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

Snorting the AGI with Claude Code

kadekillary.work

Post reply on HN
Print view View original

1–10 of 253 posts

Re: Snorting the AGI with Claude Code

#3

Post by SamPatt »

>Claude code feels more powerful than cursor, but why? One of the reasons seems it's ability to be scripted. At the end of the day, cursor is an editor, while claude code is a swiss army knife (on steroids).

Agreed, and I find that I use Claude Code on more than traditional code bases. I run it in my Obsidian vault for all kinds of things. I run it to build local custom keyboard bindings with scripts that publish screenshots to my CDN and give me a markdown link, or to build a program that talks to Ollama to summarize my terminal commands for the last day.

I remember the old days of needing to figure out if the formatting changes I wanted to make to a file were sufficient to build a script or just do them manually - now I just run Claude in the directory and have it done for me. It's useful for so many things.

Re: Snorting the AGI with Claude Code

#4

Post by TeMPOraL »

dwohnitmok wrote: post #2

On the one hand very cool. On the other hand, every time people are just spinning off sub-agents I am reminded of this: https://www.lesswrong.com/posts/kpPnReyBC54KESiSn/optimality... It's simultaneously the obvious next step and portends a potentially very dangerous future.

> It's simultaneously the obvious next step

As it has been over three years ago, when that was originally published.

I'm continuously surprised both by how fast the models themselves evolve, and how slow their use patterns are. We're still barely playing with the patterns that were obvious and thoroughly discussed back before GPT-4 was a thing.

Right now, the whole industry is obsessed with "agents", aka. giving LLMs function calls and limited control over the loop they're running under. How many years before the industry will get to the point of giving LLMs proper control over the top-level loop and managing the context, plus an ability to "shell out" to "subagents" as a matter of course?

Re: Snorting the AGI with Claude Code

#5

Post by jjice »

SamPatt wrote: post #3

>Claude code feels more powerful than cursor, but why? One of the reasons seems it's ability to be scripted. At the end of the day, cursor is an editor, while claude code is a swiss army knife (on steroids). Agreed, and I find that I use Claude Code on more than traditional code bases. I run it in my Obsidian vault for all kinds of things. I run it to build local custom keyboard bindings with scripts that publish scr…

I'm very interested to hear what your uses cases are when using it in your Obsidian Vault

Re: Snorting the AGI with Claude Code

#6

Post by tinyhouse »

This article is a bit all over the place. First, a slide deck to describe a codebase is not that useful. There's a reason why no one ever uses a slide deck for anything besides supporting an oral presentation.

Most of these things in the post aren't new capabilities. The automation of workflows is indeed valuable and cool. Not sure what AGI has anything to do with it.

Re: Snorting the AGI with Claude Code

#7

Post by qsort »

TeMPOraL wrote: post #4
dwohnitmok wrote: post #2

On the one hand very cool. On the other hand, every time people are just spinning off sub-agents I am reminded of this: https://www.lesswrong.com/posts/kpPnReyBC54KESiSn/optimality... It's simultaneously the obvious next step and portends a potentially very dangerous future.

> It's simultaneously the obvious next step As it has been over three years ago , when that was originally published. I'm continuously surprised both by how fast the models themselves evolve, and how slow their use patterns are . We're still barely playing with the patterns that were obvious and thoroughly discussed back before GPT-4 was a thing. Right now, the whole industry is obsessed with "agents", aka. giving LL…

> How many years before the industry will get to the point

When/if the underlying model gets good enough to support that pattern. As an extreme example, you aren't ever going to make even a basic agent with GPT-3 as the base model, the juice isn't worth the squeeze.

Models have gotten way better and I'm now convinced (new data -> new opinion) that they are a major win for coding, but they still need a lot, a lot of handholding, left to their own devices they just make a mess.

The underlying capabilities of the model are the entire ballgame, the "use patterns" aren't exactly rocket science.

Re: Snorting the AGI with Claude Code

#8

Post by benlivengood »

TeMPOraL wrote: post #4
dwohnitmok wrote: post #2

On the one hand very cool. On the other hand, every time people are just spinning off sub-agents I am reminded of this: https://www.lesswrong.com/posts/kpPnReyBC54KESiSn/optimality... It's simultaneously the obvious next step and portends a potentially very dangerous future.

> It's simultaneously the obvious next step As it has been over three years ago , when that was originally published. I'm continuously surprised both by how fast the models themselves evolve, and how slow their use patterns are . We're still barely playing with the patterns that were obvious and thoroughly discussed back before GPT-4 was a thing. Right now, the whole industry is obsessed with "agents", aka. giving LL…

We haven't hit the RSI threshold yet and so evolution is so slow that it's usually terminated as not-useful or it solves a concrete problem and is terminated by itself or a human. Earlier model+frameworks merely petered out almost immediately. I'm guessing it's roughly correlated with the progress on METR.

Re: Snorting the AGI with Claude Code

#9

Post by bravesoul2 »

tinyhouse wrote: post #6

This article is a bit all over the place. First, a slide deck to describe a codebase is not that useful. There's a reason why no one ever uses a slide deck for anything besides supporting an oral presentation. Most of these things in the post aren't new capabilities. The automation of workflows is indeed valuable and cool. Not sure what AGI has anything to do with it.

Also I don't trust it. They touched on that I think (I only skimmed).

Plus you shouldn't need an LLM to understand a codebase. Just make it more understandable! Of course capital likes shortcuts and hacks to get the next feature out in Q3.

Post reply on HN