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

151–160 of 182 posts

Re: Claude Cookbook

#151

Post by NichoPaolucci »

Centigonal wrote: post #127
NichoPaolucci wrote: post #71

Earlier quoted context omitted.

I actually think that good prompting MOSTLY comes from good writing skills in general. Being able to more clearly state things to an agent, knowing what pieces of context are entirely unnecessary and which are important, having a larger vocabulary helps too. Of course, there are other areas that can improve model output (Direction rather than open-ended assistance requests, using keywords + plugins that help, the "yo…

Is Superpowers any good? My coworkers who've used it seem to think that its main purpose is to consume a lot of tokens.

Honestly, within the last few days I've gone back to a mostly vanilla installation of Claude with a handful of directives in AGENTS.md. Depending on what I'm working on, I don't feel I need the extra plugins or a context repository. (It DOES feel at times like it blows through tokens for no reason).

Been working on some things that require more targeted, smaller scale changes and the base models do perfectly fine when given good instructions.

Superpowers and Compound Engineering are the two that I hear about around our team, both seem "fine" if you're into the fully agentic engineering "big change" future technology stuff.

Re: Claude Cookbook

#152

Post by rafram »

apsurd wrote: post #140
rafram wrote: post #137

Earlier quoted context omitted.

You should read their frontend design skill [1], which lots of guides recommend blindly, in classic LLM cargo-cult fashion. It doesn't say what people think it does. [1]: https://github.com/anthropics/claude-code/blob/main/plugins/...

it’s crazy to see right there in writing the prompt go out of its way to avoid the bootstrap effect with homogeneous templated results and then proceeds to produce fully homogeneous obviously templated AI results.

Well, relatively little of the prompt actually addresses visual design, and the parts that do seem to evoke Claude's worst impulses toward cliches rather than discouraging them. It is pretty crazy.

Re: Claude Cookbook

#153

Post by kkukshtel »

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.

This is also where I'm at. "Just ask the model stuff" continues to be the best, most durable advice. Karpathy himself had something recently about this on Twitter.

Re: Claude Cookbook

#154

Post by simonw »

zahlman wrote: post #148
simonw wrote: post #17

Earlier quoted context omitted.

I've been cooking with the help of LLMs a few times a month for over a year now. It's worked out well 9/10 times. It turns out the "average" version of a recipe that's baked into the weights is usually a solid recipe, and they're really good at offering substitutions for things like "I don't have ingredient X" or "make it vegetarian". It's also fun promoting "make it tastier" once or twice after each recipe just to s…

Okay, but I think we all want to hear the story about the time it failed.

The other day I was making a white bean shakshuka, I'd soaked the beans over night, I told it they were soaked, Claude said I should cook them with onions and eggs... but forgot to tell me to cook the beans!

We resolved the issue and Claude chirpily commented "So breakfast just became brunch".

Re: Claude Cookbook

#155

Post by knollimar »

esperent wrote: post #145
fwip wrote: post #56

Earlier quoted context omitted.

Did you tell Claude "make an agent instructor skill, whatever you think is good, go for it," or did you use the knowledge you had gained about how AI works and how to write good instructions for it?

No, I typed this one by hand as if it was 2019. But I don't write all agent instructions by hand because I don't think that I have any particularly high skill at doing that. I review carefully to ensure that my exact requirements are being expressed, hence why I said it must present me with exact diffs to review. But when it comes up the exact structure and wording I suspect me and the agent are equally bad at it.

My assertion is that LLMs tend to add info that makes them hyperfixate on errors.

Re: Claude Cookbook

#156

Post by intuitionist »

not-kinsale-joe wrote: post #31
gherkinnn wrote: post #22

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

Yes, and a couple of them look better before, I would say only the Blog one is truly better.

The Blog after just looks like a Substack post.

Re: Claude Cookbook

#157

Post by user43928 »

zahlman wrote: post #146
user43928 wrote: post #75

Earlier quoted context omitted.

Why not open-ended assistance requests? I ask it all the time about whether X is feasible, how we can get started on Y, and to investigate issue Z. It is working great for me in a >100k LOC project. Perhaps this works less well with weaker models. I suspect the people who say Qwen 3.6 27B is working well, are using prompts like "modify the renderThreeVars() function in rendering.py".

The point is that you can properly describe what X, Y, and Z are . The irony to me is that a lot of what I'd tell people about this is exactly what I would have told them about writing Stack Overflow questions.

I hardly need to properly describe it.

For example, if I tell it that I want my app translated, it can plan for me what the recommended options are in my framework, what languages I should target for my app, and come up with a skill for a repeatable workflow.

Re: Claude Cookbook

#158

Post by Jubijub »

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.

+1, by the time everybody sworn about MCPs, skills became a more efficient alternative. People learned to aggressively context manage, then longer context windows and agentic made that a lot less important. If the technique is any good, it will be baked in the next version. My philosophy is to avoid plugins / MCPs unless strictly required, and to have thorough prompts. This way I’ve successfully avoided to be in the way of progress by forcing obsolete optimisations on my LLMs

Re: Claude Cookbook

#159

Post by retnull »

hiccuphippo wrote: post #82
mindwok wrote: post #25

Earlier quoted context omitted.

If the bar is knowing how to type a question into a box, I'm confident almost everyone is better off starting with that then reading a "cookbook" that starts with installing python packages.

I've see people write "broooo pleaseeee!" into the box. Something about the universe providing better fools.

On several occasions when Opus is trying to justify it’s solution is correct even after several rounds of steering, any ridiculous frustrated prompt seems to do the trick.

For example ”come on” and then the model will just do the reasonable thing instead of disobedience. I imagine that ” broooo pleaseeee!” would work just as well.

Though sometimes I just clear the context or fork from the past, but this might or might not give any better results.

At least cognitive load is higher for me especially with forking so I prefer not to do it

Re: Claude Cookbook

#160

Post by tshaddox »

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…

> Isn't it clear that some people are better at working with/prompting LLMs than other people?

Sure, but I think it's essentially just that people who are better at traditional non-agentic software engineering are better at agentic software engineering. The only exception would be individuals who avoid agentic coding due to skepticism, hostility, or lack of opportunity.

Post reply on HN