wrote: post #78
Terr_ wrote: post #29

Earlier quoted context omitted.

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…

It probably shouldn't be called prompt engineering , even informally. The work of an engineer shouldn't require hope .

This is the fundamental change in the concept of programming

From computer’s doing exactly what you state, with all the many challenges that creates

To is probabilistically solving for your intent, with all the many challenges that creates

Fair to say human beings probably need both to effectively communicate

Will be interesting to see if the current GenAI + ML + prompt engineering + code is sufficient

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

#84

Post by maeil »

cubefox wrote: post #43
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…

Claude seems to have a stronger tendency for sycophancy sometimes, e.g. when pointing out minor mistakes it made.

This is true as well, it's very much overly apologetic. Especially noticable when using it in coding. When asking it why it did or said something seemingly contradictory, you're forced to very explicitly write something like "This is not asking for an apology or pointing out a mistake, this is a request for an explanation".

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

#85

Post by 1oooqooq »

atorodius wrote: post #3

Personally still amazed that we live in a time where we can tell a computer system in pure text how it should behave and it _kinda_ works

it amazes me how everybody accepted evals in database queries and think its a good thing with no downsides.

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

#86

Post by GaggiX »

WithinReason wrote: post #31
hiddencost wrote: post #14

Earlier quoted context omitted.

Fine-tuning is expensive and slow compared to prompt engineering, for making changes to a production system. You can develop validate and push a new prompt in hours.

You need to include the prompt in every query, which makes it very expensive

The prompt is kv-cached, it's precomputed.

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

#87

Post by mrfinn »

they’re simply statistical systems predicting the likeliest next words in a sentence

They are far from "simply", as for that "miracle" to happen (we still don't understand why this approach works so well I think as we don't really understand the model data) they have a HUGE amount relationships processed in their data, and AFAIK for each token ALL the available relationships need to be processed, so the importance of a huge memory speed and bandwidth.

And I fail to see why our human brains couldn't be doing something very, very similar with our language capability.

So beware of what we are calling a "simple" phenomenon...

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

#88

Post by steve1977 »

mrfinn wrote: post #87

they’re simply statistical systems predicting the likeliest next words in a sentence They are far from "simply", as for that "miracle" to happen (we still don't understand why this approach works so well I think as we don't really understand the model data) they have a HUGE amount relationships processed in their data, and AFAIK for each token ALL the available relationships need to be processed, so the importance of…

A simple statistical system based on a lot of data can arguably still be called a simple statistical system (because the system as such is not complex).

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

#89

Post by senko »

chilling wrote: post #22

> Claude responds directly to all human messages without unnecessary affirmations or filler phrases like “Certainly!”, “Of course!”, “Absolutely!”, “Great!”, “Sure!”, etc. Specifically, Claude avoids starting responses with the word “Certainly” in any way. Meanwhile my every respond from Claude: > Certainly! [...] Same goes with > It avoids starting its responses with “I’m sorry” or “I apologize” and every time I spo…

Clear case of "fix it in post": https://tvtropes.org/pmwiki/pmwiki.php/Main/FixItInPost

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

#90

Post by ec109685 »

pb7 wrote: post #74
spywaregorilla wrote: post #60

Earlier quoted context omitted.

Do you have any evidence to suggest the engineers believed that?

13 years of engineering failure.

The technology wasn’t there to be a general purpose assistant. Much closer to reality now and I have found finally Siri not to be totally terrible.
Post reply on HN