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

I want to wash my car. The car wash is 50 meters away. Should I walk or drive?

mastodon.world

Post reply on HN
Print view View original

981–990 of 998 posts

Re: I want to wash my car. The car wash is 50 meters away. Should I walk or drive?

#981

Post by docjay »

lostphilosopher wrote: post #721
WarmWash wrote: post #580

Earlier quoted context omitted.

Prompting is definitely a skill, similar to "googling" in the mid 00's. You see people complaining about LLM ability, and then you see their prompt, and it's the 2006 equivalent of googling "I need to know where I can go for getting the fastest service for car washes in Toronto that does wheel washing too"

I’ve been looking for tooling that would evaluate my prompt and give feedback on how to improve. I can get somewhere with custom system prompts (“before responding ensure…”) but it seems like someone is probably already working on this? Ideally it would run outside the actual thread to keep context clean. There are some options popping up on Google but curious if anyone has a first anecdote to share?

It really depends on how deep you want to go.

1. Just jazz up and expand on a simple prompt.

2. A full context deficiency analysis and multiple question interview system to bounds check and restructure your prompt into your ‘goal’.

3. Realizing that what looks like a good human prompt is not the same as what functions as a good ‘next token’ prompt.

If you just want #1:

import dspy

class EnhancePrompt(dspy.Signature):

    """Assemble the final enhanced prompt from all gathered context"""

    essential_context: str = dspy.InputField(desc="All essential context and requirements")

    original_request: str = dspy.InputField(desc="The user's original request")

    enhanced: str = dspy.OutputField(desc="Complete, detailed, unambiguous prompt. Omit politeness markers. You must limit all numbered lists to a maximum of 3 items.")
def enhance_prompt(prompt: str, temperature: float = 0.2) -> str:

    with dspy.context(lm=dspy.LM("_MODEL_", temperature=temperature)): return dspy.ChainOfThought(EnhancePrompt)(essential_context=f"Direct enhancement request: {prompt}", original_request=prompt).enhanced
res = enhance_prompt("Read bigfile.py and explain the do_math() function.")

print(res)

Read the file `bigfile.py` and provide a detailed explanation of the `do_math()` function. Your explanation should cover:

1. The function's purpose and what it accomplishes

2. The input parameters it accepts and the output/return value it produces

3. The step-by-step logic and algorithm used within the function

Include relevant code snippets when explaining key parts of the implementation.

Re: I want to wash my car. The car wash is 50 meters away. Should I walk or drive?

#982

Post by grey-area »

hackinthebochs wrote: post #553
grey-area wrote: post #283

Earlier quoted context omitted.

It’s just not intelligent or reasoning, and this sort of question exposes that more clearly. Surely anyone who has used these tools is familiar with the sometimes insane things they try to do (deleting tests, incorrect code, changing the wrong files etc etc). They get amazingly far by predicting the most likely response and having a large corpus but it has become very clear that this approach has significant limitati…

Why should odd failure modes invalidate the claim of reasoning or intelligence in LLMs? Humans also have odd failure modes, in some ways very similar to LLMs. Normal functioning humans make assumptions, lose track of context, or just outright get things wrong. And then there people with rare neurological disorders like somatoparaphrenia, a disorder where people deny ownership of a limb and will confabulate wild expla…

Because it is not an ‘odd failure mode’, it is a consequence of how it generates text without understanding.

Re: I want to wash my car. The car wash is 50 meters away. Should I walk or drive?

#983

Post by hackinthebochs »

grey-area wrote: post #982
hackinthebochs wrote: post #553

Earlier quoted context omitted.

Why should odd failure modes invalidate the claim of reasoning or intelligence in LLMs? Humans also have odd failure modes, in some ways very similar to LLMs. Normal functioning humans make assumptions, lose track of context, or just outright get things wrong. And then there people with rare neurological disorders like somatoparaphrenia, a disorder where people deny ownership of a limb and will confabulate wild expla…

Because it is not an ‘odd failure mode’, it is a consequence of how it generates text without understanding.

This is called begging the question. I don't know why I keep expecting more from HN.

Re: I want to wash my car. The car wash is 50 meters away. Should I walk or drive?

#986

Post by 3abiton »

dirkc wrote: post #512
jstummbillig wrote: post #147

Earlier quoted context omitted.

> so you need to tell them the specifics That is the entire point, right? Us having to specify things that we would never specify when talking to a human. You would not start with "The car is functional. The tank is filled with gas. I have my keys." As soon as we are required to do that for the model to any extend that is a problem and not a detail (regardless that those of us, who are familiar with the matter, do bu…

> That is the entire point, right? Us having to specify things that we would never specify when talking to a human. Maybe in the distant future we'll realize that the most reliable way to prompting LLMs are by using a structured language that eliminates ambiguity, it will probably be rather unnatural and take some time to learn. But this will only happen after the last programmer has died and no-one will remember pro…

"Check your assumptions", will get a very long answer from a "thorough"LLM.

Re: I want to wash my car. The car wash is 50 meters away. Should I walk or drive?

#988

Post by bavell »

lostphilosopher wrote: post #721
WarmWash wrote: post #580

Earlier quoted context omitted.

Prompting is definitely a skill, similar to "googling" in the mid 00's. You see people complaining about LLM ability, and then you see their prompt, and it's the 2006 equivalent of googling "I need to know where I can go for getting the fastest service for car washes in Toronto that does wheel washing too"

I’ve been looking for tooling that would evaluate my prompt and give feedback on how to improve. I can get somewhere with custom system prompts (“before responding ensure…”) but it seems like someone is probably already working on this? Ideally it would run outside the actual thread to keep context clean. There are some options popping up on Google but curious if anyone has a first anecdote to share?

Anthropic has a prompt improver tool: https://platform.claude.com/docs/en/build-with-claude/prompt...

Re: I want to wash my car. The car wash is 50 meters away. Should I walk or drive?

#989

Post by hellotomyrars »

LordDragonfang wrote: post #969
hellotomyrars wrote: post #932

Earlier quoted context omitted.

AI isn’t “from a different culture”. It doesn’t have culture. Any culture it does have is what it has sucked up from its training data and set in its weights. There is no need to be “humane” to AI because it possess no humanity. It has no personhood at all. It can’t feel. You can’t be inhumane to something that is literally incapable of feeling. A blade of grass has more humanity and is more deserving of respect than…

> A blade of grass has more humanity and is more deserving of respect than anything being referred to as AI does. Emphatically disagree. Even ignoring the obvious absurdity in this statement by pointing out that an LLM is emulating a human (quite well!) and a blade of grass is not: I don't trust any human who can interact with something that uses the same method of communication as a human, and for all intents and pu…

I think ascribing humanity to to something that isn’t human is far more dehumanizing to actual real life humans than the alternative. You are taking away actual people’s humanity if you’re giving it to anything we call AI.

I am capable of distinguishing between talking to another person and talking to an LLM and I don’t think that is hard to do.

I don’t think there is any other word than delusional to describe someone who thinks LLMs should be treated as humans.

Re: I want to wash my car. The car wash is 50 meters away. Should I walk or drive?

#990

Post by arcfour »

neya wrote: post #924
arcfour wrote: post #201

Earlier quoted context omitted.

What does this nonsensical question that some LLMs get wrong some of the time, and that some don't get wrong ever, have to do with anything? This isn't a "gotcha" even though you want it to be. It's just mildly amusing.

Because, this fundamental premise demonstrates that LLMs can't really think logically like we do and they are far from replacing actual humans, let alone senior software engineers.

So if you took one of the greatest software engineers ever and made it so he was unable to answer this nonsensical and pointless question, he would be a lesser engineer because of it?
Post reply on HN