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

Some things just take time

lucumr.pocoo.org

Post reply on HN
Print view View original

141–150 of 295 posts

Re: Some things just take time

#141

Post by 3121aksj8p »

jstummbillig wrote: post #139
Chris_Newton wrote: post #60

With all the emphasis on the speed of modern AI tools, we often seem to forget that velocity is a vector quantity. Increased speed only gets us where we want to be sooner if we are also heading in the right direction. If we’re far enough off course, increasing speed becomes counterproductive and it ends up taking longer to get where we want to be. I’ve been noticing that this simple reality explains almost all of bot…

Ah, metaphors. Abstract concepts are not moving objects. You don't actually need to "turn it around" or "sail past it". You can break the laws of physics (because they don't apply). You can teleport around. Speed actually just wins, because we are usually constrained by time.

Yes, AI can emit BS at a faster rate than ever. We can also produce more blog posts than ever.

Working or useful software? AI hasn't produced any at all since 2023.

Re: Some things just take time

#142

Post by jstummbillig »

3121aksj8p wrote: post #141
jstummbillig wrote: post #139

Earlier quoted context omitted.

Ah, metaphors. Abstract concepts are not moving objects. You don't actually need to "turn it around" or "sail past it". You can break the laws of physics (because they don't apply). You can teleport around. Speed actually just wins, because we are usually constrained by time.

Yes, AI can emit BS at a faster rate than ever. We can also produce more blog posts than ever. Working or useful software? AI hasn't produced any at all since 2023.

Wow, an account, just for that? I feel honored and slightly suspicious.

Re: Some things just take time

#143

Post by FrankRay78 »

tombert wrote: post #91
skydhash wrote: post #86

Earlier quoted context omitted.

> It moves fast but without knowing which direction to move in. It also moves fast with a tendency to pick the wrong direction (according to the goal of the prompter) at every decision point (known or unknown).

I've definitely gotten it into contexts where it will never stop going into the wrong direction, even when I tell it to forget everything it did before, and told it a correct path forward. Usually restarting the entire session fixes it, but not always.

Shrewd context management is the go here.

Re: Some things just take time

#144

Post by FrankRay78 »

ChrisMarshallNY wrote: post #136

I find myself sympathetic to the author's PoV, but I am incorporating LLMs into my workflow, with a resultant jaw-dropping (to me) increase in velocity. But I am not just dispatching to agents. I work interactively with a chat interface, and sometimes, I will just bin a whole hour's worth of back-and-forth, because we're not getting anywhere (in fact, I did exactly that, about 30 minutes ago). But that hour is peanut…

A perfectly good methodology with the right guardrails in place imho.

Re: Some things just take time

#146

Post by nchmy »

I've been slowly working on something for a decade, and I'm always comforted by this poem by Mary Oliver

Things take the time they take.

Don't worry.

How many roads did St. Augustine follow

before he became St. Augustine?

Re: Some things just take time

#147

Post by triwats »

Sometimes to move fast - we have to go slow.

That's a mantra I learned when getting into technology.

Asking questions about how things work, why it is a certain way, or why a shortcut was made often give you far better insights than anything else.

Slowing down and understandng is great. With AI this is even easier. But choose wisely, brains get full.

Re: Some things just take time

#148

Post by iafiaf »

loandbehold wrote: post #115
keiferski wrote: post #106

One of my favorite ideas from Nietzsche [1] is that civilizations take millennia to “digest” or integrate concepts. It seems a little obvious, maybe, until you look at the modern world and realize the baseline assumption is something like, “every problem is just a question of resources.” An example being the common attitude that [advanced tech] is just a math problem to be solved, and not a process that needs to play…

Knowledge is a distilled experience.

shouldnt it be the other way around?

Re: Some things just take time

#149

Post by smj-edison »

timacles wrote: post #129
ErroneousBosh wrote: post #89

Earlier quoted context omitted.

Well following advice from folk on here earlier, I thought I'd start small and try to get it to write some code in Go that would listen on a network socket, wait for a packet with a bunch of messages (in a known format) come in, and split those messages out from the packet. I ended up having to type hundreds of lines of description to get thousands of lines of code that doesn't actually work, when the one I wrote mys…

Hate to pull the skill issue card here, but that is a trivial problem that can be one shotted with almost any model with

tbh that's not a helpful thing to say. I think a more productive thing would be to ask "What model are you using?" "Are you using it in chat mode or as a dedicated agent?" "Do you have an AGENTS.md or CLAUDE.md?"

I've also been underwhelmed with its ability to iterate, as it tends to pile on hacks. So another useful question is "did you try having it write again with what you/it learned?"

Re: Some things just take time

#150

Post by ErroneousBosh »

timacles wrote: post #129
ErroneousBosh wrote: post #89

Earlier quoted context omitted.

Well following advice from folk on here earlier, I thought I'd start small and try to get it to write some code in Go that would listen on a network socket, wait for a packet with a bunch of messages (in a known format) come in, and split those messages out from the packet. I ended up having to type hundreds of lines of description to get thousands of lines of code that doesn't actually work, when the one I wrote mys…

Hate to pull the skill issue card here, but that is a trivial problem that can be one shotted with almost any model with

Okay, tell you what then. Help me learn.

The problem is that I want something that listens on a TCP connection for GD92 packets, and when they arrive send appropriate handshaking to the other end and parse them into Go structs that can be stuffed into a channel to be dealt with elsewhere.

And, of course, something to encode them and send them again.

How would I do that with whatever AI you choose?

I'm pretty certain you can't solve this with AI because there is literally no published example of code to do it that it can copy from.

Post reply on HN