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

A few random notes from Claude coding quite a bit last few weeks

twitter.com

Post reply on HN
Print view View original

551–560 of 870 posts

Re: A few random notes from Claude coding quite a bit last few weeks

#551

Post by FeteCommuniste »

ed_mercer wrote: post #513
arh5451 wrote: post #507

Thank you for the really excellent summation. I echo your thought 1 to 1. I have found it more difficult to learn new languages or coding skills, because I am no longer forced to go through the painful slow grind of learning.

Does one ever still need to learn new languages or coding skills if an AI will be able to do it?

Probably not. But as someone who has learned a few languages, having to outsource a conversation to a machine will never not feel incredibly lame.

I doubt most people feel the same, though.

Re: A few random notes from Claude coding quite a bit last few weeks

#552

Post by akoboldfrying »

gregjor wrote: post #516
jwilliams wrote: post #353

> It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day. It's a "feel the AGI" moment to watch it struggle with something for a long time just to come out victorious 30 minutes later. This is true... Equally I've seen it dive into a rabbit hole, make…

I don't understand why anyone finds it interesting that a machine, or chatbot, never tires or gets demoralized. You have to anthromorphize the LLM before you can even think of those possibilities. A tractor never tires or gets demoralized either, because it can't. Chatbots don't "dive into a rabbit hole ... and then keep digging" because they have superhuman tenacity, they do it because that's what software does. If…

You're a machine. You're literally a wet, analog device converting some forms of energy into other forms just like any other machine as you work, rest, type out HN comments, etc. There is nothing special about the carbon atoms in your body -- there's no metadata attached to them marking them out as belonging to a Living Person. Other living-person-machines treat "you" differently than other clusters of atoms only because evolution has taught us that doing so is a mutually beneficial social convention.

So, since you're just a machine, any text you generate should be uninteresting to me -- correct?

Alternatively, could it be that a sufficiently complex and intricate machine can be interesting to observe in its own right?

Re: A few random notes from Claude coding quite a bit last few weeks

#553

Post by shaftoe »

throwup238 wrote: post #322
daxfohl wrote: post #176

Earlier quoted context omitted.

Businesses too. For two years it's been "throw everything into AI." But now that shit is getting real, are they really feeling so coy about letting AI run ahead of their engineering team's ability to manage it? How long will it be until we start seeing outages that just don't get resolved because the engineers have lost the plot?

How long until “the LLM did it it” is just as effective as “AWS is down, not my fault”?

If you’re just a gladhander for an algorithm, what are you really needed for?

Re: A few random notes from Claude coding quite a bit last few weeks

#554

Post by KronisLV »

carimura wrote: post #541
raducu wrote: post #453

Earlier quoted context omitted.

> let myself atrophy, run on a treadmill forever, for something You're lucky to afford the luxury not to atrophy. It's been almost 4 years since my last software job interview and I know the drills about preparing for one. Long before LLMs my skills naturally atrophy in my day job. I remember the good old days of J2ME of writing everything from scratch. Or writing some graph editor for universiry, or some speculative…

Ya I agree it's totally crazy.... but, do most app deployments need even half that stuff? I feel like most apps at most companies can just build an app and deploy it using some modern paas-like thing.

> I feel like most apps at most companies can just build an app and deploy it using some modern paas-like thing.

Most companies (in the global, not SV sense) would be well served by an app that runs in a Docker container in a VPS somewhere and has PostgreSQL and maybe Garage, RabbitMQ and Redis if you wanna get fancy, behind Apache2/Nginx/Caddy.

But obviously that’s not Serious Business™ and won’t give you zero downtime and high availability.

Though tbh most mid-size companies would also be okay with Docker Swarm or Nomad and the same software clustered and running behind HAProxy.

But that wouldn’t pad your CV so yeah.

Re: A few random notes from Claude coding quite a bit last few weeks

#555

Post by bob1029 »

I would agree that OAIs GPT-5 family of models is a phase change over GPT-4.

In the ChatGPT product this is not immediately obvious and many people would strongly argue their preference for 4. However, once you introduce several complex tools and make tool calling mandatory, the difference becomes stark.

I've got an agent loop that will fail nearly every time on GPT-4. It works sometimes, but definitely not enough to go to production. GPT-5 with reasoning set to minimal works 100% of the time. $200 worth of tokens and it still hasn't failed to select the proper sequence of tools. It sometimes gets the arguments to the tools incorrect, but it's always holding the right ones now.

I was very skeptical based upon prior experience but flipping between the models makes it clear there has been recent stepwise progress.

I'll probably be $500 deep in tokens before the end of the month. I could barely go $20 before I called bullshit on this stuff last time.

Re: A few random notes from Claude coding quite a bit last few weeks

#556

Post by suddenlybananas »

akoboldfrying wrote: post #552
gregjor wrote: post #516

Earlier quoted context omitted.

I don't understand why anyone finds it interesting that a machine, or chatbot, never tires or gets demoralized. You have to anthromorphize the LLM before you can even think of those possibilities. A tractor never tires or gets demoralized either, because it can't. Chatbots don't "dive into a rabbit hole ... and then keep digging" because they have superhuman tenacity, they do it because that's what software does. If…

You're a machine. You're literally a wet, analog device converting some forms of energy into other forms just like any other machine as you work, rest, type out HN comments, etc. There is nothing special about the carbon atoms in your body -- there's no metadata attached to them marking them out as belonging to a Living Person. Other living-person-machines treat "you" differently than other clusters of atoms only bec…

If humans are machines, they are still a subset of machines and they (among other animals) are the only ones who can be demotivated and so it is still a mistake to assume an entirely different kind of machine would have those properties.

>Other living-person-machines treat "you" differently than other clusters of atoms only because evolution has taught us that doing so is a mutually beneficial social convention

Evolution doesn't "teach" anything. It's just an emergent property of the fact that life reproduces (and sometimes doesn't). If you're going to have this radically reductionist view of humanity, you can't also treat evolution as having any kind of agency.

Re: A few random notes from Claude coding quite a bit last few weeks

#557

Post by webdevver »

xyzsparetimexyz wrote: post #244
maximedupre wrote: post #45

> It hurts the ego a bit but the power to operate over software in large "code actions" is just too net useful It does hurt, that's why all programmers now need an entrepreneurial mindset... you become if you use your skills + new AI power to build a business.

What about the people who dont want to be entrepreneurs?

permanent underclass...

Re: A few random notes from Claude coding quite a bit last few weeks

#558

Post by alansaber »

daxfohl wrote: post #65

I worry about the "brain atrophy" part, as I've felt this too. And not just atrophy, but even moreso I think it's evolving into "complacency". Like there have been multiple times now where I wanted the code to look a certain way, but it kept pulling back to the way it wanted to do things. Like if I had stated certain design goals recently it would adhere to them, but after a few iterations it would forget again and g…

"I wanted the code to look a certain way, but it kept pulling back to the way it wanted to do things."

I would argue this is ok for front-end. For back-end? very, very bad- if you can't get a usable output do it by hand.

Re: A few random notes from Claude coding quite a bit last few weeks

#559

Post by alansaber »

bob1029 wrote: post #555

I would agree that OAIs GPT-5 family of models is a phase change over GPT-4. In the ChatGPT product this is not immediately obvious and many people would strongly argue their preference for 4. However, once you introduce several complex tools and make tool calling mandatory, the difference becomes stark. I've got an agent loop that will fail nearly every time on GPT-4. It works sometimes, but definitely not enough to…

Pretty sure there wasn't extensive training on tooling beforehand. I mean, god, during GPT-3 even getting a reliable json output was a battle and there were dedicated packages for json inference.

Re: A few random notes from Claude coding quite a bit last few weeks

#560

Post by akoboldfrying »

ActorNightly wrote: post #431
kshri24 wrote: post #343

Agree with Karpathy's take. Finally a down to Earth analysis from a respected source in the AI space. I guess I'll be using slopocalypse a lot more now :) > I am bracing for 2026 as the year of the slopacolypse across all of github, substack, arxiv, X/instagram, and generally all digital media It has arrived. Github will be most affected thanks to git-terrorists at Apna College refusing to take down that stupid tutor…

The respect is unwarranted. He ran Teslas ML division, but still doesnt know what a simple kalman filter is (in the sense where he claimed that lidar would be hard to integrate with cameras).

The Kalman filter examples I've seen always involve estimating a very simple quantity, like the location of a single 3D point, from noisy sensors. It's clear how multiple estimates can be combined into a new estimate.

I'd guess that cameras on a self-driving car are trying to estimate something much more complex, something like 3D surfaces labeled with categories ("person", "traffic light", etc.). It's not obvious to me how estimates of such things from multiple sensors and predictions can be sensibly and efficiently combined to produce a better estimate. For example, what if there is a near red object in front of a distant red background, so that the camera estimates just a single object, but the lidar sees two?

Post reply on HN