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

Claude Cookbook

platform.claude.com

Post reply on HN
Print view View original

41–50 of 182 posts

Re: Claude Cookbook

#41

Post by CuriouslyC »

mindwok wrote: post #8

Gotta be honest, almost every "how to use AI" resource seems pointless to me. I'm either going to ask the AI how to do it, or if it's about using the AI then we can just bake it into the harness or wait for Anthropic/OpenAI to do it for me because they're always trivial. All of these resources on agentic workflows, managing agent memory, harness engineering, etc. appear to just be theatre to me.

It was more important with earlier models, as they were less RL'd to golden paths, so the context could steer them more.

Now process engineering is more important than prompt engineering.

Re: Claude Cookbook

#42

Post by omega3 »

embedding-shape wrote: post #37
cloakandswagger wrote: post #24

Earlier quoted context omitted.

Remember in 2023 when people thought "prompt engineering" would be the new software engineering and invested tons of time into learning CoT, ReAct, thread-of-thoughts, etc? Those were mostly obviated by reasoning models and harness updates by 2024. It seems pointless to invest energy into the latest/greatest AI technique or framework when they're going to either be absorbed or replaced on a 3 month cycle.

Isn't it clear that some people are better at working with/prompting LLMs than other people? Or is the idea that what you write to them and how you use them doesn't matter, it's all up to the model/harness? To me this seems clear, so then clearly this is a skill, which typically is called "prompt engineering". Specifically CoT or the other things you mention wasn't referred to as "prompt engineering" as far as I know…

What's clear is that there is a lot of hype around LLM and people who were previously valued for their IC are now in the business of shilling.

Re: Claude Cookbook

#43

Post by CuriouslyC »

embedding-shape wrote: post #37
cloakandswagger wrote: post #24

Earlier quoted context omitted.

Remember in 2023 when people thought "prompt engineering" would be the new software engineering and invested tons of time into learning CoT, ReAct, thread-of-thoughts, etc? Those were mostly obviated by reasoning models and harness updates by 2024. It seems pointless to invest energy into the latest/greatest AI technique or framework when they're going to either be absorbed or replaced on a 3 month cycle.

Isn't it clear that some people are better at working with/prompting LLMs than other people? Or is the idea that what you write to them and how you use them doesn't matter, it's all up to the model/harness? To me this seems clear, so then clearly this is a skill, which typically is called "prompt engineering". Specifically CoT or the other things you mention wasn't referred to as "prompt engineering" as far as I know…

RL has basically killed prompt engineering. You still need to provide the right context and process, but how you communicate with them beyond that is no longer so important.

Re: Claude Cookbook

#44

Post by saberience »

embedding-shape wrote: post #37
cloakandswagger wrote: post #24

Earlier quoted context omitted.

Remember in 2023 when people thought "prompt engineering" would be the new software engineering and invested tons of time into learning CoT, ReAct, thread-of-thoughts, etc? Those were mostly obviated by reasoning models and harness updates by 2024. It seems pointless to invest energy into the latest/greatest AI technique or framework when they're going to either be absorbed or replaced on a 3 month cycle.

Isn't it clear that some people are better at working with/prompting LLMs than other people? Or is the idea that what you write to them and how you use them doesn't matter, it's all up to the model/harness? To me this seems clear, so then clearly this is a skill, which typically is called "prompt engineering". Specifically CoT or the other things you mention wasn't referred to as "prompt engineering" as far as I know…

It's not really a skill. The models are at this point smarter than you are, so the idea that you can prompt them "better" is laughable really when discussing frontier models.

It's like imagining you could "prompt" Richard Feynman to be smarter at Physics.

That is, for 99.9% of engineers, if you want the model to do a code review of your project, the best solution is to just ask Fable, "Hey Fable, do a code review of this project." Throwing in extra text like "think like a senior engineer", "ensure you focus on DRY principles, KISS, self documenting code, etc", doesn't make a difference.

These sorts of tricks used to work with dumber models, but now, like I said before, it's like thinking you can prompt Linus Torvalds into writing better C than he already can do.

Re: Claude Cookbook

#45

Post by Xalutiono »

mindwok wrote: post #8

Gotta be honest, almost every "how to use AI" resource seems pointless to me. I'm either going to ask the AI how to do it, or if it's about using the AI then we can just bake it into the harness or wait for Anthropic/OpenAI to do it for me because they're always trivial. All of these resources on agentic workflows, managing agent memory, harness engineering, etc. appear to just be theatre to me.

You don't learn about progress if you don't take part in it.

Before /goal was ralph-wiggum it was def an interesting learning experience, it was interesting to see how Claude became a lot better doing this itself but it still took 6 Month and more.

You can wait and sit it out and suddenly you get fired if you miss the point when to start spending more time and energy on topics like this.

Re: Claude Cookbook

#46

Post by murkt »

gherkinnn wrote: post #22

https://platform.claude.com/cookbook/coding-prompting-for-fr... Before: bland After: bland with gradients

Yeah, along with UPPERCASE labels, which is a staple of AI designed pages

Re: Claude Cookbook

#47

Post by tomrod »

varjag wrote: post #36
adhamsalama wrote: post #33

Earlier quoted context omitted.

Aren't closed models used to kill people by the US and Israel?

Will they stop killing if the open models will also start killing?

That sounds like a great idea. Let's stop killing people altogether. It's almost entirely unnecessary.

Re: Claude Cookbook

#48

Post by defrost »

saberience wrote: post #44
embedding-shape wrote: post #37

Earlier quoted context omitted.

Isn't it clear that some people are better at working with/prompting LLMs than other people? Or is the idea that what you write to them and how you use them doesn't matter, it's all up to the model/harness? To me this seems clear, so then clearly this is a skill, which typically is called "prompt engineering". Specifically CoT or the other things you mention wasn't referred to as "prompt engineering" as far as I know…

It's not really a skill. The models are at this point smarter than you are, so the idea that you can prompt them "better" is laughable really when discussing frontier models. It's like imagining you could "prompt" Richard Feynman to be smarter at Physics. That is, for 99.9% of engineers, if you want the model to do a code review of your project, the best solution is to just ask Fable, "Hey Fable, do a code review of…

FWiW

> it's like thinking you can prompt Linus Torvalds into writing better C++ than he already can do.

  Linus Torvalds, the inventor (and beloved dictator) of Linux, has always been quite harsh about C++ and why he rejects it for Linux kernel development. He’s not just been very vocal about it, but also brought up some arguments against the use of C++ that are worth reviewing in detail.
~ https://medium.com/@jankammerath/linus-torvalds-critique-of-...

Re: Claude Cookbook

#49

Post by throw1234567891 »

murkt wrote: post #46
gherkinnn wrote: post #22

https://platform.claude.com/cookbook/coding-prompting-for-fr... Before: bland After: bland with gradients

Yeah, along with UPPERCASE labels, which is a staple of AI designed pages

It should not be difficult to change the CSS. LLMs have learned from us.
Post reply on HN