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

Focus and Context and LLMs

taras.glek.net

Post reply on HN
Print view View original

31–40 of 51 posts

Re: Focus and Context and LLMs

#31

Post by lojack »

padolsey wrote: post #15
jumploops wrote: post #14

Has the author tried Claude Code? It’s the first useful “agent” (LLM in a loop + tools) that I’ve tried. IME it is hard to explain why it’s better than e.g. Aider or Cursor, but once you try it you’ll migrate your workflow pretty quickly.

How much transparency does Claude Code give you into what it's doing? I like IDE-integrated agents as they show diffs and allow focused prompting for specific areas of concern. And I get to control what's in context at any given time in a longer thread. I haven't tried Claude's thing in a while, but from what I gather it's more of a "prompt and pray" kind of agent.. ?

Definitely not a prompt and pray type thing, though you can do that if you choose. It shows its work, in the newest version there's three modes (planning, executing, auto accepting edits). You can also hit Esc at any time to redirect as you see it going in the wrong direction.

Re: Focus and Context and LLMs

#32

Post by ofjcihen »

tptacek wrote: post #30
ofjcihen wrote: post #23

Earlier quoted context omitted.

It’s almost like unrealistic expectations of LLMs driven by those working for companies who have something to gain by labeling any skepticism as “crazy” does significant damage to our perception of it’s usefulness. Believe it or not I agree.

I'm sorry, I read this comment like 3 times and I still don't understand what it's trying to say. Who are the companies you're talking about and are they too positive on LLMs or too negative?

Just that blind fanaticism leads to things like constant goal post moving when the product doesn’t live up to the hype. This damages people’s perception of the tool and causes them to be burnt out on it when it isn’t in fact magic.

Instead we should be accepting that people will or wont find uses for it depending on their competency (CRUD app churn VS somewhat novel creations) and accept that without telling them they’re nuts, luddites, etc.

Then again like I said the people doing that usually have something to gain such as a product related to the hype generating product.

Here’s an example article that hit the front page for HN this week https://fly.io/blog/youre-all-nuts/

Re: Focus and Context and LLMs

#33

Post by tptacek »

ofjcihen wrote: post #32
tptacek wrote: post #30

Earlier quoted context omitted.

I'm sorry, I read this comment like 3 times and I still don't understand what it's trying to say. Who are the companies you're talking about and are they too positive on LLMs or too negative?

Just that blind fanaticism leads to things like constant goal post moving when the product doesn’t live up to the hype. This damages people’s perception of the tool and causes them to be burnt out on it when it isn’t in fact magic. Instead we should be accepting that people will or wont find uses for it depending on their competency (CRUD app churn VS somewhat novel creations) and accept that without telling them the…

I wrote that article, and I don't believe "any" skepticism of "AI" is nuts. As an existence proof: I think "vibe coding" produces results as bad as skeptics say it does. The article is pretty specific about what it says the nutty claims are.

Re: Focus and Context and LLMs

#34

Post by ofjcihen »

tptacek wrote: post #33
ofjcihen wrote: post #32

Earlier quoted context omitted.

Just that blind fanaticism leads to things like constant goal post moving when the product doesn’t live up to the hype. This damages people’s perception of the tool and causes them to be burnt out on it when it isn’t in fact magic. Instead we should be accepting that people will or wont find uses for it depending on their competency (CRUD app churn VS somewhat novel creations) and accept that without telling them the…

I wrote that article, and I don't believe "any" skepticism of "AI" is nuts. As an existence proof: I think "vibe coding" produces results as bad as skeptics say it does. The article is pretty specific about what it says the nutty claims are.

Hah. Perfect. Then you’ll also agree with my statement about differing levels of acceptance I assume?

Re: Focus and Context and LLMs

#35

Post by tptacek »

ofjcihen wrote: post #34
tptacek wrote: post #33

Earlier quoted context omitted.

I wrote that article, and I don't believe "any" skepticism of "AI" is nuts. As an existence proof: I think "vibe coding" produces results as bad as skeptics say it does. The article is pretty specific about what it says the nutty claims are.

Hah. Perfect. Then you’ll also agree with my statement about differing levels of acceptance I assume?

Could you restate it? My whole point in this thread is that the article is knocking down an argument many supporters of "AI coding" aren't making. As I've just demonstrated, it's easy to find a skeptical argument that this "supporter" agrees with.

Re: Focus and Context and LLMs

#36

Post by ofjcihen »

tptacek wrote: post #35
ofjcihen wrote: post #34

Earlier quoted context omitted.

Hah. Perfect. Then you’ll also agree with my statement about differing levels of acceptance I assume?

Could you restate it? My whole point in this thread is that the article is knocking down an argument many supporters of "AI coding" aren't making. As I've just demonstrated, it's easy to find a skeptical argument that this "supporter" agrees with.

I mean I could but I think a better way to get to the heart of this discussion is to ask why you put quotations around supporter when describing the author.

Do you think he’s secretly against the tool itself or do you acknowledge that maybe the tool just doesn’t work for him and his use case and maybe he’s not nuts for finding fault with it?

Re: Focus and Context and LLMs

#37

Post by gsf_emergency »

tptacek wrote: post #33
ofjcihen wrote: post #32

Earlier quoted context omitted.

Just that blind fanaticism leads to things like constant goal post moving when the product doesn’t live up to the hype. This damages people’s perception of the tool and causes them to be burnt out on it when it isn’t in fact magic. Instead we should be accepting that people will or wont find uses for it depending on their competency (CRUD app churn VS somewhat novel creations) and accept that without telling them the…

I wrote that article, and I don't believe "any" skepticism of "AI" is nuts. As an existence proof: I think "vibe coding" produces results as bad as skeptics say it does. The article is pretty specific about what it says the nutty claims are.

Ahh I finally get it: you were claiming you only hang out with nuts (when it comes to AI)

--the link itself says "you", but that's also addressing your friends I presume?

Edit: the politicians too?

>To the consternation of many of my friends, I’m not a radical or a futurist.

(Apologies if you were tipsy at any point in the relevant parts)

Re: Focus and Context and LLMs

#38

Post by tptacek »

gsf_emergency wrote: post #37
tptacek wrote: post #33

Earlier quoted context omitted.

I wrote that article, and I don't believe "any" skepticism of "AI" is nuts. As an existence proof: I think "vibe coding" produces results as bad as skeptics say it does. The article is pretty specific about what it says the nutty claims are.

Ahh I finally get it: you were claiming you only hang out with nuts (when it comes to AI) --the link itself says "you", but that's also addressing your friends I presume? Edit: the politicians too? > To the consternation of many of my friends, I’m not a radical or a futurist. (Apologies if you were tipsy at any point in the relevant parts)

I'm sorry, I really can't follow any of this. No two lines of this seem to go together. "The politicians"?

Re: Focus and Context and LLMs

#39

Post by tptacek »

ofjcihen wrote: post #36
tptacek wrote: post #35

Earlier quoted context omitted.

Could you restate it? My whole point in this thread is that the article is knocking down an argument many supporters of "AI coding" aren't making. As I've just demonstrated, it's easy to find a skeptical argument that this "supporter" agrees with.

I mean I could but I think a better way to get to the heart of this discussion is to ask why you put quotations around supporter when describing the author. Do you think he’s secretly against the tool itself or do you acknowledge that maybe the tool just doesn’t work for him and his use case and maybe he’s not nuts for finding fault with it?

I wasn't referring in any particular way to the author, just acknowledging that there are multiple kinds of supporter.

Re: Focus and Context and LLMs

#40

Post by gsf_emergency_2 »

tptacek wrote: post #38
gsf_emergency wrote: post #37

Earlier quoted context omitted.

Ahh I finally get it: you were claiming you only hang out with nuts (when it comes to AI) --the link itself says "you", but that's also addressing your friends I presume? Edit: the politicians too? > To the consternation of many of my friends, I’m not a radical or a futurist. (Apologies if you were tipsy at any point in the relevant parts)

I'm sorry, I really can't follow any of this. No two lines of this seem to go together. "The politicians"?

The many of your friends who are into radicalism or futurism

The link: fly.io/blog/YOUre-all-nuts/

(XD)

Post reply on HN