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

Eight more months of agents

crawshaw.io

Post reply on HN
Print view View original

141–150 of 250 posts

Re: Eight more months of agents

#141

Post by moron4hire »

happytoexplain wrote: post #4

I don't trust the idea of "not getting", "not understanding", or "being out of touch" with anti-LLM (or pro-LLM) sentiment. There is nothing complicated about this divide. The pros and cons are both as plain as anything has ever been. You can disagree - even strongly - with either side. You can't "not understand".

Yeah, "not understanding" means they aren't engaging with the issue honestly. They go on to compare to carpentry, which is a classic sign the speaker understands neither carpentry or software development.

The anti-LLM arguments aren't just "hand tools are more pure." I would even say that isn't even a majority argument. There are plenty more arguments to make about environmental and economic sustainability, correctness, safety, intellectual property rights, and whether there are actual productivity gains distinguishable from placebo.

It's one of the reasons why "I am enjoying programming again" is such a frustrating genre of blog post right now. Like, I'm soooo glad we could fire up some old coal plants so you could have a little treat, Brian from Middle Management.

Re: Eight more months of agents

#143

Post by dude250711 »

xyzsparetimexyz wrote: post #106

> Pay through the nose for Opus or GPT-7.9-xhigh-with-cheese. Don't worry, it's only for a few years. > You have to turn off the sandbox, which means you have to provide your own sandbox. I have tried just about everything and I highly recommend: use a fresh VM. > I am extremely out of touch with anti-LLM arguments 'Just pay out the arse and run models without a sandbox or in some annoying VM just to see them fail. W…

Well, not 'against' per se, just watching LLM-enthusiasts tumble in the mud for now. Though I have heard that if I don't jump into the mud this instance, I will be left behind apparently for some reason. So you either get left behind or get a muddy behind, your choice.

Re: Eight more months of agents

#144

Post by MrSandingMan »

> In 2000, less than one percent lived on farms and 1% of workers are in agriculture. That was a net benefit to the world, that we all don't have to work to eat.

Not obvious

> To me that statement is as obvious as "water is wet".

Well... is water *wet* or does it *wet things*? So not obvious either.

I'm really dubious when reading posts posing some things as obvious or trivial. In general they are not.

Re: Eight more months of agents

#145

Post by dude250711 »

gip wrote: post #80

> In 2026, I don't use an IDE any more. I don't think it is the best way to look at it. I think that now every team has the power to build and maintain an internal agent (tool + UX) to manager software products. I don't necessarily think that chat-only is enough except for small projects, so teams will build agent that gives them access to the level of abstraction that works best. It's a data point but this weekend (…

> ...and director of engineering for 10 years. I'm blown away.

It's always the CTO types who get most enthusiastic.

Re: Eight more months of agents

#146

Post by imron »

baq wrote: post #111
skydhash wrote: post #98

Earlier quoted context omitted.

Ok, I’ll bite. What’s there to learn that you can tie directly to an increase of productivity? I can say “learn how to use vim makeprg feature so that you can jump directly to errors reported by the build and tool” and it’s very clear where the ROI. But all the AI hypers are selling are hope, prayers, and rituals.

I’m not an AI hyper, I just don’t code manually anymore. Tickets take about as much time to close as before, but the code shipped now has higher test coverage, higher performance, better concurrency error handling, less follow-up refactor PRs, less escapes to staging/prod and better documentation; some of it is now also modeled in a model checker.

> I just don’t code manually anymore

I'm curious about what industry you are in and the tech stack you are using?

Re: Eight more months of agents

#147

Post by timr »

mattmanser wrote: post #122
0xbadcafebee wrote: post #117

Local models are decent now. Qwen3 coder is pretty good and decent speed. I use smaller models (qwen2.5:1.5b) with keyboard shortcuts and speech to text to ask for man page entries, and get 'em back faster than my internet connection and a "robust" frontier model does. And web search/RAG hides a multitude of sins. "Using anything other than the frontier models is actively harmful" - so how come I'm getting solid resu…

Have you used the frontier models recently? It's hard to communicate the difference the last 6 months has seen. We're at the point where copilot is irrelevant. Your way of working is irrelevant. Because that's not how you interact with coding AIs anymore, you're chatting with them about the code outside the IDE.

> Have you used the frontier models recently?

Yes.

> It's hard to communicate the difference the last 6 months has seen.

No, it isn't. The hypebeast discovered Claude code, but hasn't yet realized that the "let the model burn tokens with access to a shell" part is the key innovation, not the model itself.

I can (and do) use GH Copilot's "agent" mode with older generation models, and it's fine. There's no step function of improvement from one model to another, though there are always specific situations where one outperforms. My current go-to model for "sit and spin" mode is actually Grok, and I will splurge for tokens when that doesn't work. Tools and skills and blahblahblah are nice to have (and in fact, part of GH Copilot now), but not at all core to the process.

Re: Eight more months of agents

#148

Post by baq »

imron wrote: post #146
baq wrote: post #111

Earlier quoted context omitted.

I’m not an AI hyper, I just don’t code manually anymore. Tickets take about as much time to close as before, but the code shipped now has higher test coverage, higher performance, better concurrency error handling, less follow-up refactor PRs, less escapes to staging/prod and better documentation; some of it is now also modeled in a model checker.

> I just don’t code manually anymore I'm curious about what industry you are in and the tech stack you are using?

without revealing too much generic saas at non-toy scale, 95% TS + postgres + 5% a very long tail of other stuff.

Re: Eight more months of agents

#149

Post by baq »

skydhash wrote: post #114
baq wrote: post #111

Earlier quoted context omitted.

I’m not an AI hyper, I just don’t code manually anymore. Tickets take about as much time to close as before, but the code shipped now has higher test coverage, higher performance, better concurrency error handling, less follow-up refactor PRs, less escapes to staging/prod and better documentation; some of it is now also modeled in a model checker.

So the code was an unknown (to the world) X quality, but now it’s X+k quality? How does that help me exactly?

I don't care to be honest, it's up to you to learn to use the tool.
Post reply on HN