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

171–180 of 182 posts

Re: Claude Cookbook

#171

Post by mindwok »

bad_username wrote: post #68
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.

> I'm either going to ask the AI how to do it First you have to know that "it" exists and is possible. A cookbook like this introduces readers to concepts and features they didn't know were there in the first place.

That's a fair response. I could see how some folks would benefit. I suppose what bothers me more is that they don't actually seem pedagogical in nature, they seem promotional.

Re: Claude Cookbook

#172

Post by varjag »

tomrod wrote: post #47
varjag wrote: post #36

Earlier quoted context omitted.

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.

if everyone just…

Re: Claude Cookbook

#173

Post by pdimitar »

tedggh wrote: post #72
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.

There was an article by Vercel on how ineffective tool calling is compared to just a single md file with clearly defined instructions. They showed a clever way on how to use compressed indexes. My experience with tool calling was similar to what Vercel described, and I spent hours trying to perfect it. Since reading Vercel’s findings, Claude.md and Agents.md, maybe a Project.md it’s all I use.

Do you have a link?

Re: Claude Cookbook

#174

Post by game_the0ry »

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.

I appreciate the cookbooks bc sometimes I learn about ways to use ai that I did no know before.

Re: Claude Cookbook

#175

Post by mbarlow12 »

pdimitar wrote: post #173
tedggh wrote: post #72

Earlier quoted context omitted.

There was an article by Vercel on how ineffective tool calling is compared to just a single md file with clearly defined instructions. They showed a clever way on how to use compressed indexes. My experience with tool calling was similar to what Vercel described, and I spent hours trying to perfect it. Since reading Vercel’s findings, Claude.md and Agents.md, maybe a Project.md it’s all I use.

Do you have a link?

https://vercel.com/blog/agents-md-outperforms-skills-in-our-... perhaps?

Re: Claude Cookbook

#176

Post by NickNaraghi »

cloakandswagger wrote: post #24
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.

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.

I think one day it will relatively plateau and then these approaches will be meaningful improvements in performance. But yes, pointless for now.

Re: Claude Cookbook

#177

Post by killix »

nater5000 wrote: post #130
mexicocitinluez wrote: post #83

This is definitely controversial, but I think the best CLAUDE.MD is no CLAUDE.MD at all. Every time I found myself wanting to put information into that file, I asked myself "Why isn't this already obvious from the code itself?" I don't need to tell the agent my tech stack, what DB access library I'm using, the way in which I write my tests, etc. Why? Because it's all very clearly spelled out within the code itself. I…

I've found CLAUDE.md (etc.) make more sense when the agent is doing more generalized tasks rather than just coding. If you're just having an agent produce code, then I'd agree. I'd argue that any additional context it might need ought to be included in README.md anyways, just like a human. But I have projects where agents do more than just code, and retaining context about how I want the agents to operate, keeping tr…

[flagged]

Re: Claude Cookbook

#178

Post by onetrickwolf »

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.

Yeah 100% agree, I would even go as far as it's kind of harmful it seems to just pollute the context or stagnant as the models and tooling changes so rapidly or it is just better to do something bespoke for your own project.

Re: Claude Cookbook

#179

Post by DrJid »

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.

Maybe this “how to use ai” isn’t written for you, but for the agents who then have many ideas on what to do.

Re: Claude Cookbook

#180

Post by Timwi »

cubefox wrote: post #122
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.

> 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? Prompt engineering was a GPT-3 era term, which couldn't understand instructions. Then ChatGPT came out in late 2022, which made actual prompt engineering superfluous.

No, people tried to sell “prompt engineering” services well beyond that — especially for image generating AIs, which where believed to need extra instructions like “professional lighting”, a name of a camera model, lens parameters, etc.
Post reply on HN